diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,78218 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9999888074318652, + "eval_steps": 500, + "global_step": 11168, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 8.954054507806816e-05, + "grad_norm": 6.8605176727777835, + "learning_rate": 5.952380952380953e-08, + "loss": 1.3694, + "step": 1 + }, + { + "epoch": 0.00017908109015613632, + "grad_norm": 7.691125126718495, + "learning_rate": 1.1904761904761906e-07, + "loss": 1.4215, + "step": 2 + }, + { + "epoch": 0.0002686216352342045, + "grad_norm": 5.680496943421626, + "learning_rate": 1.7857142857142858e-07, + "loss": 1.3723, + "step": 3 + }, + { + "epoch": 0.00035816218031227263, + "grad_norm": 5.401625404885626, + "learning_rate": 2.3809523809523811e-07, + "loss": 1.3616, + "step": 4 + }, + { + "epoch": 0.0004477027253903408, + "grad_norm": 4.967220662606621, + "learning_rate": 2.9761904761904765e-07, + "loss": 1.3153, + "step": 5 + }, + { + "epoch": 0.000537243270468409, + "grad_norm": 6.1817393765434865, + "learning_rate": 3.5714285714285716e-07, + "loss": 1.3156, + "step": 6 + }, + { + "epoch": 0.0006267838155464771, + "grad_norm": 6.276733593598593, + "learning_rate": 4.1666666666666667e-07, + "loss": 1.3896, + "step": 7 + }, + { + "epoch": 0.0007163243606245453, + "grad_norm": 7.256473178370257, + "learning_rate": 4.7619047619047623e-07, + "loss": 1.4456, + "step": 8 + }, + { + "epoch": 0.0008058649057026135, + "grad_norm": 3.884565476184392, + "learning_rate": 5.357142857142857e-07, + "loss": 1.356, + "step": 9 + }, + { + "epoch": 0.0008954054507806816, + "grad_norm": 8.322504183965533, + "learning_rate": 5.952380952380953e-07, + "loss": 1.4909, + "step": 10 + }, + { + "epoch": 0.0009849459958587497, + "grad_norm": 6.815961533452488, + "learning_rate": 6.547619047619048e-07, + "loss": 1.4052, + "step": 11 + }, + { + "epoch": 0.001074486540936818, + "grad_norm": 5.162486223457818, + "learning_rate": 7.142857142857143e-07, + "loss": 1.3826, + "step": 12 + }, + { + "epoch": 0.0011640270860148862, + "grad_norm": 4.065629083093374, + "learning_rate": 7.738095238095239e-07, + "loss": 1.3456, + "step": 13 + }, + { + "epoch": 0.0012535676310929543, + "grad_norm": 5.967045434829423, + "learning_rate": 8.333333333333333e-07, + "loss": 1.314, + "step": 14 + }, + { + "epoch": 0.0013431081761710224, + "grad_norm": 6.255988604020014, + "learning_rate": 8.928571428571429e-07, + "loss": 1.2564, + "step": 15 + }, + { + "epoch": 0.0014326487212490905, + "grad_norm": 5.005226032915486, + "learning_rate": 9.523809523809525e-07, + "loss": 1.3065, + "step": 16 + }, + { + "epoch": 0.0015221892663271589, + "grad_norm": 5.42562394704774, + "learning_rate": 1.011904761904762e-06, + "loss": 1.3002, + "step": 17 + }, + { + "epoch": 0.001611729811405227, + "grad_norm": 4.772711542442117, + "learning_rate": 1.0714285714285714e-06, + "loss": 1.2308, + "step": 18 + }, + { + "epoch": 0.001701270356483295, + "grad_norm": 3.1174431394341227, + "learning_rate": 1.130952380952381e-06, + "loss": 1.27, + "step": 19 + }, + { + "epoch": 0.0017908109015613632, + "grad_norm": 4.0990299111949655, + "learning_rate": 1.1904761904761906e-06, + "loss": 1.2408, + "step": 20 + }, + { + "epoch": 0.0018803514466394313, + "grad_norm": 3.4441565958301013, + "learning_rate": 1.25e-06, + "loss": 1.2137, + "step": 21 + }, + { + "epoch": 0.0019698919917174994, + "grad_norm": 3.85140860102152, + "learning_rate": 1.3095238095238096e-06, + "loss": 1.1605, + "step": 22 + }, + { + "epoch": 0.0020594325367955676, + "grad_norm": 3.2980804912499093, + "learning_rate": 1.3690476190476193e-06, + "loss": 1.1968, + "step": 23 + }, + { + "epoch": 0.002148973081873636, + "grad_norm": 2.8501123951614105, + "learning_rate": 1.4285714285714286e-06, + "loss": 1.2073, + "step": 24 + }, + { + "epoch": 0.0022385136269517042, + "grad_norm": 1.9955484371820171, + "learning_rate": 1.4880952380952381e-06, + "loss": 1.1405, + "step": 25 + }, + { + "epoch": 0.0023280541720297723, + "grad_norm": 2.0796096933942554, + "learning_rate": 1.5476190476190479e-06, + "loss": 1.2414, + "step": 26 + }, + { + "epoch": 0.0024175947171078405, + "grad_norm": 1.9258413112172945, + "learning_rate": 1.6071428571428574e-06, + "loss": 1.1795, + "step": 27 + }, + { + "epoch": 0.0025071352621859086, + "grad_norm": 2.219156059146595, + "learning_rate": 1.6666666666666667e-06, + "loss": 1.1385, + "step": 28 + }, + { + "epoch": 0.0025966758072639767, + "grad_norm": 1.9782264643890668, + "learning_rate": 1.7261904761904764e-06, + "loss": 1.2193, + "step": 29 + }, + { + "epoch": 0.002686216352342045, + "grad_norm": 1.7202534544729537, + "learning_rate": 1.7857142857142859e-06, + "loss": 1.1381, + "step": 30 + }, + { + "epoch": 0.002775756897420113, + "grad_norm": 1.9188370445046954, + "learning_rate": 1.8452380952380954e-06, + "loss": 1.1534, + "step": 31 + }, + { + "epoch": 0.002865297442498181, + "grad_norm": 1.6628023890548072, + "learning_rate": 1.904761904761905e-06, + "loss": 1.111, + "step": 32 + }, + { + "epoch": 0.002954837987576249, + "grad_norm": 1.687574299864664, + "learning_rate": 1.9642857142857144e-06, + "loss": 1.1263, + "step": 33 + }, + { + "epoch": 0.0030443785326543177, + "grad_norm": 1.9568607394885413, + "learning_rate": 2.023809523809524e-06, + "loss": 1.117, + "step": 34 + }, + { + "epoch": 0.003133919077732386, + "grad_norm": 1.4443616128675203, + "learning_rate": 2.0833333333333334e-06, + "loss": 1.1181, + "step": 35 + }, + { + "epoch": 0.003223459622810454, + "grad_norm": 1.5247390243321048, + "learning_rate": 2.1428571428571427e-06, + "loss": 1.1419, + "step": 36 + }, + { + "epoch": 0.003313000167888522, + "grad_norm": 1.8050294358262133, + "learning_rate": 2.2023809523809525e-06, + "loss": 1.05, + "step": 37 + }, + { + "epoch": 0.00340254071296659, + "grad_norm": 1.659186619613239, + "learning_rate": 2.261904761904762e-06, + "loss": 1.0356, + "step": 38 + }, + { + "epoch": 0.0034920812580446583, + "grad_norm": 1.6504799209044219, + "learning_rate": 2.321428571428572e-06, + "loss": 1.0876, + "step": 39 + }, + { + "epoch": 0.0035816218031227264, + "grad_norm": 2.1681526883367717, + "learning_rate": 2.380952380952381e-06, + "loss": 1.0765, + "step": 40 + }, + { + "epoch": 0.0036711623482007945, + "grad_norm": 1.5610114447711314, + "learning_rate": 2.4404761904761905e-06, + "loss": 1.0003, + "step": 41 + }, + { + "epoch": 0.0037607028932788627, + "grad_norm": 1.8664840413808228, + "learning_rate": 2.5e-06, + "loss": 1.0805, + "step": 42 + }, + { + "epoch": 0.003850243438356931, + "grad_norm": 1.6464834387199405, + "learning_rate": 2.5595238095238095e-06, + "loss": 1.024, + "step": 43 + }, + { + "epoch": 0.003939783983434999, + "grad_norm": 1.832559754455683, + "learning_rate": 2.6190476190476192e-06, + "loss": 1.1215, + "step": 44 + }, + { + "epoch": 0.0040293245285130674, + "grad_norm": 1.5690875950142695, + "learning_rate": 2.6785714285714285e-06, + "loss": 1.07, + "step": 45 + }, + { + "epoch": 0.004118865073591135, + "grad_norm": 1.7754511705781226, + "learning_rate": 2.7380952380952387e-06, + "loss": 1.0774, + "step": 46 + }, + { + "epoch": 0.004208405618669204, + "grad_norm": 1.7547670602622754, + "learning_rate": 2.797619047619048e-06, + "loss": 1.1511, + "step": 47 + }, + { + "epoch": 0.004297946163747272, + "grad_norm": 1.3840214830218103, + "learning_rate": 2.8571428571428573e-06, + "loss": 1.0025, + "step": 48 + }, + { + "epoch": 0.00438748670882534, + "grad_norm": 1.479028052166697, + "learning_rate": 2.916666666666667e-06, + "loss": 1.0388, + "step": 49 + }, + { + "epoch": 0.0044770272539034085, + "grad_norm": 1.3895404661557715, + "learning_rate": 2.9761904761904763e-06, + "loss": 1.0936, + "step": 50 + }, + { + "epoch": 0.004566567798981476, + "grad_norm": 1.5593391246124038, + "learning_rate": 3.0357142857142856e-06, + "loss": 1.1312, + "step": 51 + }, + { + "epoch": 0.004656108344059545, + "grad_norm": 1.381786521648719, + "learning_rate": 3.0952380952380957e-06, + "loss": 1.0383, + "step": 52 + }, + { + "epoch": 0.004745648889137612, + "grad_norm": 1.6108949600051055, + "learning_rate": 3.154761904761905e-06, + "loss": 1.1068, + "step": 53 + }, + { + "epoch": 0.004835189434215681, + "grad_norm": 1.3335728546559724, + "learning_rate": 3.2142857142857147e-06, + "loss": 1.0878, + "step": 54 + }, + { + "epoch": 0.004924729979293749, + "grad_norm": 1.3893733824914392, + "learning_rate": 3.273809523809524e-06, + "loss": 1.0441, + "step": 55 + }, + { + "epoch": 0.005014270524371817, + "grad_norm": 1.591666225031461, + "learning_rate": 3.3333333333333333e-06, + "loss": 1.1077, + "step": 56 + }, + { + "epoch": 0.005103811069449885, + "grad_norm": 1.4876988140406033, + "learning_rate": 3.3928571428571435e-06, + "loss": 1.0835, + "step": 57 + }, + { + "epoch": 0.005193351614527953, + "grad_norm": 1.612063957917511, + "learning_rate": 3.4523809523809528e-06, + "loss": 1.0452, + "step": 58 + }, + { + "epoch": 0.005282892159606022, + "grad_norm": 1.6995990850825666, + "learning_rate": 3.511904761904762e-06, + "loss": 1.0326, + "step": 59 + }, + { + "epoch": 0.00537243270468409, + "grad_norm": 1.5465428512000507, + "learning_rate": 3.5714285714285718e-06, + "loss": 1.0428, + "step": 60 + }, + { + "epoch": 0.005461973249762158, + "grad_norm": 1.4221354638775416, + "learning_rate": 3.630952380952381e-06, + "loss": 1.0711, + "step": 61 + }, + { + "epoch": 0.005551513794840226, + "grad_norm": 1.5346769717891102, + "learning_rate": 3.690476190476191e-06, + "loss": 1.0837, + "step": 62 + }, + { + "epoch": 0.005641054339918294, + "grad_norm": 1.4159568033864736, + "learning_rate": 3.7500000000000005e-06, + "loss": 1.0506, + "step": 63 + }, + { + "epoch": 0.005730594884996362, + "grad_norm": 1.5690530218920364, + "learning_rate": 3.80952380952381e-06, + "loss": 1.0556, + "step": 64 + }, + { + "epoch": 0.005820135430074431, + "grad_norm": 1.5697504797030712, + "learning_rate": 3.869047619047619e-06, + "loss": 1.108, + "step": 65 + }, + { + "epoch": 0.005909675975152498, + "grad_norm": 1.8258299131084181, + "learning_rate": 3.928571428571429e-06, + "loss": 1.0756, + "step": 66 + }, + { + "epoch": 0.005999216520230567, + "grad_norm": 1.3728995166901874, + "learning_rate": 3.9880952380952386e-06, + "loss": 1.0429, + "step": 67 + }, + { + "epoch": 0.006088757065308635, + "grad_norm": 1.6939658639097959, + "learning_rate": 4.047619047619048e-06, + "loss": 1.0502, + "step": 68 + }, + { + "epoch": 0.006178297610386703, + "grad_norm": 1.4741960493495423, + "learning_rate": 4.107142857142857e-06, + "loss": 1.0528, + "step": 69 + }, + { + "epoch": 0.006267838155464772, + "grad_norm": 1.2853134828284618, + "learning_rate": 4.166666666666667e-06, + "loss": 1.0087, + "step": 70 + }, + { + "epoch": 0.006357378700542839, + "grad_norm": 1.4131068074499027, + "learning_rate": 4.226190476190477e-06, + "loss": 1.0035, + "step": 71 + }, + { + "epoch": 0.006446919245620908, + "grad_norm": 1.732671970636036, + "learning_rate": 4.2857142857142855e-06, + "loss": 1.0427, + "step": 72 + }, + { + "epoch": 0.006536459790698976, + "grad_norm": 1.6582392452806265, + "learning_rate": 4.345238095238096e-06, + "loss": 1.0438, + "step": 73 + }, + { + "epoch": 0.006626000335777044, + "grad_norm": 1.3182809895287744, + "learning_rate": 4.404761904761905e-06, + "loss": 1.0354, + "step": 74 + }, + { + "epoch": 0.006715540880855112, + "grad_norm": 1.3635845321776408, + "learning_rate": 4.464285714285715e-06, + "loss": 1.0494, + "step": 75 + }, + { + "epoch": 0.00680508142593318, + "grad_norm": 1.360498693077617, + "learning_rate": 4.523809523809524e-06, + "loss": 0.9935, + "step": 76 + }, + { + "epoch": 0.006894621971011249, + "grad_norm": 1.342450847470953, + "learning_rate": 4.583333333333333e-06, + "loss": 0.9944, + "step": 77 + }, + { + "epoch": 0.006984162516089317, + "grad_norm": 1.5740992165930958, + "learning_rate": 4.642857142857144e-06, + "loss": 0.9559, + "step": 78 + }, + { + "epoch": 0.007073703061167385, + "grad_norm": 1.3305886574115868, + "learning_rate": 4.702380952380953e-06, + "loss": 0.9313, + "step": 79 + }, + { + "epoch": 0.007163243606245453, + "grad_norm": 1.4627139160234712, + "learning_rate": 4.761904761904762e-06, + "loss": 1.0191, + "step": 80 + }, + { + "epoch": 0.007252784151323521, + "grad_norm": 1.5236143264045536, + "learning_rate": 4.821428571428572e-06, + "loss": 1.0295, + "step": 81 + }, + { + "epoch": 0.007342324696401589, + "grad_norm": 1.3070050715842225, + "learning_rate": 4.880952380952381e-06, + "loss": 1.0189, + "step": 82 + }, + { + "epoch": 0.007431865241479658, + "grad_norm": 1.33321070796309, + "learning_rate": 4.940476190476191e-06, + "loss": 1.0472, + "step": 83 + }, + { + "epoch": 0.007521405786557725, + "grad_norm": 1.2816371085172078, + "learning_rate": 5e-06, + "loss": 1.0327, + "step": 84 + }, + { + "epoch": 0.007610946331635794, + "grad_norm": 1.5235193144001336, + "learning_rate": 5.05952380952381e-06, + "loss": 1.0228, + "step": 85 + }, + { + "epoch": 0.007700486876713862, + "grad_norm": 1.3640744753358327, + "learning_rate": 5.119047619047619e-06, + "loss": 1.0084, + "step": 86 + }, + { + "epoch": 0.00779002742179193, + "grad_norm": 1.348787452974458, + "learning_rate": 5.1785714285714296e-06, + "loss": 0.9735, + "step": 87 + }, + { + "epoch": 0.007879567966869998, + "grad_norm": 1.276205787658554, + "learning_rate": 5.2380952380952384e-06, + "loss": 1.0244, + "step": 88 + }, + { + "epoch": 0.007969108511948066, + "grad_norm": 1.3052753646594772, + "learning_rate": 5.297619047619048e-06, + "loss": 0.9838, + "step": 89 + }, + { + "epoch": 0.008058649057026135, + "grad_norm": 1.3457428597610344, + "learning_rate": 5.357142857142857e-06, + "loss": 0.9628, + "step": 90 + }, + { + "epoch": 0.008148189602104203, + "grad_norm": 1.2868020672550435, + "learning_rate": 5.416666666666667e-06, + "loss": 0.937, + "step": 91 + }, + { + "epoch": 0.00823773014718227, + "grad_norm": 2.081956527692941, + "learning_rate": 5.476190476190477e-06, + "loss": 0.9857, + "step": 92 + }, + { + "epoch": 0.008327270692260339, + "grad_norm": 1.2536316087509864, + "learning_rate": 5.535714285714286e-06, + "loss": 1.0148, + "step": 93 + }, + { + "epoch": 0.008416811237338407, + "grad_norm": 1.6015988253413718, + "learning_rate": 5.595238095238096e-06, + "loss": 1.0322, + "step": 94 + }, + { + "epoch": 0.008506351782416476, + "grad_norm": 1.6548495158042813, + "learning_rate": 5.654761904761905e-06, + "loss": 1.0035, + "step": 95 + }, + { + "epoch": 0.008595892327494544, + "grad_norm": 1.4078823723272547, + "learning_rate": 5.7142857142857145e-06, + "loss": 0.9758, + "step": 96 + }, + { + "epoch": 0.008685432872572611, + "grad_norm": 1.5218636021557224, + "learning_rate": 5.773809523809523e-06, + "loss": 0.9634, + "step": 97 + }, + { + "epoch": 0.00877497341765068, + "grad_norm": 1.4411111232736358, + "learning_rate": 5.833333333333334e-06, + "loss": 0.9968, + "step": 98 + }, + { + "epoch": 0.008864513962728748, + "grad_norm": 1.4845544049865678, + "learning_rate": 5.892857142857144e-06, + "loss": 0.9755, + "step": 99 + }, + { + "epoch": 0.008954054507806817, + "grad_norm": 1.4805450172448043, + "learning_rate": 5.9523809523809525e-06, + "loss": 0.954, + "step": 100 + }, + { + "epoch": 0.009043595052884884, + "grad_norm": 1.3168462755841288, + "learning_rate": 6.011904761904762e-06, + "loss": 0.9991, + "step": 101 + }, + { + "epoch": 0.009133135597962952, + "grad_norm": 1.4411969742896522, + "learning_rate": 6.071428571428571e-06, + "loss": 0.9616, + "step": 102 + }, + { + "epoch": 0.00922267614304102, + "grad_norm": 1.4503808055083731, + "learning_rate": 6.130952380952382e-06, + "loss": 0.9989, + "step": 103 + }, + { + "epoch": 0.00931221668811909, + "grad_norm": 1.441168610056887, + "learning_rate": 6.1904761904761914e-06, + "loss": 1.0268, + "step": 104 + }, + { + "epoch": 0.009401757233197158, + "grad_norm": 1.390408253303954, + "learning_rate": 6.25e-06, + "loss": 0.9328, + "step": 105 + }, + { + "epoch": 0.009491297778275225, + "grad_norm": 1.3895700800718895, + "learning_rate": 6.30952380952381e-06, + "loss": 1.008, + "step": 106 + }, + { + "epoch": 0.009580838323353293, + "grad_norm": 1.4775664954059724, + "learning_rate": 6.369047619047619e-06, + "loss": 1.0632, + "step": 107 + }, + { + "epoch": 0.009670378868431362, + "grad_norm": 1.550361713976216, + "learning_rate": 6.4285714285714295e-06, + "loss": 0.9601, + "step": 108 + }, + { + "epoch": 0.00975991941350943, + "grad_norm": 1.3078283659340315, + "learning_rate": 6.488095238095239e-06, + "loss": 1.0247, + "step": 109 + }, + { + "epoch": 0.009849459958587497, + "grad_norm": 1.322044169233702, + "learning_rate": 6.547619047619048e-06, + "loss": 0.9589, + "step": 110 + }, + { + "epoch": 0.009939000503665566, + "grad_norm": 1.403959589278741, + "learning_rate": 6.607142857142858e-06, + "loss": 1.0003, + "step": 111 + }, + { + "epoch": 0.010028541048743634, + "grad_norm": 1.4502321635121647, + "learning_rate": 6.666666666666667e-06, + "loss": 1.005, + "step": 112 + }, + { + "epoch": 0.010118081593821703, + "grad_norm": 1.4420768567846465, + "learning_rate": 6.726190476190477e-06, + "loss": 0.9415, + "step": 113 + }, + { + "epoch": 0.01020762213889977, + "grad_norm": 1.4698692117387229, + "learning_rate": 6.785714285714287e-06, + "loss": 1.0095, + "step": 114 + }, + { + "epoch": 0.010297162683977838, + "grad_norm": 1.3241258190333822, + "learning_rate": 6.845238095238096e-06, + "loss": 0.9819, + "step": 115 + }, + { + "epoch": 0.010386703229055907, + "grad_norm": 1.5308240430048938, + "learning_rate": 6.9047619047619055e-06, + "loss": 1.0196, + "step": 116 + }, + { + "epoch": 0.010476243774133975, + "grad_norm": 1.3400065057088364, + "learning_rate": 6.964285714285714e-06, + "loss": 0.9778, + "step": 117 + }, + { + "epoch": 0.010565784319212044, + "grad_norm": 1.3984498071873686, + "learning_rate": 7.023809523809524e-06, + "loss": 0.9846, + "step": 118 + }, + { + "epoch": 0.01065532486429011, + "grad_norm": 1.425113759601797, + "learning_rate": 7.083333333333335e-06, + "loss": 0.9965, + "step": 119 + }, + { + "epoch": 0.01074486540936818, + "grad_norm": 1.3770492080848322, + "learning_rate": 7.1428571428571436e-06, + "loss": 1.024, + "step": 120 + }, + { + "epoch": 0.010834405954446248, + "grad_norm": 1.4459962866429865, + "learning_rate": 7.202380952380953e-06, + "loss": 1.0129, + "step": 121 + }, + { + "epoch": 0.010923946499524316, + "grad_norm": 1.3100912174599022, + "learning_rate": 7.261904761904762e-06, + "loss": 0.9614, + "step": 122 + }, + { + "epoch": 0.011013487044602383, + "grad_norm": 1.5305042076623463, + "learning_rate": 7.321428571428572e-06, + "loss": 0.981, + "step": 123 + }, + { + "epoch": 0.011103027589680452, + "grad_norm": 1.2433333731355567, + "learning_rate": 7.380952380952382e-06, + "loss": 0.9791, + "step": 124 + }, + { + "epoch": 0.01119256813475852, + "grad_norm": 1.3889845259093059, + "learning_rate": 7.440476190476191e-06, + "loss": 0.9765, + "step": 125 + }, + { + "epoch": 0.011282108679836589, + "grad_norm": 1.502651313820656, + "learning_rate": 7.500000000000001e-06, + "loss": 1.0094, + "step": 126 + }, + { + "epoch": 0.011371649224914657, + "grad_norm": 1.4771171422373752, + "learning_rate": 7.55952380952381e-06, + "loss": 0.992, + "step": 127 + }, + { + "epoch": 0.011461189769992724, + "grad_norm": 1.2753017174252659, + "learning_rate": 7.61904761904762e-06, + "loss": 1.0145, + "step": 128 + }, + { + "epoch": 0.011550730315070793, + "grad_norm": 1.3288798388981164, + "learning_rate": 7.67857142857143e-06, + "loss": 0.965, + "step": 129 + }, + { + "epoch": 0.011640270860148861, + "grad_norm": 1.3896000789531564, + "learning_rate": 7.738095238095238e-06, + "loss": 0.9574, + "step": 130 + }, + { + "epoch": 0.01172981140522693, + "grad_norm": 1.400636887292073, + "learning_rate": 7.797619047619049e-06, + "loss": 0.9677, + "step": 131 + }, + { + "epoch": 0.011819351950304997, + "grad_norm": 1.4834782043503996, + "learning_rate": 7.857142857142858e-06, + "loss": 0.9613, + "step": 132 + }, + { + "epoch": 0.011908892495383065, + "grad_norm": 1.4226787998801091, + "learning_rate": 7.916666666666667e-06, + "loss": 0.9504, + "step": 133 + }, + { + "epoch": 0.011998433040461134, + "grad_norm": 1.5098653254615386, + "learning_rate": 7.976190476190477e-06, + "loss": 0.9955, + "step": 134 + }, + { + "epoch": 0.012087973585539202, + "grad_norm": 1.2705414690639203, + "learning_rate": 8.035714285714286e-06, + "loss": 0.9821, + "step": 135 + }, + { + "epoch": 0.01217751413061727, + "grad_norm": 1.3407959556633955, + "learning_rate": 8.095238095238097e-06, + "loss": 0.9363, + "step": 136 + }, + { + "epoch": 0.012267054675695338, + "grad_norm": 1.4441549278470907, + "learning_rate": 8.154761904761905e-06, + "loss": 0.9111, + "step": 137 + }, + { + "epoch": 0.012356595220773406, + "grad_norm": 1.4028581785408012, + "learning_rate": 8.214285714285714e-06, + "loss": 0.9877, + "step": 138 + }, + { + "epoch": 0.012446135765851475, + "grad_norm": 1.398569645765137, + "learning_rate": 8.273809523809523e-06, + "loss": 1.0216, + "step": 139 + }, + { + "epoch": 0.012535676310929543, + "grad_norm": 1.2531219966896094, + "learning_rate": 8.333333333333334e-06, + "loss": 0.9097, + "step": 140 + }, + { + "epoch": 0.01262521685600761, + "grad_norm": 1.3940632443651146, + "learning_rate": 8.392857142857144e-06, + "loss": 0.9529, + "step": 141 + }, + { + "epoch": 0.012714757401085679, + "grad_norm": 1.505737845025738, + "learning_rate": 8.452380952380953e-06, + "loss": 0.9739, + "step": 142 + }, + { + "epoch": 0.012804297946163747, + "grad_norm": 1.4344630058806271, + "learning_rate": 8.511904761904762e-06, + "loss": 1.04, + "step": 143 + }, + { + "epoch": 0.012893838491241816, + "grad_norm": 1.361451985668616, + "learning_rate": 8.571428571428571e-06, + "loss": 1.006, + "step": 144 + }, + { + "epoch": 0.012983379036319884, + "grad_norm": 1.3657036535038112, + "learning_rate": 8.630952380952381e-06, + "loss": 0.9894, + "step": 145 + }, + { + "epoch": 0.013072919581397951, + "grad_norm": 1.4027313732363873, + "learning_rate": 8.690476190476192e-06, + "loss": 0.9422, + "step": 146 + }, + { + "epoch": 0.01316246012647602, + "grad_norm": 1.339486554692635, + "learning_rate": 8.750000000000001e-06, + "loss": 0.946, + "step": 147 + }, + { + "epoch": 0.013252000671554088, + "grad_norm": 1.2207375784735799, + "learning_rate": 8.80952380952381e-06, + "loss": 0.9685, + "step": 148 + }, + { + "epoch": 0.013341541216632157, + "grad_norm": 1.2898935942769207, + "learning_rate": 8.869047619047619e-06, + "loss": 0.9228, + "step": 149 + }, + { + "epoch": 0.013431081761710224, + "grad_norm": 1.4123772858280599, + "learning_rate": 8.92857142857143e-06, + "loss": 1.0187, + "step": 150 + }, + { + "epoch": 0.013520622306788292, + "grad_norm": 1.2596251148002016, + "learning_rate": 8.98809523809524e-06, + "loss": 0.9466, + "step": 151 + }, + { + "epoch": 0.01361016285186636, + "grad_norm": 1.3755666142514171, + "learning_rate": 9.047619047619049e-06, + "loss": 0.9445, + "step": 152 + }, + { + "epoch": 0.01369970339694443, + "grad_norm": 1.391555104218961, + "learning_rate": 9.107142857142858e-06, + "loss": 1.0195, + "step": 153 + }, + { + "epoch": 0.013789243942022498, + "grad_norm": 1.2783454670190193, + "learning_rate": 9.166666666666666e-06, + "loss": 1.0155, + "step": 154 + }, + { + "epoch": 0.013878784487100565, + "grad_norm": 1.3063039982513691, + "learning_rate": 9.226190476190477e-06, + "loss": 0.9396, + "step": 155 + }, + { + "epoch": 0.013968325032178633, + "grad_norm": 1.2938757442437152, + "learning_rate": 9.285714285714288e-06, + "loss": 1.0104, + "step": 156 + }, + { + "epoch": 0.014057865577256702, + "grad_norm": 1.3808606773264782, + "learning_rate": 9.345238095238096e-06, + "loss": 0.9891, + "step": 157 + }, + { + "epoch": 0.01414740612233477, + "grad_norm": 1.2614854087003178, + "learning_rate": 9.404761904761905e-06, + "loss": 0.9717, + "step": 158 + }, + { + "epoch": 0.014236946667412837, + "grad_norm": 1.2642808998858541, + "learning_rate": 9.464285714285714e-06, + "loss": 0.9344, + "step": 159 + }, + { + "epoch": 0.014326487212490906, + "grad_norm": 1.2302383357152784, + "learning_rate": 9.523809523809525e-06, + "loss": 1.0114, + "step": 160 + }, + { + "epoch": 0.014416027757568974, + "grad_norm": 1.255141844023732, + "learning_rate": 9.583333333333335e-06, + "loss": 0.9564, + "step": 161 + }, + { + "epoch": 0.014505568302647043, + "grad_norm": 1.3698214664865263, + "learning_rate": 9.642857142857144e-06, + "loss": 0.9686, + "step": 162 + }, + { + "epoch": 0.014595108847725111, + "grad_norm": 1.3419018411191843, + "learning_rate": 9.702380952380953e-06, + "loss": 0.9748, + "step": 163 + }, + { + "epoch": 0.014684649392803178, + "grad_norm": 1.1614847734170037, + "learning_rate": 9.761904761904762e-06, + "loss": 0.9161, + "step": 164 + }, + { + "epoch": 0.014774189937881247, + "grad_norm": 1.368116245539826, + "learning_rate": 9.821428571428573e-06, + "loss": 1.0298, + "step": 165 + }, + { + "epoch": 0.014863730482959315, + "grad_norm": 1.4199667158707043, + "learning_rate": 9.880952380952381e-06, + "loss": 0.9031, + "step": 166 + }, + { + "epoch": 0.014953271028037384, + "grad_norm": 1.4252433399103757, + "learning_rate": 9.940476190476192e-06, + "loss": 0.9912, + "step": 167 + }, + { + "epoch": 0.01504281157311545, + "grad_norm": 1.3896954573715155, + "learning_rate": 1e-05, + "loss": 0.938, + "step": 168 + }, + { + "epoch": 0.01513235211819352, + "grad_norm": 1.3013901404188426, + "learning_rate": 1.005952380952381e-05, + "loss": 0.9786, + "step": 169 + }, + { + "epoch": 0.015221892663271588, + "grad_norm": 1.3296804047070019, + "learning_rate": 1.011904761904762e-05, + "loss": 1.0077, + "step": 170 + }, + { + "epoch": 0.015311433208349656, + "grad_norm": 1.3918359833476754, + "learning_rate": 1.0178571428571429e-05, + "loss": 0.9493, + "step": 171 + }, + { + "epoch": 0.015400973753427725, + "grad_norm": 1.283405187122454, + "learning_rate": 1.0238095238095238e-05, + "loss": 0.9433, + "step": 172 + }, + { + "epoch": 0.015490514298505792, + "grad_norm": 1.3750965752510205, + "learning_rate": 1.0297619047619047e-05, + "loss": 0.991, + "step": 173 + }, + { + "epoch": 0.01558005484358386, + "grad_norm": 1.300250340319829, + "learning_rate": 1.0357142857142859e-05, + "loss": 0.9566, + "step": 174 + }, + { + "epoch": 0.015669595388661927, + "grad_norm": 1.1949688314302664, + "learning_rate": 1.0416666666666668e-05, + "loss": 0.8441, + "step": 175 + }, + { + "epoch": 0.015759135933739996, + "grad_norm": 1.321743869216069, + "learning_rate": 1.0476190476190477e-05, + "loss": 0.909, + "step": 176 + }, + { + "epoch": 0.015848676478818064, + "grad_norm": 1.3363798807219291, + "learning_rate": 1.0535714285714287e-05, + "loss": 0.905, + "step": 177 + }, + { + "epoch": 0.015938217023896133, + "grad_norm": 1.4593971998537487, + "learning_rate": 1.0595238095238096e-05, + "loss": 0.938, + "step": 178 + }, + { + "epoch": 0.0160277575689742, + "grad_norm": 1.445421099859946, + "learning_rate": 1.0654761904761905e-05, + "loss": 0.9366, + "step": 179 + }, + { + "epoch": 0.01611729811405227, + "grad_norm": 1.3614058430879477, + "learning_rate": 1.0714285714285714e-05, + "loss": 1.0041, + "step": 180 + }, + { + "epoch": 0.01620683865913034, + "grad_norm": 1.5686440239591053, + "learning_rate": 1.0773809523809525e-05, + "loss": 0.9215, + "step": 181 + }, + { + "epoch": 0.016296379204208407, + "grad_norm": 1.2934528124033098, + "learning_rate": 1.0833333333333334e-05, + "loss": 0.9991, + "step": 182 + }, + { + "epoch": 0.016385919749286475, + "grad_norm": 1.2021664875612033, + "learning_rate": 1.0892857142857142e-05, + "loss": 0.9283, + "step": 183 + }, + { + "epoch": 0.01647546029436454, + "grad_norm": 1.3767762471746128, + "learning_rate": 1.0952380952380955e-05, + "loss": 0.9849, + "step": 184 + }, + { + "epoch": 0.01656500083944261, + "grad_norm": 1.2164130350107607, + "learning_rate": 1.1011904761904764e-05, + "loss": 0.9246, + "step": 185 + }, + { + "epoch": 0.016654541384520678, + "grad_norm": 1.368032712333836, + "learning_rate": 1.1071428571428572e-05, + "loss": 0.9453, + "step": 186 + }, + { + "epoch": 0.016744081929598746, + "grad_norm": 1.3469222988219791, + "learning_rate": 1.1130952380952383e-05, + "loss": 1.0545, + "step": 187 + }, + { + "epoch": 0.016833622474676815, + "grad_norm": 1.8300489265056759, + "learning_rate": 1.1190476190476192e-05, + "loss": 0.8654, + "step": 188 + }, + { + "epoch": 0.016923163019754883, + "grad_norm": 1.3505891905752436, + "learning_rate": 1.125e-05, + "loss": 0.9516, + "step": 189 + }, + { + "epoch": 0.017012703564832952, + "grad_norm": 1.4346732544846332, + "learning_rate": 1.130952380952381e-05, + "loss": 0.9323, + "step": 190 + }, + { + "epoch": 0.01710224410991102, + "grad_norm": 1.4145336071053909, + "learning_rate": 1.136904761904762e-05, + "loss": 0.9982, + "step": 191 + }, + { + "epoch": 0.01719178465498909, + "grad_norm": 1.3729621826328517, + "learning_rate": 1.1428571428571429e-05, + "loss": 0.9534, + "step": 192 + }, + { + "epoch": 0.017281325200067154, + "grad_norm": 1.3545358955770777, + "learning_rate": 1.1488095238095238e-05, + "loss": 0.9654, + "step": 193 + }, + { + "epoch": 0.017370865745145223, + "grad_norm": 1.2958480407714497, + "learning_rate": 1.1547619047619047e-05, + "loss": 0.9709, + "step": 194 + }, + { + "epoch": 0.01746040629022329, + "grad_norm": 1.417419616391308, + "learning_rate": 1.1607142857142859e-05, + "loss": 0.9933, + "step": 195 + }, + { + "epoch": 0.01754994683530136, + "grad_norm": 1.2187334395358913, + "learning_rate": 1.1666666666666668e-05, + "loss": 0.9824, + "step": 196 + }, + { + "epoch": 0.017639487380379428, + "grad_norm": 1.382354810818814, + "learning_rate": 1.1726190476190478e-05, + "loss": 0.9633, + "step": 197 + }, + { + "epoch": 0.017729027925457497, + "grad_norm": 1.4095044078409356, + "learning_rate": 1.1785714285714287e-05, + "loss": 0.947, + "step": 198 + }, + { + "epoch": 0.017818568470535565, + "grad_norm": 1.3356052977273825, + "learning_rate": 1.1845238095238096e-05, + "loss": 0.994, + "step": 199 + }, + { + "epoch": 0.017908109015613634, + "grad_norm": 1.4655877002540365, + "learning_rate": 1.1904761904761905e-05, + "loss": 0.9436, + "step": 200 + }, + { + "epoch": 0.017997649560691702, + "grad_norm": 1.488756592776806, + "learning_rate": 1.1964285714285716e-05, + "loss": 0.9966, + "step": 201 + }, + { + "epoch": 0.018087190105769767, + "grad_norm": 1.3525701096076792, + "learning_rate": 1.2023809523809525e-05, + "loss": 0.9324, + "step": 202 + }, + { + "epoch": 0.018176730650847836, + "grad_norm": 1.4121435139307525, + "learning_rate": 1.2083333333333333e-05, + "loss": 0.9448, + "step": 203 + }, + { + "epoch": 0.018266271195925905, + "grad_norm": 1.3258960013505587, + "learning_rate": 1.2142857142857142e-05, + "loss": 1.0262, + "step": 204 + }, + { + "epoch": 0.018355811741003973, + "grad_norm": 1.1839792345048852, + "learning_rate": 1.2202380952380955e-05, + "loss": 0.8914, + "step": 205 + }, + { + "epoch": 0.01844535228608204, + "grad_norm": 1.3564771867906358, + "learning_rate": 1.2261904761904763e-05, + "loss": 0.8948, + "step": 206 + }, + { + "epoch": 0.01853489283116011, + "grad_norm": 1.6777434640215823, + "learning_rate": 1.2321428571428572e-05, + "loss": 0.9361, + "step": 207 + }, + { + "epoch": 0.01862443337623818, + "grad_norm": 1.2414949636325754, + "learning_rate": 1.2380952380952383e-05, + "loss": 0.981, + "step": 208 + }, + { + "epoch": 0.018713973921316247, + "grad_norm": 1.350636107950117, + "learning_rate": 1.2440476190476192e-05, + "loss": 0.9689, + "step": 209 + }, + { + "epoch": 0.018803514466394316, + "grad_norm": 1.33427149141748, + "learning_rate": 1.25e-05, + "loss": 0.9206, + "step": 210 + }, + { + "epoch": 0.01889305501147238, + "grad_norm": 1.1998127387502966, + "learning_rate": 1.2559523809523811e-05, + "loss": 0.9281, + "step": 211 + }, + { + "epoch": 0.01898259555655045, + "grad_norm": 1.3476198056947557, + "learning_rate": 1.261904761904762e-05, + "loss": 0.934, + "step": 212 + }, + { + "epoch": 0.019072136101628518, + "grad_norm": 1.3741871404916675, + "learning_rate": 1.2678571428571429e-05, + "loss": 1.0093, + "step": 213 + }, + { + "epoch": 0.019161676646706587, + "grad_norm": 1.2270861175633545, + "learning_rate": 1.2738095238095238e-05, + "loss": 0.9155, + "step": 214 + }, + { + "epoch": 0.019251217191784655, + "grad_norm": 1.2452907840956695, + "learning_rate": 1.2797619047619048e-05, + "loss": 0.9528, + "step": 215 + }, + { + "epoch": 0.019340757736862724, + "grad_norm": 1.3856294183070534, + "learning_rate": 1.2857142857142859e-05, + "loss": 0.957, + "step": 216 + }, + { + "epoch": 0.019430298281940792, + "grad_norm": 1.4644668358733208, + "learning_rate": 1.2916666666666668e-05, + "loss": 0.9731, + "step": 217 + }, + { + "epoch": 0.01951983882701886, + "grad_norm": 1.2869545198770278, + "learning_rate": 1.2976190476190478e-05, + "loss": 0.9313, + "step": 218 + }, + { + "epoch": 0.01960937937209693, + "grad_norm": 1.233394188597046, + "learning_rate": 1.3035714285714287e-05, + "loss": 0.9386, + "step": 219 + }, + { + "epoch": 0.019698919917174994, + "grad_norm": 1.1779294605283495, + "learning_rate": 1.3095238095238096e-05, + "loss": 0.8988, + "step": 220 + }, + { + "epoch": 0.019788460462253063, + "grad_norm": 1.3649114963818465, + "learning_rate": 1.3154761904761905e-05, + "loss": 0.9694, + "step": 221 + }, + { + "epoch": 0.01987800100733113, + "grad_norm": 1.2929423505249116, + "learning_rate": 1.3214285714285716e-05, + "loss": 0.9131, + "step": 222 + }, + { + "epoch": 0.0199675415524092, + "grad_norm": 1.2651829321222632, + "learning_rate": 1.3273809523809524e-05, + "loss": 1.0312, + "step": 223 + }, + { + "epoch": 0.02005708209748727, + "grad_norm": 1.4679051518959685, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.9725, + "step": 224 + }, + { + "epoch": 0.020146622642565337, + "grad_norm": 1.2523234262550003, + "learning_rate": 1.3392857142857142e-05, + "loss": 0.9389, + "step": 225 + }, + { + "epoch": 0.020236163187643406, + "grad_norm": 1.2768673189458624, + "learning_rate": 1.3452380952380954e-05, + "loss": 0.9746, + "step": 226 + }, + { + "epoch": 0.020325703732721474, + "grad_norm": 1.3282583630031086, + "learning_rate": 1.3511904761904763e-05, + "loss": 0.9726, + "step": 227 + }, + { + "epoch": 0.02041524427779954, + "grad_norm": 1.245528315258455, + "learning_rate": 1.3571428571428574e-05, + "loss": 0.9756, + "step": 228 + }, + { + "epoch": 0.020504784822877608, + "grad_norm": 1.2482999509375599, + "learning_rate": 1.3630952380952383e-05, + "loss": 0.9426, + "step": 229 + }, + { + "epoch": 0.020594325367955676, + "grad_norm": 1.2269661387783157, + "learning_rate": 1.3690476190476192e-05, + "loss": 0.8852, + "step": 230 + }, + { + "epoch": 0.020683865913033745, + "grad_norm": 1.2918128081032816, + "learning_rate": 1.375e-05, + "loss": 0.8946, + "step": 231 + }, + { + "epoch": 0.020773406458111814, + "grad_norm": 1.294616303481284, + "learning_rate": 1.3809523809523811e-05, + "loss": 0.9958, + "step": 232 + }, + { + "epoch": 0.020862947003189882, + "grad_norm": 1.3451743251615973, + "learning_rate": 1.386904761904762e-05, + "loss": 0.9277, + "step": 233 + }, + { + "epoch": 0.02095248754826795, + "grad_norm": 1.3030767633167066, + "learning_rate": 1.3928571428571429e-05, + "loss": 0.9886, + "step": 234 + }, + { + "epoch": 0.02104202809334602, + "grad_norm": 1.5956175984393084, + "learning_rate": 1.3988095238095238e-05, + "loss": 0.9578, + "step": 235 + }, + { + "epoch": 0.021131568638424088, + "grad_norm": 1.6042283010809089, + "learning_rate": 1.4047619047619048e-05, + "loss": 0.9404, + "step": 236 + }, + { + "epoch": 0.021221109183502153, + "grad_norm": 1.4714817421979074, + "learning_rate": 1.4107142857142859e-05, + "loss": 0.906, + "step": 237 + }, + { + "epoch": 0.02131064972858022, + "grad_norm": 1.1734285774248108, + "learning_rate": 1.416666666666667e-05, + "loss": 0.938, + "step": 238 + }, + { + "epoch": 0.02140019027365829, + "grad_norm": 1.2504049411129798, + "learning_rate": 1.4226190476190478e-05, + "loss": 0.964, + "step": 239 + }, + { + "epoch": 0.02148973081873636, + "grad_norm": 1.348650134376146, + "learning_rate": 1.4285714285714287e-05, + "loss": 0.9242, + "step": 240 + }, + { + "epoch": 0.021579271363814427, + "grad_norm": 1.125410541920277, + "learning_rate": 1.4345238095238096e-05, + "loss": 0.9829, + "step": 241 + }, + { + "epoch": 0.021668811908892496, + "grad_norm": 1.2425939596990612, + "learning_rate": 1.4404761904761907e-05, + "loss": 0.9329, + "step": 242 + }, + { + "epoch": 0.021758352453970564, + "grad_norm": 1.2947312519312828, + "learning_rate": 1.4464285714285715e-05, + "loss": 0.9172, + "step": 243 + }, + { + "epoch": 0.021847892999048633, + "grad_norm": 1.2421461784241594, + "learning_rate": 1.4523809523809524e-05, + "loss": 0.938, + "step": 244 + }, + { + "epoch": 0.0219374335441267, + "grad_norm": 1.2572211370448974, + "learning_rate": 1.4583333333333333e-05, + "loss": 0.9676, + "step": 245 + }, + { + "epoch": 0.022026974089204766, + "grad_norm": 1.254642676133443, + "learning_rate": 1.4642857142857144e-05, + "loss": 0.9531, + "step": 246 + }, + { + "epoch": 0.022116514634282835, + "grad_norm": 1.3851200771479248, + "learning_rate": 1.4702380952380954e-05, + "loss": 1.0124, + "step": 247 + }, + { + "epoch": 0.022206055179360903, + "grad_norm": 1.4017617822521042, + "learning_rate": 1.4761904761904763e-05, + "loss": 0.8903, + "step": 248 + }, + { + "epoch": 0.022295595724438972, + "grad_norm": 1.1560384690623424, + "learning_rate": 1.4821428571428574e-05, + "loss": 0.9086, + "step": 249 + }, + { + "epoch": 0.02238513626951704, + "grad_norm": 1.4586151690902063, + "learning_rate": 1.4880952380952383e-05, + "loss": 0.9175, + "step": 250 + }, + { + "epoch": 0.02247467681459511, + "grad_norm": 1.2338910970784036, + "learning_rate": 1.4940476190476192e-05, + "loss": 0.9879, + "step": 251 + }, + { + "epoch": 0.022564217359673178, + "grad_norm": 1.3922914075241761, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.9513, + "step": 252 + }, + { + "epoch": 0.022653757904751246, + "grad_norm": 1.3300603379010327, + "learning_rate": 1.5059523809523811e-05, + "loss": 1.0006, + "step": 253 + }, + { + "epoch": 0.022743298449829315, + "grad_norm": 1.5273512053589549, + "learning_rate": 1.511904761904762e-05, + "loss": 0.9738, + "step": 254 + }, + { + "epoch": 0.02283283899490738, + "grad_norm": 1.396678207050215, + "learning_rate": 1.5178571428571429e-05, + "loss": 0.8837, + "step": 255 + }, + { + "epoch": 0.02292237953998545, + "grad_norm": 1.2861620665630484, + "learning_rate": 1.523809523809524e-05, + "loss": 0.9543, + "step": 256 + }, + { + "epoch": 0.023011920085063517, + "grad_norm": 1.4691272216286264, + "learning_rate": 1.5297619047619046e-05, + "loss": 0.9201, + "step": 257 + }, + { + "epoch": 0.023101460630141585, + "grad_norm": 1.2754063399808757, + "learning_rate": 1.535714285714286e-05, + "loss": 0.9442, + "step": 258 + }, + { + "epoch": 0.023191001175219654, + "grad_norm": 1.3005351288923879, + "learning_rate": 1.5416666666666668e-05, + "loss": 1.001, + "step": 259 + }, + { + "epoch": 0.023280541720297723, + "grad_norm": 1.2515896550362557, + "learning_rate": 1.5476190476190476e-05, + "loss": 0.9559, + "step": 260 + }, + { + "epoch": 0.02337008226537579, + "grad_norm": 1.237838957465389, + "learning_rate": 1.553571428571429e-05, + "loss": 0.9448, + "step": 261 + }, + { + "epoch": 0.02345962281045386, + "grad_norm": 1.2897409321131819, + "learning_rate": 1.5595238095238098e-05, + "loss": 0.9845, + "step": 262 + }, + { + "epoch": 0.023549163355531928, + "grad_norm": 1.17906683487718, + "learning_rate": 1.5654761904761906e-05, + "loss": 1.0076, + "step": 263 + }, + { + "epoch": 0.023638703900609993, + "grad_norm": 1.2490508619903085, + "learning_rate": 1.5714285714285715e-05, + "loss": 0.9666, + "step": 264 + }, + { + "epoch": 0.023728244445688062, + "grad_norm": 1.223240675225147, + "learning_rate": 1.5773809523809524e-05, + "loss": 0.9171, + "step": 265 + }, + { + "epoch": 0.02381778499076613, + "grad_norm": 1.1985738977030302, + "learning_rate": 1.5833333333333333e-05, + "loss": 0.9431, + "step": 266 + }, + { + "epoch": 0.0239073255358442, + "grad_norm": 1.3688562148592254, + "learning_rate": 1.5892857142857142e-05, + "loss": 0.9309, + "step": 267 + }, + { + "epoch": 0.023996866080922268, + "grad_norm": 1.3354654095343694, + "learning_rate": 1.5952380952380954e-05, + "loss": 0.9838, + "step": 268 + }, + { + "epoch": 0.024086406626000336, + "grad_norm": 1.3708472732213348, + "learning_rate": 1.6011904761904763e-05, + "loss": 1.0132, + "step": 269 + }, + { + "epoch": 0.024175947171078405, + "grad_norm": 1.268922384284169, + "learning_rate": 1.6071428571428572e-05, + "loss": 0.9706, + "step": 270 + }, + { + "epoch": 0.024265487716156473, + "grad_norm": 1.2617017544944156, + "learning_rate": 1.6130952380952384e-05, + "loss": 0.8745, + "step": 271 + }, + { + "epoch": 0.02435502826123454, + "grad_norm": 1.139790716312867, + "learning_rate": 1.6190476190476193e-05, + "loss": 0.9588, + "step": 272 + }, + { + "epoch": 0.024444568806312607, + "grad_norm": 1.1818596979066731, + "learning_rate": 1.6250000000000002e-05, + "loss": 0.9524, + "step": 273 + }, + { + "epoch": 0.024534109351390675, + "grad_norm": 1.2738117528692605, + "learning_rate": 1.630952380952381e-05, + "loss": 0.9619, + "step": 274 + }, + { + "epoch": 0.024623649896468744, + "grad_norm": 1.1467449114397317, + "learning_rate": 1.636904761904762e-05, + "loss": 0.9172, + "step": 275 + }, + { + "epoch": 0.024713190441546812, + "grad_norm": 1.2632158063398984, + "learning_rate": 1.642857142857143e-05, + "loss": 0.992, + "step": 276 + }, + { + "epoch": 0.02480273098662488, + "grad_norm": 1.2015540600116177, + "learning_rate": 1.6488095238095237e-05, + "loss": 0.9638, + "step": 277 + }, + { + "epoch": 0.02489227153170295, + "grad_norm": 1.6194864119335934, + "learning_rate": 1.6547619047619046e-05, + "loss": 0.9563, + "step": 278 + }, + { + "epoch": 0.024981812076781018, + "grad_norm": 1.317110222923093, + "learning_rate": 1.660714285714286e-05, + "loss": 0.9467, + "step": 279 + }, + { + "epoch": 0.025071352621859087, + "grad_norm": 1.2084077377335762, + "learning_rate": 1.6666666666666667e-05, + "loss": 0.9559, + "step": 280 + }, + { + "epoch": 0.025160893166937155, + "grad_norm": 1.2177578314772777, + "learning_rate": 1.672619047619048e-05, + "loss": 0.9208, + "step": 281 + }, + { + "epoch": 0.02525043371201522, + "grad_norm": 1.3396968157893492, + "learning_rate": 1.678571428571429e-05, + "loss": 0.929, + "step": 282 + }, + { + "epoch": 0.02533997425709329, + "grad_norm": 1.2709315475510545, + "learning_rate": 1.6845238095238097e-05, + "loss": 0.9717, + "step": 283 + }, + { + "epoch": 0.025429514802171357, + "grad_norm": 1.1736756823003907, + "learning_rate": 1.6904761904761906e-05, + "loss": 0.9442, + "step": 284 + }, + { + "epoch": 0.025519055347249426, + "grad_norm": 1.2819378880729473, + "learning_rate": 1.6964285714285715e-05, + "loss": 0.9784, + "step": 285 + }, + { + "epoch": 0.025608595892327495, + "grad_norm": 1.2072524557125448, + "learning_rate": 1.7023809523809524e-05, + "loss": 0.9367, + "step": 286 + }, + { + "epoch": 0.025698136437405563, + "grad_norm": 1.1931206254308466, + "learning_rate": 1.7083333333333333e-05, + "loss": 0.928, + "step": 287 + }, + { + "epoch": 0.02578767698248363, + "grad_norm": 1.2451944086669584, + "learning_rate": 1.7142857142857142e-05, + "loss": 0.9856, + "step": 288 + }, + { + "epoch": 0.0258772175275617, + "grad_norm": 1.186333557285608, + "learning_rate": 1.7202380952380954e-05, + "loss": 0.9207, + "step": 289 + }, + { + "epoch": 0.02596675807263977, + "grad_norm": 1.2859414579975315, + "learning_rate": 1.7261904761904763e-05, + "loss": 1.0336, + "step": 290 + }, + { + "epoch": 0.026056298617717834, + "grad_norm": 1.2692773660377794, + "learning_rate": 1.7321428571428572e-05, + "loss": 0.9622, + "step": 291 + }, + { + "epoch": 0.026145839162795902, + "grad_norm": 1.2009944656927962, + "learning_rate": 1.7380952380952384e-05, + "loss": 0.8634, + "step": 292 + }, + { + "epoch": 0.02623537970787397, + "grad_norm": 1.192861316510647, + "learning_rate": 1.7440476190476193e-05, + "loss": 0.9012, + "step": 293 + }, + { + "epoch": 0.02632492025295204, + "grad_norm": 1.2344980831774923, + "learning_rate": 1.7500000000000002e-05, + "loss": 0.9481, + "step": 294 + }, + { + "epoch": 0.026414460798030108, + "grad_norm": 1.3273083647356205, + "learning_rate": 1.755952380952381e-05, + "loss": 0.9185, + "step": 295 + }, + { + "epoch": 0.026504001343108177, + "grad_norm": 1.2967623142399103, + "learning_rate": 1.761904761904762e-05, + "loss": 0.939, + "step": 296 + }, + { + "epoch": 0.026593541888186245, + "grad_norm": 1.2671348071058701, + "learning_rate": 1.767857142857143e-05, + "loss": 0.9737, + "step": 297 + }, + { + "epoch": 0.026683082433264314, + "grad_norm": 1.4884601300030078, + "learning_rate": 1.7738095238095237e-05, + "loss": 0.9058, + "step": 298 + }, + { + "epoch": 0.026772622978342382, + "grad_norm": 1.3585149324752888, + "learning_rate": 1.779761904761905e-05, + "loss": 0.9579, + "step": 299 + }, + { + "epoch": 0.026862163523420447, + "grad_norm": 1.251343435632289, + "learning_rate": 1.785714285714286e-05, + "loss": 0.9218, + "step": 300 + }, + { + "epoch": 0.026951704068498516, + "grad_norm": 1.1879850640137528, + "learning_rate": 1.7916666666666667e-05, + "loss": 0.8826, + "step": 301 + }, + { + "epoch": 0.027041244613576584, + "grad_norm": 1.1686705636610717, + "learning_rate": 1.797619047619048e-05, + "loss": 0.8943, + "step": 302 + }, + { + "epoch": 0.027130785158654653, + "grad_norm": 1.3269898001103417, + "learning_rate": 1.803571428571429e-05, + "loss": 0.9295, + "step": 303 + }, + { + "epoch": 0.02722032570373272, + "grad_norm": 1.188519023547051, + "learning_rate": 1.8095238095238097e-05, + "loss": 0.9809, + "step": 304 + }, + { + "epoch": 0.02730986624881079, + "grad_norm": 1.3206352421494414, + "learning_rate": 1.8154761904761906e-05, + "loss": 0.9565, + "step": 305 + }, + { + "epoch": 0.02739940679388886, + "grad_norm": 1.2560526345765262, + "learning_rate": 1.8214285714285715e-05, + "loss": 0.9757, + "step": 306 + }, + { + "epoch": 0.027488947338966927, + "grad_norm": 1.4476339312774624, + "learning_rate": 1.8273809523809524e-05, + "loss": 0.9555, + "step": 307 + }, + { + "epoch": 0.027578487884044996, + "grad_norm": 1.3209041933174963, + "learning_rate": 1.8333333333333333e-05, + "loss": 0.893, + "step": 308 + }, + { + "epoch": 0.02766802842912306, + "grad_norm": 1.278921184328932, + "learning_rate": 1.8392857142857142e-05, + "loss": 0.9433, + "step": 309 + }, + { + "epoch": 0.02775756897420113, + "grad_norm": 1.238903595474599, + "learning_rate": 1.8452380952380954e-05, + "loss": 0.9346, + "step": 310 + }, + { + "epoch": 0.027847109519279198, + "grad_norm": 1.2846775825747934, + "learning_rate": 1.8511904761904763e-05, + "loss": 0.9268, + "step": 311 + }, + { + "epoch": 0.027936650064357266, + "grad_norm": 1.1542758792293397, + "learning_rate": 1.8571428571428575e-05, + "loss": 0.9662, + "step": 312 + }, + { + "epoch": 0.028026190609435335, + "grad_norm": 1.2940399503698272, + "learning_rate": 1.8630952380952384e-05, + "loss": 0.9071, + "step": 313 + }, + { + "epoch": 0.028115731154513404, + "grad_norm": 1.1780693686095078, + "learning_rate": 1.8690476190476193e-05, + "loss": 0.8983, + "step": 314 + }, + { + "epoch": 0.028205271699591472, + "grad_norm": 1.2731633775610305, + "learning_rate": 1.8750000000000002e-05, + "loss": 0.9516, + "step": 315 + }, + { + "epoch": 0.02829481224466954, + "grad_norm": 1.337023007007858, + "learning_rate": 1.880952380952381e-05, + "loss": 0.9505, + "step": 316 + }, + { + "epoch": 0.02838435278974761, + "grad_norm": 1.2936786958242825, + "learning_rate": 1.886904761904762e-05, + "loss": 0.9611, + "step": 317 + }, + { + "epoch": 0.028473893334825674, + "grad_norm": 1.3612811004646033, + "learning_rate": 1.892857142857143e-05, + "loss": 0.9937, + "step": 318 + }, + { + "epoch": 0.028563433879903743, + "grad_norm": 1.1658265192952217, + "learning_rate": 1.8988095238095237e-05, + "loss": 0.9922, + "step": 319 + }, + { + "epoch": 0.02865297442498181, + "grad_norm": 1.2044117714956288, + "learning_rate": 1.904761904761905e-05, + "loss": 0.8805, + "step": 320 + }, + { + "epoch": 0.02874251497005988, + "grad_norm": 1.2259452468459933, + "learning_rate": 1.910714285714286e-05, + "loss": 0.9154, + "step": 321 + }, + { + "epoch": 0.02883205551513795, + "grad_norm": 1.1179903436614513, + "learning_rate": 1.916666666666667e-05, + "loss": 0.941, + "step": 322 + }, + { + "epoch": 0.028921596060216017, + "grad_norm": 1.3082458991850165, + "learning_rate": 1.922619047619048e-05, + "loss": 0.8364, + "step": 323 + }, + { + "epoch": 0.029011136605294086, + "grad_norm": 1.103997232008849, + "learning_rate": 1.928571428571429e-05, + "loss": 0.9284, + "step": 324 + }, + { + "epoch": 0.029100677150372154, + "grad_norm": 1.2402651208124122, + "learning_rate": 1.9345238095238097e-05, + "loss": 0.9415, + "step": 325 + }, + { + "epoch": 0.029190217695450223, + "grad_norm": 1.1946287678518863, + "learning_rate": 1.9404761904761906e-05, + "loss": 0.861, + "step": 326 + }, + { + "epoch": 0.029279758240528288, + "grad_norm": 1.2913893706035076, + "learning_rate": 1.9464285714285715e-05, + "loss": 0.945, + "step": 327 + }, + { + "epoch": 0.029369298785606356, + "grad_norm": 1.2357971553362492, + "learning_rate": 1.9523809523809524e-05, + "loss": 0.9335, + "step": 328 + }, + { + "epoch": 0.029458839330684425, + "grad_norm": 1.3450287990312693, + "learning_rate": 1.9583333333333333e-05, + "loss": 0.9363, + "step": 329 + }, + { + "epoch": 0.029548379875762493, + "grad_norm": 1.3454130192674454, + "learning_rate": 1.9642857142857145e-05, + "loss": 0.903, + "step": 330 + }, + { + "epoch": 0.029637920420840562, + "grad_norm": 1.3951306355796904, + "learning_rate": 1.9702380952380954e-05, + "loss": 0.9393, + "step": 331 + }, + { + "epoch": 0.02972746096591863, + "grad_norm": 1.2117680774838118, + "learning_rate": 1.9761904761904763e-05, + "loss": 0.9326, + "step": 332 + }, + { + "epoch": 0.0298170015109967, + "grad_norm": 1.2228522050442563, + "learning_rate": 1.9821428571428575e-05, + "loss": 0.9054, + "step": 333 + }, + { + "epoch": 0.029906542056074768, + "grad_norm": 1.1940677033805458, + "learning_rate": 1.9880952380952384e-05, + "loss": 1.0374, + "step": 334 + }, + { + "epoch": 0.029996082601152836, + "grad_norm": 1.445666161448832, + "learning_rate": 1.9940476190476193e-05, + "loss": 0.8591, + "step": 335 + }, + { + "epoch": 0.0300856231462309, + "grad_norm": 1.175121282559073, + "learning_rate": 2e-05, + "loss": 0.9034, + "step": 336 + }, + { + "epoch": 0.03017516369130897, + "grad_norm": 1.1840759609844393, + "learning_rate": 1.9999999579416295e-05, + "loss": 0.9852, + "step": 337 + }, + { + "epoch": 0.03026470423638704, + "grad_norm": 1.2972577877784766, + "learning_rate": 1.999999831766521e-05, + "loss": 0.9217, + "step": 338 + }, + { + "epoch": 0.030354244781465107, + "grad_norm": 1.3410857496455018, + "learning_rate": 1.9999996214746854e-05, + "loss": 0.922, + "step": 339 + }, + { + "epoch": 0.030443785326543175, + "grad_norm": 1.2858331779234244, + "learning_rate": 1.9999993270661405e-05, + "loss": 0.9902, + "step": 340 + }, + { + "epoch": 0.030533325871621244, + "grad_norm": 1.2906061274610103, + "learning_rate": 1.9999989485409108e-05, + "loss": 0.9497, + "step": 341 + }, + { + "epoch": 0.030622866416699313, + "grad_norm": 1.3438050934807848, + "learning_rate": 1.9999984858990286e-05, + "loss": 0.9774, + "step": 342 + }, + { + "epoch": 0.03071240696177738, + "grad_norm": 1.122789551808367, + "learning_rate": 1.9999979391405317e-05, + "loss": 0.9693, + "step": 343 + }, + { + "epoch": 0.03080194750685545, + "grad_norm": 1.2958773216664197, + "learning_rate": 1.9999973082654672e-05, + "loss": 0.9157, + "step": 344 + }, + { + "epoch": 0.030891488051933515, + "grad_norm": 1.1076076237587629, + "learning_rate": 1.999996593273888e-05, + "loss": 0.9138, + "step": 345 + }, + { + "epoch": 0.030981028597011583, + "grad_norm": 1.274050445689624, + "learning_rate": 1.9999957941658542e-05, + "loss": 0.9782, + "step": 346 + }, + { + "epoch": 0.031070569142089652, + "grad_norm": 1.1724707586484096, + "learning_rate": 1.9999949109414324e-05, + "loss": 0.9915, + "step": 347 + }, + { + "epoch": 0.03116010968716772, + "grad_norm": 1.2030585442294828, + "learning_rate": 1.9999939436006975e-05, + "loss": 0.9435, + "step": 348 + }, + { + "epoch": 0.03124965023224579, + "grad_norm": 1.260596168675043, + "learning_rate": 1.9999928921437312e-05, + "loss": 0.9314, + "step": 349 + }, + { + "epoch": 0.031339190777323854, + "grad_norm": 1.130308218986913, + "learning_rate": 1.9999917565706212e-05, + "loss": 0.9528, + "step": 350 + }, + { + "epoch": 0.031428731322401926, + "grad_norm": 1.2635135167153189, + "learning_rate": 1.999990536881463e-05, + "loss": 0.9238, + "step": 351 + }, + { + "epoch": 0.03151827186747999, + "grad_norm": 1.2419529359399137, + "learning_rate": 1.99998923307636e-05, + "loss": 0.9508, + "step": 352 + }, + { + "epoch": 0.03160781241255806, + "grad_norm": 1.3089890933275954, + "learning_rate": 1.999987845155421e-05, + "loss": 0.9375, + "step": 353 + }, + { + "epoch": 0.03169735295763613, + "grad_norm": 1.1855978529504216, + "learning_rate": 1.9999863731187633e-05, + "loss": 1.0427, + "step": 354 + }, + { + "epoch": 0.0317868935027142, + "grad_norm": 1.24608020740071, + "learning_rate": 1.9999848169665106e-05, + "loss": 0.9625, + "step": 355 + }, + { + "epoch": 0.031876434047792265, + "grad_norm": 1.0665556967385843, + "learning_rate": 1.9999831766987937e-05, + "loss": 0.9446, + "step": 356 + }, + { + "epoch": 0.03196597459287034, + "grad_norm": 1.2824843635764926, + "learning_rate": 1.999981452315751e-05, + "loss": 0.8955, + "step": 357 + }, + { + "epoch": 0.0320555151379484, + "grad_norm": 1.1380499628928542, + "learning_rate": 1.9999796438175267e-05, + "loss": 0.9579, + "step": 358 + }, + { + "epoch": 0.03214505568302647, + "grad_norm": 1.1681159772783272, + "learning_rate": 1.9999777512042735e-05, + "loss": 1.0003, + "step": 359 + }, + { + "epoch": 0.03223459622810454, + "grad_norm": 1.159237296775598, + "learning_rate": 1.99997577447615e-05, + "loss": 0.9512, + "step": 360 + }, + { + "epoch": 0.032324136773182605, + "grad_norm": 1.1051170969030417, + "learning_rate": 1.9999737136333238e-05, + "loss": 0.9539, + "step": 361 + }, + { + "epoch": 0.03241367731826068, + "grad_norm": 1.2179667737810091, + "learning_rate": 1.9999715686759672e-05, + "loss": 0.9592, + "step": 362 + }, + { + "epoch": 0.03250321786333874, + "grad_norm": 1.3549356438467903, + "learning_rate": 1.9999693396042606e-05, + "loss": 0.9131, + "step": 363 + }, + { + "epoch": 0.032592758408416814, + "grad_norm": 1.1247588026228426, + "learning_rate": 1.999967026418392e-05, + "loss": 0.9621, + "step": 364 + }, + { + "epoch": 0.03268229895349488, + "grad_norm": 1.110894022484044, + "learning_rate": 1.9999646291185556e-05, + "loss": 0.8561, + "step": 365 + }, + { + "epoch": 0.03277183949857295, + "grad_norm": 1.1168106343953137, + "learning_rate": 1.9999621477049533e-05, + "loss": 0.9586, + "step": 366 + }, + { + "epoch": 0.032861380043651016, + "grad_norm": 1.3079644833146529, + "learning_rate": 1.999959582177794e-05, + "loss": 0.8862, + "step": 367 + }, + { + "epoch": 0.03295092058872908, + "grad_norm": 2.341257425754997, + "learning_rate": 1.9999569325372924e-05, + "loss": 0.9556, + "step": 368 + }, + { + "epoch": 0.03304046113380715, + "grad_norm": 1.2118853822143971, + "learning_rate": 1.999954198783673e-05, + "loss": 0.9515, + "step": 369 + }, + { + "epoch": 0.03313000167888522, + "grad_norm": 1.2054431047537317, + "learning_rate": 1.9999513809171645e-05, + "loss": 0.9037, + "step": 370 + }, + { + "epoch": 0.03321954222396329, + "grad_norm": 1.1627706090098924, + "learning_rate": 1.9999484789380043e-05, + "loss": 0.9678, + "step": 371 + }, + { + "epoch": 0.033309082769041355, + "grad_norm": 1.317538657224851, + "learning_rate": 1.999945492846437e-05, + "loss": 0.9004, + "step": 372 + }, + { + "epoch": 0.03339862331411943, + "grad_norm": 1.0334149458465276, + "learning_rate": 1.9999424226427132e-05, + "loss": 0.8923, + "step": 373 + }, + { + "epoch": 0.03348816385919749, + "grad_norm": 1.1182486507943536, + "learning_rate": 1.9999392683270913e-05, + "loss": 0.9031, + "step": 374 + }, + { + "epoch": 0.033577704404275564, + "grad_norm": 1.1021130166795021, + "learning_rate": 1.9999360298998366e-05, + "loss": 0.9194, + "step": 375 + }, + { + "epoch": 0.03366724494935363, + "grad_norm": 1.1480514714426844, + "learning_rate": 1.9999327073612215e-05, + "loss": 0.95, + "step": 376 + }, + { + "epoch": 0.033756785494431694, + "grad_norm": 1.2102737349523482, + "learning_rate": 1.999929300711526e-05, + "loss": 0.9607, + "step": 377 + }, + { + "epoch": 0.033846326039509766, + "grad_norm": 1.1460299125442661, + "learning_rate": 1.9999258099510358e-05, + "loss": 0.959, + "step": 378 + }, + { + "epoch": 0.03393586658458783, + "grad_norm": 1.340156983358306, + "learning_rate": 1.9999222350800447e-05, + "loss": 0.9048, + "step": 379 + }, + { + "epoch": 0.034025407129665904, + "grad_norm": 1.1394376365295866, + "learning_rate": 1.999918576098854e-05, + "loss": 0.9143, + "step": 380 + }, + { + "epoch": 0.03411494767474397, + "grad_norm": 1.239318983026435, + "learning_rate": 1.999914833007771e-05, + "loss": 0.9614, + "step": 381 + }, + { + "epoch": 0.03420448821982204, + "grad_norm": 1.08302823697214, + "learning_rate": 1.999911005807111e-05, + "loss": 0.936, + "step": 382 + }, + { + "epoch": 0.034294028764900106, + "grad_norm": 1.0989866494677702, + "learning_rate": 1.999907094497195e-05, + "loss": 0.9845, + "step": 383 + }, + { + "epoch": 0.03438356930997818, + "grad_norm": 1.2556845899582212, + "learning_rate": 1.999903099078353e-05, + "loss": 0.9983, + "step": 384 + }, + { + "epoch": 0.03447310985505624, + "grad_norm": 1.1480845483728792, + "learning_rate": 1.9998990195509206e-05, + "loss": 0.9746, + "step": 385 + }, + { + "epoch": 0.03456265040013431, + "grad_norm": 1.2305798693471501, + "learning_rate": 1.999894855915241e-05, + "loss": 0.8903, + "step": 386 + }, + { + "epoch": 0.03465219094521238, + "grad_norm": 1.125735318482672, + "learning_rate": 1.9998906081716645e-05, + "loss": 0.9234, + "step": 387 + }, + { + "epoch": 0.034741731490290445, + "grad_norm": 1.294810748801314, + "learning_rate": 1.9998862763205483e-05, + "loss": 0.9278, + "step": 388 + }, + { + "epoch": 0.03483127203536852, + "grad_norm": 1.1759301483100835, + "learning_rate": 1.9998818603622575e-05, + "loss": 0.9174, + "step": 389 + }, + { + "epoch": 0.03492081258044658, + "grad_norm": 1.260059086574787, + "learning_rate": 1.999877360297162e-05, + "loss": 1.0049, + "step": 390 + }, + { + "epoch": 0.035010353125524654, + "grad_norm": 1.3752136311451377, + "learning_rate": 1.999872776125642e-05, + "loss": 0.9573, + "step": 391 + }, + { + "epoch": 0.03509989367060272, + "grad_norm": 1.147360042768058, + "learning_rate": 1.9998681078480818e-05, + "loss": 0.9478, + "step": 392 + }, + { + "epoch": 0.03518943421568079, + "grad_norm": 1.2233832039373622, + "learning_rate": 1.999863355464875e-05, + "loss": 0.9409, + "step": 393 + }, + { + "epoch": 0.035278974760758856, + "grad_norm": 1.15056592762095, + "learning_rate": 1.9998585189764207e-05, + "loss": 0.9302, + "step": 394 + }, + { + "epoch": 0.03536851530583692, + "grad_norm": 1.2384668684871656, + "learning_rate": 1.9998535983831263e-05, + "loss": 0.9427, + "step": 395 + }, + { + "epoch": 0.03545805585091499, + "grad_norm": 1.3431795917504665, + "learning_rate": 1.9998485936854056e-05, + "loss": 0.9102, + "step": 396 + }, + { + "epoch": 0.03554759639599306, + "grad_norm": 1.0871331326251104, + "learning_rate": 1.999843504883679e-05, + "loss": 0.8903, + "step": 397 + }, + { + "epoch": 0.03563713694107113, + "grad_norm": 1.2290120067211536, + "learning_rate": 1.9998383319783752e-05, + "loss": 0.9418, + "step": 398 + }, + { + "epoch": 0.035726677486149196, + "grad_norm": 1.1409857583770284, + "learning_rate": 1.9998330749699287e-05, + "loss": 0.9443, + "step": 399 + }, + { + "epoch": 0.03581621803122727, + "grad_norm": 1.0803116597017157, + "learning_rate": 1.9998277338587826e-05, + "loss": 0.9996, + "step": 400 + }, + { + "epoch": 0.03590575857630533, + "grad_norm": 1.2605290135576785, + "learning_rate": 1.9998223086453855e-05, + "loss": 0.9771, + "step": 401 + }, + { + "epoch": 0.035995299121383405, + "grad_norm": 1.1815088737776223, + "learning_rate": 1.9998167993301938e-05, + "loss": 0.9321, + "step": 402 + }, + { + "epoch": 0.03608483966646147, + "grad_norm": 1.17998901759651, + "learning_rate": 1.999811205913671e-05, + "loss": 0.883, + "step": 403 + }, + { + "epoch": 0.036174380211539535, + "grad_norm": 1.116737020520798, + "learning_rate": 1.999805528396288e-05, + "loss": 0.918, + "step": 404 + }, + { + "epoch": 0.03626392075661761, + "grad_norm": 1.2038238201377083, + "learning_rate": 1.999799766778522e-05, + "loss": 1.0135, + "step": 405 + }, + { + "epoch": 0.03635346130169567, + "grad_norm": 1.2055240672593202, + "learning_rate": 1.9997939210608573e-05, + "loss": 0.9373, + "step": 406 + }, + { + "epoch": 0.036443001846773744, + "grad_norm": 1.138475667606657, + "learning_rate": 1.999787991243786e-05, + "loss": 0.9546, + "step": 407 + }, + { + "epoch": 0.03653254239185181, + "grad_norm": 1.1026782481638375, + "learning_rate": 1.9997819773278074e-05, + "loss": 0.9716, + "step": 408 + }, + { + "epoch": 0.03662208293692988, + "grad_norm": 1.18258582282077, + "learning_rate": 1.9997758793134264e-05, + "loss": 0.936, + "step": 409 + }, + { + "epoch": 0.036711623482007946, + "grad_norm": 1.2339445059329697, + "learning_rate": 1.9997696972011563e-05, + "loss": 0.9309, + "step": 410 + }, + { + "epoch": 0.03680116402708602, + "grad_norm": 1.1089366234467675, + "learning_rate": 1.9997634309915175e-05, + "loss": 0.9657, + "step": 411 + }, + { + "epoch": 0.03689070457216408, + "grad_norm": 1.2797706811043954, + "learning_rate": 1.999757080685037e-05, + "loss": 0.9765, + "step": 412 + }, + { + "epoch": 0.03698024511724215, + "grad_norm": 1.0922420262255677, + "learning_rate": 1.9997506462822485e-05, + "loss": 0.9832, + "step": 413 + }, + { + "epoch": 0.03706978566232022, + "grad_norm": 1.3469308175814345, + "learning_rate": 1.9997441277836935e-05, + "loss": 0.9861, + "step": 414 + }, + { + "epoch": 0.037159326207398286, + "grad_norm": 1.2351600276828343, + "learning_rate": 1.9997375251899204e-05, + "loss": 0.9614, + "step": 415 + }, + { + "epoch": 0.03724886675247636, + "grad_norm": 1.130633680767699, + "learning_rate": 1.9997308385014843e-05, + "loss": 0.9451, + "step": 416 + }, + { + "epoch": 0.03733840729755442, + "grad_norm": 1.3925859902896762, + "learning_rate": 1.9997240677189484e-05, + "loss": 1.0413, + "step": 417 + }, + { + "epoch": 0.037427947842632495, + "grad_norm": 1.123328941203412, + "learning_rate": 1.9997172128428815e-05, + "loss": 0.9286, + "step": 418 + }, + { + "epoch": 0.03751748838771056, + "grad_norm": 1.2204541169927308, + "learning_rate": 1.9997102738738607e-05, + "loss": 0.952, + "step": 419 + }, + { + "epoch": 0.03760702893278863, + "grad_norm": 1.3518948043649528, + "learning_rate": 1.9997032508124687e-05, + "loss": 0.9437, + "step": 420 + }, + { + "epoch": 0.0376965694778667, + "grad_norm": 1.2385395750726995, + "learning_rate": 1.9996961436592977e-05, + "loss": 0.9578, + "step": 421 + }, + { + "epoch": 0.03778611002294476, + "grad_norm": 1.1959920011410816, + "learning_rate": 1.9996889524149444e-05, + "loss": 0.9175, + "step": 422 + }, + { + "epoch": 0.037875650568022834, + "grad_norm": 1.2159878915973947, + "learning_rate": 1.9996816770800143e-05, + "loss": 0.9322, + "step": 423 + }, + { + "epoch": 0.0379651911131009, + "grad_norm": 1.0299544045858229, + "learning_rate": 1.999674317655119e-05, + "loss": 0.8602, + "step": 424 + }, + { + "epoch": 0.03805473165817897, + "grad_norm": 1.113403302132828, + "learning_rate": 1.999666874140878e-05, + "loss": 0.9484, + "step": 425 + }, + { + "epoch": 0.038144272203257036, + "grad_norm": 1.2025517736216589, + "learning_rate": 1.9996593465379168e-05, + "loss": 0.9388, + "step": 426 + }, + { + "epoch": 0.03823381274833511, + "grad_norm": 1.138031720481696, + "learning_rate": 1.9996517348468694e-05, + "loss": 0.943, + "step": 427 + }, + { + "epoch": 0.03832335329341317, + "grad_norm": 1.1108921533296434, + "learning_rate": 1.9996440390683752e-05, + "loss": 0.979, + "step": 428 + }, + { + "epoch": 0.038412893838491245, + "grad_norm": 1.024459313852225, + "learning_rate": 1.9996362592030822e-05, + "loss": 0.9139, + "step": 429 + }, + { + "epoch": 0.03850243438356931, + "grad_norm": 1.1076151056767962, + "learning_rate": 1.9996283952516448e-05, + "loss": 0.9639, + "step": 430 + }, + { + "epoch": 0.038591974928647375, + "grad_norm": 1.0879548490443949, + "learning_rate": 1.9996204472147238e-05, + "loss": 0.9499, + "step": 431 + }, + { + "epoch": 0.03868151547372545, + "grad_norm": 1.1733192906965282, + "learning_rate": 1.9996124150929886e-05, + "loss": 0.9239, + "step": 432 + }, + { + "epoch": 0.03877105601880351, + "grad_norm": 1.241422221144721, + "learning_rate": 1.9996042988871146e-05, + "loss": 0.8901, + "step": 433 + }, + { + "epoch": 0.038860596563881585, + "grad_norm": 1.1091807248142462, + "learning_rate": 1.9995960985977844e-05, + "loss": 0.9268, + "step": 434 + }, + { + "epoch": 0.03895013710895965, + "grad_norm": 1.2636147143991028, + "learning_rate": 1.9995878142256872e-05, + "loss": 0.9633, + "step": 435 + }, + { + "epoch": 0.03903967765403772, + "grad_norm": 1.0162106523467713, + "learning_rate": 1.9995794457715208e-05, + "loss": 0.9258, + "step": 436 + }, + { + "epoch": 0.03912921819911579, + "grad_norm": 1.098656229656379, + "learning_rate": 1.999570993235989e-05, + "loss": 0.8883, + "step": 437 + }, + { + "epoch": 0.03921875874419386, + "grad_norm": 1.0691834365895647, + "learning_rate": 1.9995624566198023e-05, + "loss": 0.8965, + "step": 438 + }, + { + "epoch": 0.039308299289271924, + "grad_norm": 1.1137901476993821, + "learning_rate": 1.999553835923679e-05, + "loss": 0.9311, + "step": 439 + }, + { + "epoch": 0.03939783983434999, + "grad_norm": 1.3594161594027432, + "learning_rate": 1.9995451311483442e-05, + "loss": 0.9408, + "step": 440 + }, + { + "epoch": 0.03948738037942806, + "grad_norm": 1.103002573666054, + "learning_rate": 1.9995363422945303e-05, + "loss": 0.9071, + "step": 441 + }, + { + "epoch": 0.039576920924506126, + "grad_norm": 1.0808630142789442, + "learning_rate": 1.9995274693629765e-05, + "loss": 0.9343, + "step": 442 + }, + { + "epoch": 0.0396664614695842, + "grad_norm": 1.193375569151024, + "learning_rate": 1.9995185123544292e-05, + "loss": 0.9647, + "step": 443 + }, + { + "epoch": 0.03975600201466226, + "grad_norm": 1.0958279624064393, + "learning_rate": 1.9995094712696413e-05, + "loss": 0.9862, + "step": 444 + }, + { + "epoch": 0.039845542559740335, + "grad_norm": 1.0094831712069403, + "learning_rate": 1.9995003461093744e-05, + "loss": 0.9528, + "step": 445 + }, + { + "epoch": 0.0399350831048184, + "grad_norm": 1.0360560736768474, + "learning_rate": 1.9994911368743953e-05, + "loss": 0.9518, + "step": 446 + }, + { + "epoch": 0.04002462364989647, + "grad_norm": 1.0161465901307165, + "learning_rate": 1.9994818435654787e-05, + "loss": 0.9509, + "step": 447 + }, + { + "epoch": 0.04011416419497454, + "grad_norm": 1.112758987143763, + "learning_rate": 1.9994724661834065e-05, + "loss": 0.9917, + "step": 448 + }, + { + "epoch": 0.0402037047400526, + "grad_norm": 1.1811256418627025, + "learning_rate": 1.9994630047289675e-05, + "loss": 0.9369, + "step": 449 + }, + { + "epoch": 0.040293245285130674, + "grad_norm": 1.2142042607316923, + "learning_rate": 1.9994534592029575e-05, + "loss": 0.8877, + "step": 450 + }, + { + "epoch": 0.04038278583020874, + "grad_norm": 1.2873978374756583, + "learning_rate": 1.9994438296061793e-05, + "loss": 0.8962, + "step": 451 + }, + { + "epoch": 0.04047232637528681, + "grad_norm": 1.1547875572102886, + "learning_rate": 1.999434115939443e-05, + "loss": 0.904, + "step": 452 + }, + { + "epoch": 0.04056186692036488, + "grad_norm": 1.2216695070885337, + "learning_rate": 1.9994243182035658e-05, + "loss": 0.9964, + "step": 453 + }, + { + "epoch": 0.04065140746544295, + "grad_norm": 1.0418262682528086, + "learning_rate": 1.999414436399372e-05, + "loss": 0.9159, + "step": 454 + }, + { + "epoch": 0.040740948010521014, + "grad_norm": 1.0003786758740296, + "learning_rate": 1.9994044705276924e-05, + "loss": 0.9723, + "step": 455 + }, + { + "epoch": 0.04083048855559908, + "grad_norm": 1.0678157331913944, + "learning_rate": 1.9993944205893654e-05, + "loss": 0.929, + "step": 456 + }, + { + "epoch": 0.04092002910067715, + "grad_norm": 1.0590530498465156, + "learning_rate": 1.9993842865852366e-05, + "loss": 0.9192, + "step": 457 + }, + { + "epoch": 0.041009569645755216, + "grad_norm": 1.1364089137580078, + "learning_rate": 1.999374068516158e-05, + "loss": 0.9362, + "step": 458 + }, + { + "epoch": 0.04109911019083329, + "grad_norm": 1.150935142690887, + "learning_rate": 1.9993637663829898e-05, + "loss": 0.9626, + "step": 459 + }, + { + "epoch": 0.04118865073591135, + "grad_norm": 1.1161011977567339, + "learning_rate": 1.9993533801865984e-05, + "loss": 0.9452, + "step": 460 + }, + { + "epoch": 0.041278191280989425, + "grad_norm": 1.0916024650943628, + "learning_rate": 1.9993429099278567e-05, + "loss": 0.939, + "step": 461 + }, + { + "epoch": 0.04136773182606749, + "grad_norm": 1.1049388674486635, + "learning_rate": 1.9993323556076466e-05, + "loss": 0.9046, + "step": 462 + }, + { + "epoch": 0.04145727237114556, + "grad_norm": 1.1582655424392185, + "learning_rate": 1.9993217172268548e-05, + "loss": 0.9352, + "step": 463 + }, + { + "epoch": 0.04154681291622363, + "grad_norm": 1.2105801488656158, + "learning_rate": 1.9993109947863768e-05, + "loss": 0.9388, + "step": 464 + }, + { + "epoch": 0.04163635346130169, + "grad_norm": 1.192649949701616, + "learning_rate": 1.9993001882871144e-05, + "loss": 1.0016, + "step": 465 + }, + { + "epoch": 0.041725894006379764, + "grad_norm": 1.110099893030217, + "learning_rate": 1.9992892977299765e-05, + "loss": 0.9141, + "step": 466 + }, + { + "epoch": 0.04181543455145783, + "grad_norm": 1.210350536116226, + "learning_rate": 1.999278323115879e-05, + "loss": 0.9627, + "step": 467 + }, + { + "epoch": 0.0419049750965359, + "grad_norm": 1.1038053999985182, + "learning_rate": 1.9992672644457455e-05, + "loss": 0.9471, + "step": 468 + }, + { + "epoch": 0.041994515641613966, + "grad_norm": 1.1373982218123397, + "learning_rate": 1.9992561217205064e-05, + "loss": 0.9586, + "step": 469 + }, + { + "epoch": 0.04208405618669204, + "grad_norm": 1.0604068313149375, + "learning_rate": 1.9992448949410984e-05, + "loss": 0.9341, + "step": 470 + }, + { + "epoch": 0.042173596731770104, + "grad_norm": 1.034261570588313, + "learning_rate": 1.999233584108466e-05, + "loss": 0.8946, + "step": 471 + }, + { + "epoch": 0.042263137276848176, + "grad_norm": 1.0552614129053202, + "learning_rate": 1.9992221892235605e-05, + "loss": 0.923, + "step": 472 + }, + { + "epoch": 0.04235267782192624, + "grad_norm": 1.2337679200552256, + "learning_rate": 1.999210710287341e-05, + "loss": 0.959, + "step": 473 + }, + { + "epoch": 0.042442218367004306, + "grad_norm": 1.1658435350844465, + "learning_rate": 1.9991991473007724e-05, + "loss": 0.9643, + "step": 474 + }, + { + "epoch": 0.04253175891208238, + "grad_norm": 1.069903998029625, + "learning_rate": 1.999187500264828e-05, + "loss": 0.8971, + "step": 475 + }, + { + "epoch": 0.04262129945716044, + "grad_norm": 1.2237395659698547, + "learning_rate": 1.9991757691804866e-05, + "loss": 0.9618, + "step": 476 + }, + { + "epoch": 0.042710840002238515, + "grad_norm": 1.1178284750387897, + "learning_rate": 1.999163954048736e-05, + "loss": 0.983, + "step": 477 + }, + { + "epoch": 0.04280038054731658, + "grad_norm": 1.0711916917599673, + "learning_rate": 1.9991520548705695e-05, + "loss": 0.9555, + "step": 478 + }, + { + "epoch": 0.04288992109239465, + "grad_norm": 1.0089883890975022, + "learning_rate": 1.999140071646988e-05, + "loss": 0.9253, + "step": 479 + }, + { + "epoch": 0.04297946163747272, + "grad_norm": 0.9530952959533482, + "learning_rate": 1.9991280043789992e-05, + "loss": 0.9168, + "step": 480 + }, + { + "epoch": 0.04306900218255079, + "grad_norm": 1.0543192038478133, + "learning_rate": 1.9991158530676192e-05, + "loss": 0.9382, + "step": 481 + }, + { + "epoch": 0.043158542727628854, + "grad_norm": 1.0660027262009064, + "learning_rate": 1.999103617713869e-05, + "loss": 0.9, + "step": 482 + }, + { + "epoch": 0.04324808327270692, + "grad_norm": 1.0153999928167032, + "learning_rate": 1.9990912983187786e-05, + "loss": 0.863, + "step": 483 + }, + { + "epoch": 0.04333762381778499, + "grad_norm": 1.1310027815228523, + "learning_rate": 1.9990788948833835e-05, + "loss": 0.9149, + "step": 484 + }, + { + "epoch": 0.043427164362863056, + "grad_norm": 1.145060884011434, + "learning_rate": 1.9990664074087278e-05, + "loss": 0.901, + "step": 485 + }, + { + "epoch": 0.04351670490794113, + "grad_norm": 1.0882347830609251, + "learning_rate": 1.9990538358958616e-05, + "loss": 0.9194, + "step": 486 + }, + { + "epoch": 0.04360624545301919, + "grad_norm": 1.1157463077907417, + "learning_rate": 1.999041180345842e-05, + "loss": 0.9135, + "step": 487 + }, + { + "epoch": 0.043695785998097265, + "grad_norm": 1.1289838198075401, + "learning_rate": 1.9990284407597343e-05, + "loss": 0.9185, + "step": 488 + }, + { + "epoch": 0.04378532654317533, + "grad_norm": 1.0537068780705858, + "learning_rate": 1.9990156171386092e-05, + "loss": 0.9711, + "step": 489 + }, + { + "epoch": 0.0438748670882534, + "grad_norm": 1.1472070588947672, + "learning_rate": 1.9990027094835463e-05, + "loss": 0.9498, + "step": 490 + }, + { + "epoch": 0.04396440763333147, + "grad_norm": 1.2653321553280341, + "learning_rate": 1.9989897177956308e-05, + "loss": 0.8896, + "step": 491 + }, + { + "epoch": 0.04405394817840953, + "grad_norm": 1.0291960991493623, + "learning_rate": 1.9989766420759554e-05, + "loss": 0.9283, + "step": 492 + }, + { + "epoch": 0.044143488723487605, + "grad_norm": 1.2134748302201406, + "learning_rate": 1.9989634823256206e-05, + "loss": 0.9518, + "step": 493 + }, + { + "epoch": 0.04423302926856567, + "grad_norm": 1.1918645895354567, + "learning_rate": 1.998950238545733e-05, + "loss": 0.8942, + "step": 494 + }, + { + "epoch": 0.04432256981364374, + "grad_norm": 1.1747911685732364, + "learning_rate": 1.9989369107374064e-05, + "loss": 0.993, + "step": 495 + }, + { + "epoch": 0.04441211035872181, + "grad_norm": 1.0404512175154763, + "learning_rate": 1.9989234989017622e-05, + "loss": 0.8671, + "step": 496 + }, + { + "epoch": 0.04450165090379988, + "grad_norm": 1.1566238142038705, + "learning_rate": 1.9989100030399285e-05, + "loss": 0.9272, + "step": 497 + }, + { + "epoch": 0.044591191448877944, + "grad_norm": 1.3440675808590532, + "learning_rate": 1.9988964231530404e-05, + "loss": 0.9688, + "step": 498 + }, + { + "epoch": 0.044680731993956016, + "grad_norm": 1.1060168723939328, + "learning_rate": 1.9988827592422404e-05, + "loss": 0.8904, + "step": 499 + }, + { + "epoch": 0.04477027253903408, + "grad_norm": 1.0456481612834965, + "learning_rate": 1.9988690113086776e-05, + "loss": 0.8563, + "step": 500 + }, + { + "epoch": 0.044859813084112146, + "grad_norm": 1.0684988092141845, + "learning_rate": 1.9988551793535088e-05, + "loss": 0.9535, + "step": 501 + }, + { + "epoch": 0.04494935362919022, + "grad_norm": 1.086717744123546, + "learning_rate": 1.998841263377897e-05, + "loss": 0.9526, + "step": 502 + }, + { + "epoch": 0.04503889417426828, + "grad_norm": 1.211186497271187, + "learning_rate": 1.9988272633830136e-05, + "loss": 0.9543, + "step": 503 + }, + { + "epoch": 0.045128434719346355, + "grad_norm": 1.6278515277901342, + "learning_rate": 1.9988131793700352e-05, + "loss": 0.9347, + "step": 504 + }, + { + "epoch": 0.04521797526442442, + "grad_norm": 1.139406994339983, + "learning_rate": 1.998799011340147e-05, + "loss": 0.9104, + "step": 505 + }, + { + "epoch": 0.04530751580950249, + "grad_norm": 1.4280525627471077, + "learning_rate": 1.9987847592945412e-05, + "loss": 0.9899, + "step": 506 + }, + { + "epoch": 0.04539705635458056, + "grad_norm": 1.1584947776891752, + "learning_rate": 1.9987704232344156e-05, + "loss": 0.9458, + "step": 507 + }, + { + "epoch": 0.04548659689965863, + "grad_norm": 1.1226407021941534, + "learning_rate": 1.998756003160977e-05, + "loss": 0.9451, + "step": 508 + }, + { + "epoch": 0.045576137444736695, + "grad_norm": 1.3863609193402193, + "learning_rate": 1.998741499075438e-05, + "loss": 0.9927, + "step": 509 + }, + { + "epoch": 0.04566567798981476, + "grad_norm": 1.1968426322900878, + "learning_rate": 1.998726910979019e-05, + "loss": 0.8881, + "step": 510 + }, + { + "epoch": 0.04575521853489283, + "grad_norm": 1.08556114964565, + "learning_rate": 1.998712238872946e-05, + "loss": 0.8783, + "step": 511 + }, + { + "epoch": 0.0458447590799709, + "grad_norm": 1.1971729440195378, + "learning_rate": 1.998697482758455e-05, + "loss": 0.9201, + "step": 512 + }, + { + "epoch": 0.04593429962504897, + "grad_norm": 1.1125170942528069, + "learning_rate": 1.998682642636786e-05, + "loss": 0.9597, + "step": 513 + }, + { + "epoch": 0.046023840170127034, + "grad_norm": 1.0745580226459157, + "learning_rate": 1.9986677185091868e-05, + "loss": 0.897, + "step": 514 + }, + { + "epoch": 0.046113380715205106, + "grad_norm": 1.157707969839321, + "learning_rate": 1.998652710376914e-05, + "loss": 0.9256, + "step": 515 + }, + { + "epoch": 0.04620292126028317, + "grad_norm": 1.062027978298153, + "learning_rate": 1.9986376182412296e-05, + "loss": 0.9083, + "step": 516 + }, + { + "epoch": 0.04629246180536124, + "grad_norm": 1.2015544741184867, + "learning_rate": 1.9986224421034028e-05, + "loss": 0.9583, + "step": 517 + }, + { + "epoch": 0.04638200235043931, + "grad_norm": 1.3945234898694425, + "learning_rate": 1.9986071819647104e-05, + "loss": 0.9219, + "step": 518 + }, + { + "epoch": 0.04647154289551737, + "grad_norm": 1.3935398855835808, + "learning_rate": 1.998591837826436e-05, + "loss": 0.9184, + "step": 519 + }, + { + "epoch": 0.046561083440595445, + "grad_norm": 1.1685740438852183, + "learning_rate": 1.9985764096898705e-05, + "loss": 0.9721, + "step": 520 + }, + { + "epoch": 0.04665062398567351, + "grad_norm": 1.2563967857846845, + "learning_rate": 1.998560897556311e-05, + "loss": 1.0154, + "step": 521 + }, + { + "epoch": 0.04674016453075158, + "grad_norm": 1.3228718360054317, + "learning_rate": 1.9985453014270633e-05, + "loss": 0.8816, + "step": 522 + }, + { + "epoch": 0.04682970507582965, + "grad_norm": 1.1379330285449913, + "learning_rate": 1.9985296213034386e-05, + "loss": 0.8987, + "step": 523 + }, + { + "epoch": 0.04691924562090772, + "grad_norm": 1.106124654091436, + "learning_rate": 1.9985138571867562e-05, + "loss": 0.9433, + "step": 524 + }, + { + "epoch": 0.047008786165985784, + "grad_norm": 1.0288504965094727, + "learning_rate": 1.998498009078342e-05, + "loss": 0.9271, + "step": 525 + }, + { + "epoch": 0.047098326711063856, + "grad_norm": 1.2236402273226397, + "learning_rate": 1.998482076979529e-05, + "loss": 0.9362, + "step": 526 + }, + { + "epoch": 0.04718786725614192, + "grad_norm": 1.1421657543249277, + "learning_rate": 1.9984660608916572e-05, + "loss": 0.9194, + "step": 527 + }, + { + "epoch": 0.04727740780121999, + "grad_norm": 1.347421957195768, + "learning_rate": 1.9984499608160744e-05, + "loss": 0.843, + "step": 528 + }, + { + "epoch": 0.04736694834629806, + "grad_norm": 1.260130347357029, + "learning_rate": 1.9984337767541347e-05, + "loss": 1.0104, + "step": 529 + }, + { + "epoch": 0.047456488891376124, + "grad_norm": 1.1557217809639428, + "learning_rate": 1.998417508707199e-05, + "loss": 0.8651, + "step": 530 + }, + { + "epoch": 0.047546029436454196, + "grad_norm": 1.038526136282594, + "learning_rate": 1.998401156676636e-05, + "loss": 0.9021, + "step": 531 + }, + { + "epoch": 0.04763556998153226, + "grad_norm": 1.1454247279704335, + "learning_rate": 1.9983847206638213e-05, + "loss": 1.0541, + "step": 532 + }, + { + "epoch": 0.04772511052661033, + "grad_norm": 1.2248960104339464, + "learning_rate": 1.9983682006701373e-05, + "loss": 0.95, + "step": 533 + }, + { + "epoch": 0.0478146510716884, + "grad_norm": 1.3004474112049667, + "learning_rate": 1.9983515966969737e-05, + "loss": 0.9257, + "step": 534 + }, + { + "epoch": 0.04790419161676647, + "grad_norm": 1.2110056095798232, + "learning_rate": 1.998334908745727e-05, + "loss": 0.9363, + "step": 535 + }, + { + "epoch": 0.047993732161844535, + "grad_norm": 1.0385118312856492, + "learning_rate": 1.9983181368178012e-05, + "loss": 0.8833, + "step": 536 + }, + { + "epoch": 0.0480832727069226, + "grad_norm": 1.125943127368221, + "learning_rate": 1.998301280914607e-05, + "loss": 0.936, + "step": 537 + }, + { + "epoch": 0.04817281325200067, + "grad_norm": 1.1319848892973925, + "learning_rate": 1.998284341037562e-05, + "loss": 0.9937, + "step": 538 + }, + { + "epoch": 0.04826235379707874, + "grad_norm": 1.0607842578107185, + "learning_rate": 1.9982673171880912e-05, + "loss": 0.9319, + "step": 539 + }, + { + "epoch": 0.04835189434215681, + "grad_norm": 1.1458161108848985, + "learning_rate": 1.9982502093676273e-05, + "loss": 0.9875, + "step": 540 + }, + { + "epoch": 0.048441434887234874, + "grad_norm": 1.107451632698255, + "learning_rate": 1.9982330175776083e-05, + "loss": 0.9711, + "step": 541 + }, + { + "epoch": 0.048530975432312946, + "grad_norm": 1.1904523680192518, + "learning_rate": 1.9982157418194812e-05, + "loss": 0.9501, + "step": 542 + }, + { + "epoch": 0.04862051597739101, + "grad_norm": 1.0940295640504563, + "learning_rate": 1.9981983820946985e-05, + "loss": 0.8758, + "step": 543 + }, + { + "epoch": 0.04871005652246908, + "grad_norm": 1.0502987545970643, + "learning_rate": 1.998180938404721e-05, + "loss": 0.9263, + "step": 544 + }, + { + "epoch": 0.04879959706754715, + "grad_norm": 1.242706689006851, + "learning_rate": 1.9981634107510153e-05, + "loss": 0.9758, + "step": 545 + }, + { + "epoch": 0.048889137612625214, + "grad_norm": 1.3864003614126603, + "learning_rate": 1.9981457991350567e-05, + "loss": 0.9059, + "step": 546 + }, + { + "epoch": 0.048978678157703286, + "grad_norm": 1.1293650869323646, + "learning_rate": 1.9981281035583254e-05, + "loss": 0.9336, + "step": 547 + }, + { + "epoch": 0.04906821870278135, + "grad_norm": 1.0280092484012466, + "learning_rate": 1.9981103240223113e-05, + "loss": 0.896, + "step": 548 + }, + { + "epoch": 0.04915775924785942, + "grad_norm": 1.1709194702693853, + "learning_rate": 1.998092460528509e-05, + "loss": 0.9523, + "step": 549 + }, + { + "epoch": 0.04924729979293749, + "grad_norm": 1.1476814546059773, + "learning_rate": 1.9980745130784214e-05, + "loss": 0.9635, + "step": 550 + }, + { + "epoch": 0.04933684033801556, + "grad_norm": 1.0333891967525806, + "learning_rate": 1.9980564816735586e-05, + "loss": 0.8626, + "step": 551 + }, + { + "epoch": 0.049426380883093625, + "grad_norm": 1.3634541348571476, + "learning_rate": 1.9980383663154366e-05, + "loss": 0.9291, + "step": 552 + }, + { + "epoch": 0.0495159214281717, + "grad_norm": 1.208095092028711, + "learning_rate": 1.9980201670055796e-05, + "loss": 0.9755, + "step": 553 + }, + { + "epoch": 0.04960546197324976, + "grad_norm": 1.0221694100166283, + "learning_rate": 1.9980018837455184e-05, + "loss": 0.9257, + "step": 554 + }, + { + "epoch": 0.04969500251832783, + "grad_norm": 1.0478036866932399, + "learning_rate": 1.997983516536791e-05, + "loss": 0.9699, + "step": 555 + }, + { + "epoch": 0.0497845430634059, + "grad_norm": 1.2212610955837915, + "learning_rate": 1.997965065380942e-05, + "loss": 0.9573, + "step": 556 + }, + { + "epoch": 0.049874083608483964, + "grad_norm": 1.087699437566681, + "learning_rate": 1.9979465302795242e-05, + "loss": 0.8721, + "step": 557 + }, + { + "epoch": 0.049963624153562036, + "grad_norm": 1.2123012027101887, + "learning_rate": 1.9979279112340963e-05, + "loss": 0.872, + "step": 558 + }, + { + "epoch": 0.0500531646986401, + "grad_norm": 1.0614116504270437, + "learning_rate": 1.997909208246224e-05, + "loss": 0.9204, + "step": 559 + }, + { + "epoch": 0.05014270524371817, + "grad_norm": 1.0127235021587757, + "learning_rate": 1.9978904213174812e-05, + "loss": 0.9754, + "step": 560 + }, + { + "epoch": 0.05023224578879624, + "grad_norm": 1.0843901874857937, + "learning_rate": 1.997871550449448e-05, + "loss": 0.9378, + "step": 561 + }, + { + "epoch": 0.05032178633387431, + "grad_norm": 1.2064090720729816, + "learning_rate": 1.997852595643712e-05, + "loss": 0.919, + "step": 562 + }, + { + "epoch": 0.050411326878952376, + "grad_norm": 1.1005671262672223, + "learning_rate": 1.997833556901867e-05, + "loss": 0.958, + "step": 563 + }, + { + "epoch": 0.05050086742403044, + "grad_norm": 1.1649992322011302, + "learning_rate": 1.997814434225515e-05, + "loss": 0.9456, + "step": 564 + }, + { + "epoch": 0.05059040796910851, + "grad_norm": 1.1739740175270943, + "learning_rate": 1.997795227616264e-05, + "loss": 0.9093, + "step": 565 + }, + { + "epoch": 0.05067994851418658, + "grad_norm": 1.1671784388675037, + "learning_rate": 1.9977759370757304e-05, + "loss": 0.9211, + "step": 566 + }, + { + "epoch": 0.05076948905926465, + "grad_norm": 1.1333127285191198, + "learning_rate": 1.9977565626055364e-05, + "loss": 0.9349, + "step": 567 + }, + { + "epoch": 0.050859029604342715, + "grad_norm": 1.0997562688467957, + "learning_rate": 1.9977371042073116e-05, + "loss": 0.9142, + "step": 568 + }, + { + "epoch": 0.05094857014942079, + "grad_norm": 1.0953041818107725, + "learning_rate": 1.997717561882693e-05, + "loss": 0.8733, + "step": 569 + }, + { + "epoch": 0.05103811069449885, + "grad_norm": 1.18009258753543, + "learning_rate": 1.9976979356333247e-05, + "loss": 0.9188, + "step": 570 + }, + { + "epoch": 0.051127651239576924, + "grad_norm": 1.0726950014500436, + "learning_rate": 1.997678225460857e-05, + "loss": 0.9342, + "step": 571 + }, + { + "epoch": 0.05121719178465499, + "grad_norm": 1.2158227422112158, + "learning_rate": 1.9976584313669478e-05, + "loss": 0.8607, + "step": 572 + }, + { + "epoch": 0.051306732329733054, + "grad_norm": 1.1215672193741464, + "learning_rate": 1.9976385533532626e-05, + "loss": 0.988, + "step": 573 + }, + { + "epoch": 0.051396272874811126, + "grad_norm": 1.2408152351441124, + "learning_rate": 1.9976185914214734e-05, + "loss": 0.9906, + "step": 574 + }, + { + "epoch": 0.05148581341988919, + "grad_norm": 1.131612251100872, + "learning_rate": 1.997598545573259e-05, + "loss": 0.9769, + "step": 575 + }, + { + "epoch": 0.05157535396496726, + "grad_norm": 1.2431275805880857, + "learning_rate": 1.9975784158103062e-05, + "loss": 0.9896, + "step": 576 + }, + { + "epoch": 0.05166489451004533, + "grad_norm": 0.9744941604639711, + "learning_rate": 1.997558202134308e-05, + "loss": 0.9318, + "step": 577 + }, + { + "epoch": 0.0517544350551234, + "grad_norm": 1.0712919163391104, + "learning_rate": 1.997537904546964e-05, + "loss": 0.9492, + "step": 578 + }, + { + "epoch": 0.051843975600201465, + "grad_norm": 1.1767193915535439, + "learning_rate": 1.9975175230499823e-05, + "loss": 0.9981, + "step": 579 + }, + { + "epoch": 0.05193351614527954, + "grad_norm": 1.0550438416242316, + "learning_rate": 1.9974970576450775e-05, + "loss": 0.9399, + "step": 580 + }, + { + "epoch": 0.0520230566903576, + "grad_norm": 1.4142653171545716, + "learning_rate": 1.9974765083339705e-05, + "loss": 0.9455, + "step": 581 + }, + { + "epoch": 0.05211259723543567, + "grad_norm": 1.0749929344780913, + "learning_rate": 1.9974558751183904e-05, + "loss": 0.9818, + "step": 582 + }, + { + "epoch": 0.05220213778051374, + "grad_norm": 1.1463017384115077, + "learning_rate": 1.997435158000072e-05, + "loss": 0.9401, + "step": 583 + }, + { + "epoch": 0.052291678325591805, + "grad_norm": 1.1325236638007723, + "learning_rate": 1.9974143569807588e-05, + "loss": 0.8954, + "step": 584 + }, + { + "epoch": 0.05238121887066988, + "grad_norm": 1.1119954022615302, + "learning_rate": 1.9973934720622003e-05, + "loss": 0.9505, + "step": 585 + }, + { + "epoch": 0.05247075941574794, + "grad_norm": 1.1654191722717122, + "learning_rate": 1.9973725032461528e-05, + "loss": 0.9031, + "step": 586 + }, + { + "epoch": 0.052560299960826014, + "grad_norm": 1.1713497526622438, + "learning_rate": 1.9973514505343806e-05, + "loss": 0.9457, + "step": 587 + }, + { + "epoch": 0.05264984050590408, + "grad_norm": 1.0933210606777743, + "learning_rate": 1.9973303139286547e-05, + "loss": 0.9663, + "step": 588 + }, + { + "epoch": 0.05273938105098215, + "grad_norm": 1.114316259574633, + "learning_rate": 1.9973090934307522e-05, + "loss": 0.9503, + "step": 589 + }, + { + "epoch": 0.052828921596060216, + "grad_norm": 1.1087547414253103, + "learning_rate": 1.9972877890424592e-05, + "loss": 0.9185, + "step": 590 + }, + { + "epoch": 0.05291846214113828, + "grad_norm": 1.1276566435567281, + "learning_rate": 1.997266400765567e-05, + "loss": 0.9153, + "step": 591 + }, + { + "epoch": 0.05300800268621635, + "grad_norm": 1.108682136901737, + "learning_rate": 1.997244928601875e-05, + "loss": 0.9203, + "step": 592 + }, + { + "epoch": 0.05309754323129442, + "grad_norm": 1.1168038060334835, + "learning_rate": 1.9972233725531897e-05, + "loss": 0.9608, + "step": 593 + }, + { + "epoch": 0.05318708377637249, + "grad_norm": 1.0767143358634241, + "learning_rate": 1.9972017326213233e-05, + "loss": 0.9466, + "step": 594 + }, + { + "epoch": 0.053276624321450555, + "grad_norm": 1.040012073149749, + "learning_rate": 1.997180008808097e-05, + "loss": 0.877, + "step": 595 + }, + { + "epoch": 0.05336616486652863, + "grad_norm": 1.101845324693482, + "learning_rate": 1.9971582011153382e-05, + "loss": 0.8476, + "step": 596 + }, + { + "epoch": 0.05345570541160669, + "grad_norm": 1.0410640849956347, + "learning_rate": 1.9971363095448808e-05, + "loss": 0.91, + "step": 597 + }, + { + "epoch": 0.053545245956684764, + "grad_norm": 1.0700556692464638, + "learning_rate": 1.9971143340985663e-05, + "loss": 0.9779, + "step": 598 + }, + { + "epoch": 0.05363478650176283, + "grad_norm": 1.2281299288441592, + "learning_rate": 1.9970922747782433e-05, + "loss": 0.9262, + "step": 599 + }, + { + "epoch": 0.053724327046840895, + "grad_norm": 1.485882965567142, + "learning_rate": 1.9970701315857676e-05, + "loss": 0.8884, + "step": 600 + }, + { + "epoch": 0.05381386759191897, + "grad_norm": 1.0429377141618017, + "learning_rate": 1.9970479045230015e-05, + "loss": 0.952, + "step": 601 + }, + { + "epoch": 0.05390340813699703, + "grad_norm": 0.9372628392739595, + "learning_rate": 1.9970255935918143e-05, + "loss": 0.8715, + "step": 602 + }, + { + "epoch": 0.053992948682075104, + "grad_norm": 1.0449426674025424, + "learning_rate": 1.9970031987940837e-05, + "loss": 0.9774, + "step": 603 + }, + { + "epoch": 0.05408248922715317, + "grad_norm": 1.2112614408094393, + "learning_rate": 1.996980720131693e-05, + "loss": 0.9425, + "step": 604 + }, + { + "epoch": 0.05417202977223124, + "grad_norm": 1.1378702326987429, + "learning_rate": 1.9969581576065326e-05, + "loss": 0.9648, + "step": 605 + }, + { + "epoch": 0.054261570317309306, + "grad_norm": 1.179717432847686, + "learning_rate": 1.996935511220501e-05, + "loss": 0.9532, + "step": 606 + }, + { + "epoch": 0.05435111086238738, + "grad_norm": 1.0957510025405282, + "learning_rate": 1.996912780975503e-05, + "loss": 0.9289, + "step": 607 + }, + { + "epoch": 0.05444065140746544, + "grad_norm": 1.0479000160328913, + "learning_rate": 1.9968899668734503e-05, + "loss": 0.8953, + "step": 608 + }, + { + "epoch": 0.05453019195254351, + "grad_norm": 1.0589172649202057, + "learning_rate": 1.996867068916262e-05, + "loss": 0.8829, + "step": 609 + }, + { + "epoch": 0.05461973249762158, + "grad_norm": 1.0656660635624877, + "learning_rate": 1.9968440871058647e-05, + "loss": 0.9562, + "step": 610 + }, + { + "epoch": 0.054709273042699645, + "grad_norm": 1.1521771886233159, + "learning_rate": 1.9968210214441912e-05, + "loss": 0.9341, + "step": 611 + }, + { + "epoch": 0.05479881358777772, + "grad_norm": 0.9914658075430345, + "learning_rate": 1.9967978719331816e-05, + "loss": 0.883, + "step": 612 + }, + { + "epoch": 0.05488835413285578, + "grad_norm": 1.126233882712661, + "learning_rate": 1.996774638574783e-05, + "loss": 0.9475, + "step": 613 + }, + { + "epoch": 0.054977894677933854, + "grad_norm": 1.048059636538473, + "learning_rate": 1.9967513213709506e-05, + "loss": 0.9232, + "step": 614 + }, + { + "epoch": 0.05506743522301192, + "grad_norm": 1.3257402549838415, + "learning_rate": 1.996727920323645e-05, + "loss": 0.9704, + "step": 615 + }, + { + "epoch": 0.05515697576808999, + "grad_norm": 1.0793772383901195, + "learning_rate": 1.9967044354348347e-05, + "loss": 0.9737, + "step": 616 + }, + { + "epoch": 0.055246516313168056, + "grad_norm": 1.0297255467555129, + "learning_rate": 1.9966808667064953e-05, + "loss": 0.9414, + "step": 617 + }, + { + "epoch": 0.05533605685824612, + "grad_norm": 1.1534164261942317, + "learning_rate": 1.9966572141406092e-05, + "loss": 0.9009, + "step": 618 + }, + { + "epoch": 0.055425597403324194, + "grad_norm": 0.9709791088401495, + "learning_rate": 1.996633477739166e-05, + "loss": 0.8876, + "step": 619 + }, + { + "epoch": 0.05551513794840226, + "grad_norm": 1.124398555405512, + "learning_rate": 1.9966096575041622e-05, + "loss": 0.9383, + "step": 620 + }, + { + "epoch": 0.05560467849348033, + "grad_norm": 1.0490222700760865, + "learning_rate": 1.996585753437602e-05, + "loss": 0.9308, + "step": 621 + }, + { + "epoch": 0.055694219038558396, + "grad_norm": 1.3896934558159915, + "learning_rate": 1.9965617655414956e-05, + "loss": 0.9643, + "step": 622 + }, + { + "epoch": 0.05578375958363647, + "grad_norm": 1.075250567179632, + "learning_rate": 1.996537693817861e-05, + "loss": 0.9255, + "step": 623 + }, + { + "epoch": 0.05587330012871453, + "grad_norm": 1.0535140508053211, + "learning_rate": 1.9965135382687235e-05, + "loss": 0.9371, + "step": 624 + }, + { + "epoch": 0.055962840673792605, + "grad_norm": 1.1622469969808344, + "learning_rate": 1.996489298896114e-05, + "loss": 0.9383, + "step": 625 + }, + { + "epoch": 0.05605238121887067, + "grad_norm": 1.1868976653596344, + "learning_rate": 1.996464975702072e-05, + "loss": 0.9276, + "step": 626 + }, + { + "epoch": 0.056141921763948735, + "grad_norm": 1.1593603029995556, + "learning_rate": 1.9964405686886436e-05, + "loss": 0.9202, + "step": 627 + }, + { + "epoch": 0.05623146230902681, + "grad_norm": 1.0989889823901322, + "learning_rate": 1.9964160778578812e-05, + "loss": 1.0104, + "step": 628 + }, + { + "epoch": 0.05632100285410487, + "grad_norm": 1.1852552873018605, + "learning_rate": 1.996391503211846e-05, + "loss": 0.9384, + "step": 629 + }, + { + "epoch": 0.056410543399182944, + "grad_norm": 1.089308515529538, + "learning_rate": 1.9963668447526042e-05, + "loss": 0.8921, + "step": 630 + }, + { + "epoch": 0.05650008394426101, + "grad_norm": 1.073263054756886, + "learning_rate": 1.9963421024822304e-05, + "loss": 0.9205, + "step": 631 + }, + { + "epoch": 0.05658962448933908, + "grad_norm": 1.1009873472869982, + "learning_rate": 1.9963172764028054e-05, + "loss": 0.9565, + "step": 632 + }, + { + "epoch": 0.056679165034417146, + "grad_norm": 1.1318445024988277, + "learning_rate": 1.996292366516418e-05, + "loss": 0.9097, + "step": 633 + }, + { + "epoch": 0.05676870557949522, + "grad_norm": 1.0442891198225548, + "learning_rate": 1.9962673728251634e-05, + "loss": 0.9093, + "step": 634 + }, + { + "epoch": 0.05685824612457328, + "grad_norm": 1.1082866731928176, + "learning_rate": 1.996242295331144e-05, + "loss": 0.9177, + "step": 635 + }, + { + "epoch": 0.05694778666965135, + "grad_norm": 1.0202709197207074, + "learning_rate": 1.996217134036469e-05, + "loss": 0.9412, + "step": 636 + }, + { + "epoch": 0.05703732721472942, + "grad_norm": 1.144559414301597, + "learning_rate": 1.9961918889432552e-05, + "loss": 0.9646, + "step": 637 + }, + { + "epoch": 0.057126867759807486, + "grad_norm": 1.1896197317023043, + "learning_rate": 1.996166560053626e-05, + "loss": 0.9464, + "step": 638 + }, + { + "epoch": 0.05721640830488556, + "grad_norm": 1.1887641692600903, + "learning_rate": 1.996141147369712e-05, + "loss": 1.0243, + "step": 639 + }, + { + "epoch": 0.05730594884996362, + "grad_norm": 1.3190908728534263, + "learning_rate": 1.9961156508936505e-05, + "loss": 0.8771, + "step": 640 + }, + { + "epoch": 0.057395489395041695, + "grad_norm": 1.289480233669961, + "learning_rate": 1.996090070627587e-05, + "loss": 0.9248, + "step": 641 + }, + { + "epoch": 0.05748502994011976, + "grad_norm": 1.0006480549984968, + "learning_rate": 1.9960644065736723e-05, + "loss": 0.9403, + "step": 642 + }, + { + "epoch": 0.05757457048519783, + "grad_norm": 1.04256239080739, + "learning_rate": 1.9960386587340656e-05, + "loss": 0.8683, + "step": 643 + }, + { + "epoch": 0.0576641110302759, + "grad_norm": 1.0619556320844847, + "learning_rate": 1.9960128271109326e-05, + "loss": 0.8949, + "step": 644 + }, + { + "epoch": 0.05775365157535396, + "grad_norm": 1.2410313721954176, + "learning_rate": 1.9959869117064467e-05, + "loss": 0.9752, + "step": 645 + }, + { + "epoch": 0.057843192120432034, + "grad_norm": 1.1187897684133061, + "learning_rate": 1.9959609125227874e-05, + "loss": 0.9362, + "step": 646 + }, + { + "epoch": 0.0579327326655101, + "grad_norm": 1.0739149709563547, + "learning_rate": 1.9959348295621416e-05, + "loss": 0.9509, + "step": 647 + }, + { + "epoch": 0.05802227321058817, + "grad_norm": 1.082878174473754, + "learning_rate": 1.9959086628267032e-05, + "loss": 0.9332, + "step": 648 + }, + { + "epoch": 0.058111813755666236, + "grad_norm": 1.0371676170664081, + "learning_rate": 1.9958824123186734e-05, + "loss": 0.9046, + "step": 649 + }, + { + "epoch": 0.05820135430074431, + "grad_norm": 1.0430717449528382, + "learning_rate": 1.9958560780402608e-05, + "loss": 0.934, + "step": 650 + }, + { + "epoch": 0.05829089484582237, + "grad_norm": 1.08412250412559, + "learning_rate": 1.9958296599936798e-05, + "loss": 0.8913, + "step": 651 + }, + { + "epoch": 0.058380435390900445, + "grad_norm": 1.089961350342515, + "learning_rate": 1.995803158181153e-05, + "loss": 0.8941, + "step": 652 + }, + { + "epoch": 0.05846997593597851, + "grad_norm": 1.054212999722257, + "learning_rate": 1.9957765726049095e-05, + "loss": 0.9501, + "step": 653 + }, + { + "epoch": 0.058559516481056575, + "grad_norm": 1.019834205471067, + "learning_rate": 1.995749903267186e-05, + "loss": 0.9476, + "step": 654 + }, + { + "epoch": 0.05864905702613465, + "grad_norm": 1.0765348926529934, + "learning_rate": 1.9957231501702254e-05, + "loss": 0.929, + "step": 655 + }, + { + "epoch": 0.05873859757121271, + "grad_norm": 1.1482856973975353, + "learning_rate": 1.9956963133162776e-05, + "loss": 0.9268, + "step": 656 + }, + { + "epoch": 0.058828138116290785, + "grad_norm": 1.2888721925077, + "learning_rate": 1.995669392707601e-05, + "loss": 0.931, + "step": 657 + }, + { + "epoch": 0.05891767866136885, + "grad_norm": 1.1179859099571603, + "learning_rate": 1.9956423883464597e-05, + "loss": 0.8722, + "step": 658 + }, + { + "epoch": 0.05900721920644692, + "grad_norm": 1.0914660764876054, + "learning_rate": 1.9956153002351254e-05, + "loss": 0.9779, + "step": 659 + }, + { + "epoch": 0.05909675975152499, + "grad_norm": 1.265095230889255, + "learning_rate": 1.995588128375876e-05, + "loss": 0.9414, + "step": 660 + }, + { + "epoch": 0.05918630029660306, + "grad_norm": 1.0392274440222413, + "learning_rate": 1.9955608727709977e-05, + "loss": 0.9498, + "step": 661 + }, + { + "epoch": 0.059275840841681124, + "grad_norm": 1.424774737510009, + "learning_rate": 1.995533533422783e-05, + "loss": 0.9636, + "step": 662 + }, + { + "epoch": 0.05936538138675919, + "grad_norm": 1.1180189283395208, + "learning_rate": 1.9955061103335317e-05, + "loss": 0.909, + "step": 663 + }, + { + "epoch": 0.05945492193183726, + "grad_norm": 0.9975520497198124, + "learning_rate": 1.9954786035055505e-05, + "loss": 0.9036, + "step": 664 + }, + { + "epoch": 0.059544462476915326, + "grad_norm": 1.0954873575181803, + "learning_rate": 1.9954510129411534e-05, + "loss": 0.9227, + "step": 665 + }, + { + "epoch": 0.0596340030219934, + "grad_norm": 0.9895627093679141, + "learning_rate": 1.9954233386426605e-05, + "loss": 0.9027, + "step": 666 + }, + { + "epoch": 0.05972354356707146, + "grad_norm": 1.1027784033415864, + "learning_rate": 1.9953955806124003e-05, + "loss": 0.9398, + "step": 667 + }, + { + "epoch": 0.059813084112149535, + "grad_norm": 1.084472059437037, + "learning_rate": 1.9953677388527076e-05, + "loss": 0.9178, + "step": 668 + }, + { + "epoch": 0.0599026246572276, + "grad_norm": 0.9488185418148994, + "learning_rate": 1.9953398133659243e-05, + "loss": 0.9242, + "step": 669 + }, + { + "epoch": 0.05999216520230567, + "grad_norm": 1.1836720414780657, + "learning_rate": 1.9953118041543994e-05, + "loss": 0.9657, + "step": 670 + }, + { + "epoch": 0.06008170574738374, + "grad_norm": 1.022971600888171, + "learning_rate": 1.995283711220489e-05, + "loss": 0.9431, + "step": 671 + }, + { + "epoch": 0.0601712462924618, + "grad_norm": 0.9986351487156575, + "learning_rate": 1.9952555345665563e-05, + "loss": 0.8774, + "step": 672 + }, + { + "epoch": 0.060260786837539874, + "grad_norm": 1.018768964697811, + "learning_rate": 1.995227274194971e-05, + "loss": 0.9333, + "step": 673 + }, + { + "epoch": 0.06035032738261794, + "grad_norm": 1.2250536889430095, + "learning_rate": 1.9951989301081105e-05, + "loss": 0.875, + "step": 674 + }, + { + "epoch": 0.06043986792769601, + "grad_norm": 1.0301347028192598, + "learning_rate": 1.9951705023083594e-05, + "loss": 0.9078, + "step": 675 + }, + { + "epoch": 0.06052940847277408, + "grad_norm": 1.172855360599762, + "learning_rate": 1.9951419907981083e-05, + "loss": 0.9228, + "step": 676 + }, + { + "epoch": 0.06061894901785215, + "grad_norm": 1.07567298403186, + "learning_rate": 1.995113395579756e-05, + "loss": 0.9847, + "step": 677 + }, + { + "epoch": 0.060708489562930214, + "grad_norm": 1.0908027401090645, + "learning_rate": 1.9950847166557076e-05, + "loss": 0.9516, + "step": 678 + }, + { + "epoch": 0.060798030108008286, + "grad_norm": 1.0281355250535715, + "learning_rate": 1.9950559540283753e-05, + "loss": 0.935, + "step": 679 + }, + { + "epoch": 0.06088757065308635, + "grad_norm": 1.040634376362086, + "learning_rate": 1.9950271077001792e-05, + "loss": 0.8898, + "step": 680 + }, + { + "epoch": 0.060977111198164416, + "grad_norm": 1.0301798312707877, + "learning_rate": 1.994998177673545e-05, + "loss": 0.8949, + "step": 681 + }, + { + "epoch": 0.06106665174324249, + "grad_norm": 1.036320069153192, + "learning_rate": 1.9949691639509067e-05, + "loss": 0.9649, + "step": 682 + }, + { + "epoch": 0.06115619228832055, + "grad_norm": 1.2418971335715927, + "learning_rate": 1.9949400665347042e-05, + "loss": 0.8822, + "step": 683 + }, + { + "epoch": 0.061245732833398625, + "grad_norm": 1.0331561026970484, + "learning_rate": 1.9949108854273856e-05, + "loss": 0.9129, + "step": 684 + }, + { + "epoch": 0.06133527337847669, + "grad_norm": 1.0468745440096618, + "learning_rate": 1.994881620631406e-05, + "loss": 0.9157, + "step": 685 + }, + { + "epoch": 0.06142481392355476, + "grad_norm": 1.157857271770634, + "learning_rate": 1.9948522721492257e-05, + "loss": 0.915, + "step": 686 + }, + { + "epoch": 0.06151435446863283, + "grad_norm": 1.033996036594039, + "learning_rate": 1.9948228399833148e-05, + "loss": 0.9868, + "step": 687 + }, + { + "epoch": 0.0616038950137109, + "grad_norm": 1.0570236723148827, + "learning_rate": 1.9947933241361482e-05, + "loss": 0.8782, + "step": 688 + }, + { + "epoch": 0.061693435558788964, + "grad_norm": 1.039545198862132, + "learning_rate": 1.9947637246102092e-05, + "loss": 0.9528, + "step": 689 + }, + { + "epoch": 0.06178297610386703, + "grad_norm": 1.3440834269331907, + "learning_rate": 1.994734041407987e-05, + "loss": 1.0033, + "step": 690 + }, + { + "epoch": 0.0618725166489451, + "grad_norm": 1.1108547797258492, + "learning_rate": 1.9947042745319786e-05, + "loss": 0.9167, + "step": 691 + }, + { + "epoch": 0.061962057194023167, + "grad_norm": 0.9262542314026714, + "learning_rate": 1.9946744239846886e-05, + "loss": 0.86, + "step": 692 + }, + { + "epoch": 0.06205159773910124, + "grad_norm": 1.0721863516696286, + "learning_rate": 1.9946444897686273e-05, + "loss": 0.9295, + "step": 693 + }, + { + "epoch": 0.062141138284179304, + "grad_norm": 1.0757509069978242, + "learning_rate": 1.9946144718863122e-05, + "loss": 0.9592, + "step": 694 + }, + { + "epoch": 0.062230678829257376, + "grad_norm": 1.1073251674974691, + "learning_rate": 1.9945843703402694e-05, + "loss": 0.9614, + "step": 695 + }, + { + "epoch": 0.06232021937433544, + "grad_norm": 1.2278039551367435, + "learning_rate": 1.9945541851330304e-05, + "loss": 0.9418, + "step": 696 + }, + { + "epoch": 0.06240975991941351, + "grad_norm": 1.153469521421713, + "learning_rate": 1.9945239162671343e-05, + "loss": 0.8972, + "step": 697 + }, + { + "epoch": 0.06249930046449158, + "grad_norm": 1.0771149673276852, + "learning_rate": 1.9944935637451272e-05, + "loss": 0.8749, + "step": 698 + }, + { + "epoch": 0.06258884100956964, + "grad_norm": 1.0828949811249642, + "learning_rate": 1.994463127569562e-05, + "loss": 0.9127, + "step": 699 + }, + { + "epoch": 0.06267838155464771, + "grad_norm": 1.0228026949840077, + "learning_rate": 1.9944326077429995e-05, + "loss": 0.9695, + "step": 700 + }, + { + "epoch": 0.06276792209972579, + "grad_norm": 1.0360618043078018, + "learning_rate": 1.9944020042680065e-05, + "loss": 0.9147, + "step": 701 + }, + { + "epoch": 0.06285746264480385, + "grad_norm": 1.1527617984007996, + "learning_rate": 1.9943713171471573e-05, + "loss": 0.9435, + "step": 702 + }, + { + "epoch": 0.06294700318988192, + "grad_norm": 1.0334789718750361, + "learning_rate": 1.9943405463830336e-05, + "loss": 0.9699, + "step": 703 + }, + { + "epoch": 0.06303654373495998, + "grad_norm": 1.0816970656093612, + "learning_rate": 1.9943096919782227e-05, + "loss": 0.8716, + "step": 704 + }, + { + "epoch": 0.06312608428003806, + "grad_norm": 1.1970472273480843, + "learning_rate": 1.9942787539353216e-05, + "loss": 0.9684, + "step": 705 + }, + { + "epoch": 0.06321562482511613, + "grad_norm": 1.1481551794171696, + "learning_rate": 1.9942477322569308e-05, + "loss": 0.9098, + "step": 706 + }, + { + "epoch": 0.06330516537019419, + "grad_norm": 1.133303881985732, + "learning_rate": 1.9942166269456614e-05, + "loss": 0.9411, + "step": 707 + }, + { + "epoch": 0.06339470591527226, + "grad_norm": 1.2683539892124873, + "learning_rate": 1.9941854380041292e-05, + "loss": 0.9292, + "step": 708 + }, + { + "epoch": 0.06348424646035032, + "grad_norm": 1.176531679026709, + "learning_rate": 1.9941541654349575e-05, + "loss": 0.9297, + "step": 709 + }, + { + "epoch": 0.0635737870054284, + "grad_norm": 1.032583099485249, + "learning_rate": 1.994122809240777e-05, + "loss": 0.9516, + "step": 710 + }, + { + "epoch": 0.06366332755050647, + "grad_norm": 1.2374308346536853, + "learning_rate": 1.994091369424225e-05, + "loss": 0.9087, + "step": 711 + }, + { + "epoch": 0.06375286809558453, + "grad_norm": 1.1127319938875315, + "learning_rate": 1.994059845987947e-05, + "loss": 0.9108, + "step": 712 + }, + { + "epoch": 0.0638424086406626, + "grad_norm": 1.1136323085651891, + "learning_rate": 1.994028238934594e-05, + "loss": 0.9148, + "step": 713 + }, + { + "epoch": 0.06393194918574067, + "grad_norm": 0.9652342289170723, + "learning_rate": 1.9939965482668247e-05, + "loss": 0.8795, + "step": 714 + }, + { + "epoch": 0.06402148973081874, + "grad_norm": 1.0758253722995965, + "learning_rate": 1.993964773987305e-05, + "loss": 0.9394, + "step": 715 + }, + { + "epoch": 0.0641110302758968, + "grad_norm": 1.1272120727854955, + "learning_rate": 1.9939329160987075e-05, + "loss": 0.8927, + "step": 716 + }, + { + "epoch": 0.06420057082097487, + "grad_norm": 1.0937618755412848, + "learning_rate": 1.993900974603712e-05, + "loss": 0.9187, + "step": 717 + }, + { + "epoch": 0.06429011136605293, + "grad_norm": 1.0082067105606212, + "learning_rate": 1.9938689495050055e-05, + "loss": 0.9166, + "step": 718 + }, + { + "epoch": 0.06437965191113101, + "grad_norm": 1.1444950401152703, + "learning_rate": 1.9938368408052814e-05, + "loss": 0.8718, + "step": 719 + }, + { + "epoch": 0.06446919245620908, + "grad_norm": 1.0131926028406713, + "learning_rate": 1.993804648507241e-05, + "loss": 0.9133, + "step": 720 + }, + { + "epoch": 0.06455873300128714, + "grad_norm": 1.1528048760202945, + "learning_rate": 1.993772372613592e-05, + "loss": 0.939, + "step": 721 + }, + { + "epoch": 0.06464827354636521, + "grad_norm": 1.289270887826232, + "learning_rate": 1.9937400131270496e-05, + "loss": 0.9872, + "step": 722 + }, + { + "epoch": 0.06473781409144329, + "grad_norm": 1.080640969956045, + "learning_rate": 1.9937075700503357e-05, + "loss": 0.9279, + "step": 723 + }, + { + "epoch": 0.06482735463652135, + "grad_norm": 1.0877680650662236, + "learning_rate": 1.993675043386179e-05, + "loss": 0.9524, + "step": 724 + }, + { + "epoch": 0.06491689518159942, + "grad_norm": 1.0071707596319672, + "learning_rate": 1.993642433137316e-05, + "loss": 0.905, + "step": 725 + }, + { + "epoch": 0.06500643572667748, + "grad_norm": 1.0147041270842982, + "learning_rate": 1.993609739306489e-05, + "loss": 0.9448, + "step": 726 + }, + { + "epoch": 0.06509597627175555, + "grad_norm": 1.1591289258361375, + "learning_rate": 1.993576961896449e-05, + "loss": 0.915, + "step": 727 + }, + { + "epoch": 0.06518551681683363, + "grad_norm": 1.0680404207397045, + "learning_rate": 1.9935441009099527e-05, + "loss": 0.949, + "step": 728 + }, + { + "epoch": 0.06527505736191169, + "grad_norm": 1.0514825561451777, + "learning_rate": 1.993511156349764e-05, + "loss": 0.9384, + "step": 729 + }, + { + "epoch": 0.06536459790698976, + "grad_norm": 1.0066444729579083, + "learning_rate": 1.9934781282186545e-05, + "loss": 0.9459, + "step": 730 + }, + { + "epoch": 0.06545413845206782, + "grad_norm": 1.120524370645983, + "learning_rate": 1.9934450165194027e-05, + "loss": 0.9639, + "step": 731 + }, + { + "epoch": 0.0655436789971459, + "grad_norm": 1.1574029963684436, + "learning_rate": 1.993411821254793e-05, + "loss": 0.9241, + "step": 732 + }, + { + "epoch": 0.06563321954222397, + "grad_norm": 1.0686164605858943, + "learning_rate": 1.9933785424276185e-05, + "loss": 0.9314, + "step": 733 + }, + { + "epoch": 0.06572276008730203, + "grad_norm": 1.028393781221605, + "learning_rate": 1.993345180040678e-05, + "loss": 0.8969, + "step": 734 + }, + { + "epoch": 0.0658123006323801, + "grad_norm": 1.1457741722924495, + "learning_rate": 1.993311734096778e-05, + "loss": 0.9203, + "step": 735 + }, + { + "epoch": 0.06590184117745816, + "grad_norm": 1.1183776235429703, + "learning_rate": 1.9932782045987317e-05, + "loss": 0.9621, + "step": 736 + }, + { + "epoch": 0.06599138172253624, + "grad_norm": 1.1047821001895943, + "learning_rate": 1.9932445915493598e-05, + "loss": 0.9215, + "step": 737 + }, + { + "epoch": 0.0660809222676143, + "grad_norm": 1.029184225030201, + "learning_rate": 1.993210894951489e-05, + "loss": 0.9349, + "step": 738 + }, + { + "epoch": 0.06617046281269237, + "grad_norm": 1.2640231568202325, + "learning_rate": 1.9931771148079552e-05, + "loss": 0.9084, + "step": 739 + }, + { + "epoch": 0.06626000335777044, + "grad_norm": 1.1438205090033562, + "learning_rate": 1.9931432511215983e-05, + "loss": 0.9238, + "step": 740 + }, + { + "epoch": 0.06634954390284852, + "grad_norm": 1.1469170456221658, + "learning_rate": 1.9931093038952677e-05, + "loss": 0.8769, + "step": 741 + }, + { + "epoch": 0.06643908444792658, + "grad_norm": 1.0191067074856213, + "learning_rate": 1.993075273131819e-05, + "loss": 0.9429, + "step": 742 + }, + { + "epoch": 0.06652862499300465, + "grad_norm": 1.0266690271911931, + "learning_rate": 1.9930411588341138e-05, + "loss": 0.9899, + "step": 743 + }, + { + "epoch": 0.06661816553808271, + "grad_norm": 0.9929885173697578, + "learning_rate": 1.9930069610050228e-05, + "loss": 0.9072, + "step": 744 + }, + { + "epoch": 0.06670770608316078, + "grad_norm": 1.0841949886666007, + "learning_rate": 1.992972679647422e-05, + "loss": 0.9465, + "step": 745 + }, + { + "epoch": 0.06679724662823885, + "grad_norm": 1.0581337489643985, + "learning_rate": 1.9929383147641952e-05, + "loss": 0.9418, + "step": 746 + }, + { + "epoch": 0.06688678717331692, + "grad_norm": 1.1024536604600896, + "learning_rate": 1.992903866358233e-05, + "loss": 0.9142, + "step": 747 + }, + { + "epoch": 0.06697632771839498, + "grad_norm": 1.2154089387451648, + "learning_rate": 1.9928693344324333e-05, + "loss": 0.9489, + "step": 748 + }, + { + "epoch": 0.06706586826347305, + "grad_norm": 1.5743215424180574, + "learning_rate": 1.9928347189897006e-05, + "loss": 0.9951, + "step": 749 + }, + { + "epoch": 0.06715540880855113, + "grad_norm": 1.185152359928579, + "learning_rate": 1.9928000200329468e-05, + "loss": 0.9525, + "step": 750 + }, + { + "epoch": 0.0672449493536292, + "grad_norm": 1.022310677169066, + "learning_rate": 1.9927652375650904e-05, + "loss": 0.9605, + "step": 751 + }, + { + "epoch": 0.06733448989870726, + "grad_norm": 1.11537810169956, + "learning_rate": 1.9927303715890573e-05, + "loss": 0.9051, + "step": 752 + }, + { + "epoch": 0.06742403044378532, + "grad_norm": 1.096699551478262, + "learning_rate": 1.9926954221077807e-05, + "loss": 0.9183, + "step": 753 + }, + { + "epoch": 0.06751357098886339, + "grad_norm": 0.9775570344486216, + "learning_rate": 1.9926603891241997e-05, + "loss": 0.8832, + "step": 754 + }, + { + "epoch": 0.06760311153394147, + "grad_norm": 1.0633362765624412, + "learning_rate": 1.9926252726412618e-05, + "loss": 0.9248, + "step": 755 + }, + { + "epoch": 0.06769265207901953, + "grad_norm": 1.0628771492992868, + "learning_rate": 1.9925900726619206e-05, + "loss": 1.0107, + "step": 756 + }, + { + "epoch": 0.0677821926240976, + "grad_norm": 1.036884912617968, + "learning_rate": 1.9925547891891368e-05, + "loss": 0.8572, + "step": 757 + }, + { + "epoch": 0.06787173316917566, + "grad_norm": 1.0716293114445457, + "learning_rate": 1.9925194222258786e-05, + "loss": 0.9175, + "step": 758 + }, + { + "epoch": 0.06796127371425374, + "grad_norm": 1.238577582204527, + "learning_rate": 1.9924839717751213e-05, + "loss": 0.9242, + "step": 759 + }, + { + "epoch": 0.06805081425933181, + "grad_norm": 0.9948418188725063, + "learning_rate": 1.9924484378398462e-05, + "loss": 0.9117, + "step": 760 + }, + { + "epoch": 0.06814035480440987, + "grad_norm": 1.126841904173083, + "learning_rate": 1.992412820423043e-05, + "loss": 0.9804, + "step": 761 + }, + { + "epoch": 0.06822989534948794, + "grad_norm": 1.057157979297986, + "learning_rate": 1.9923771195277067e-05, + "loss": 0.8706, + "step": 762 + }, + { + "epoch": 0.068319435894566, + "grad_norm": 1.0278117915693268, + "learning_rate": 1.9923413351568413e-05, + "loss": 0.9279, + "step": 763 + }, + { + "epoch": 0.06840897643964408, + "grad_norm": 0.9886181854200796, + "learning_rate": 1.9923054673134566e-05, + "loss": 0.9177, + "step": 764 + }, + { + "epoch": 0.06849851698472215, + "grad_norm": 1.0578080927047577, + "learning_rate": 1.9922695160005694e-05, + "loss": 0.885, + "step": 765 + }, + { + "epoch": 0.06858805752980021, + "grad_norm": 0.979068442637175, + "learning_rate": 1.992233481221204e-05, + "loss": 0.8821, + "step": 766 + }, + { + "epoch": 0.06867759807487828, + "grad_norm": 1.1492093605802958, + "learning_rate": 1.992197362978392e-05, + "loss": 0.9065, + "step": 767 + }, + { + "epoch": 0.06876713861995636, + "grad_norm": 1.019436623612196, + "learning_rate": 1.9921611612751707e-05, + "loss": 0.9073, + "step": 768 + }, + { + "epoch": 0.06885667916503442, + "grad_norm": 1.19956497370407, + "learning_rate": 1.992124876114586e-05, + "loss": 0.9438, + "step": 769 + }, + { + "epoch": 0.06894621971011249, + "grad_norm": 1.049777686435467, + "learning_rate": 1.9920885074996893e-05, + "loss": 0.9115, + "step": 770 + }, + { + "epoch": 0.06903576025519055, + "grad_norm": 1.0312476632289158, + "learning_rate": 1.9920520554335408e-05, + "loss": 0.9416, + "step": 771 + }, + { + "epoch": 0.06912530080026862, + "grad_norm": 0.98640571376336, + "learning_rate": 1.992015519919206e-05, + "loss": 0.9169, + "step": 772 + }, + { + "epoch": 0.0692148413453467, + "grad_norm": 1.0546292616976334, + "learning_rate": 1.991978900959758e-05, + "loss": 0.9038, + "step": 773 + }, + { + "epoch": 0.06930438189042476, + "grad_norm": 0.9632518494489212, + "learning_rate": 1.991942198558278e-05, + "loss": 0.914, + "step": 774 + }, + { + "epoch": 0.06939392243550283, + "grad_norm": 0.9932321274334242, + "learning_rate": 1.9919054127178522e-05, + "loss": 0.8046, + "step": 775 + }, + { + "epoch": 0.06948346298058089, + "grad_norm": 1.0315970954329294, + "learning_rate": 1.9918685434415757e-05, + "loss": 0.8409, + "step": 776 + }, + { + "epoch": 0.06957300352565897, + "grad_norm": 1.1104393529970686, + "learning_rate": 1.991831590732549e-05, + "loss": 0.8697, + "step": 777 + }, + { + "epoch": 0.06966254407073703, + "grad_norm": 1.0774883418576322, + "learning_rate": 1.9917945545938817e-05, + "loss": 0.8738, + "step": 778 + }, + { + "epoch": 0.0697520846158151, + "grad_norm": 1.2136997380403043, + "learning_rate": 1.991757435028688e-05, + "loss": 1.0073, + "step": 779 + }, + { + "epoch": 0.06984162516089316, + "grad_norm": 1.1341939791921614, + "learning_rate": 1.991720232040091e-05, + "loss": 0.9125, + "step": 780 + }, + { + "epoch": 0.06993116570597123, + "grad_norm": 1.1292080385781416, + "learning_rate": 1.9916829456312198e-05, + "loss": 0.916, + "step": 781 + }, + { + "epoch": 0.07002070625104931, + "grad_norm": 1.1282089583036534, + "learning_rate": 1.9916455758052104e-05, + "loss": 0.9932, + "step": 782 + }, + { + "epoch": 0.07011024679612737, + "grad_norm": 1.1525777881606178, + "learning_rate": 1.991608122565207e-05, + "loss": 0.9463, + "step": 783 + }, + { + "epoch": 0.07019978734120544, + "grad_norm": 1.2735045207630338, + "learning_rate": 1.9915705859143597e-05, + "loss": 0.9512, + "step": 784 + }, + { + "epoch": 0.0702893278862835, + "grad_norm": 1.1241584606605324, + "learning_rate": 1.991532965855826e-05, + "loss": 0.9903, + "step": 785 + }, + { + "epoch": 0.07037886843136158, + "grad_norm": 0.9606026571169505, + "learning_rate": 1.9914952623927698e-05, + "loss": 0.9578, + "step": 786 + }, + { + "epoch": 0.07046840897643965, + "grad_norm": 1.205581042483934, + "learning_rate": 1.9914574755283636e-05, + "loss": 0.9117, + "step": 787 + }, + { + "epoch": 0.07055794952151771, + "grad_norm": 1.0778708362648222, + "learning_rate": 1.9914196052657852e-05, + "loss": 0.8901, + "step": 788 + }, + { + "epoch": 0.07064749006659578, + "grad_norm": 1.2084250909336678, + "learning_rate": 1.9913816516082205e-05, + "loss": 0.9264, + "step": 789 + }, + { + "epoch": 0.07073703061167384, + "grad_norm": 1.1627785089895557, + "learning_rate": 1.991343614558862e-05, + "loss": 0.9399, + "step": 790 + }, + { + "epoch": 0.07082657115675192, + "grad_norm": 1.0955128950897222, + "learning_rate": 1.9913054941209087e-05, + "loss": 0.9741, + "step": 791 + }, + { + "epoch": 0.07091611170182999, + "grad_norm": 1.1112343380824248, + "learning_rate": 1.9912672902975682e-05, + "loss": 0.9113, + "step": 792 + }, + { + "epoch": 0.07100565224690805, + "grad_norm": 0.9962753370106672, + "learning_rate": 1.9912290030920533e-05, + "loss": 0.9057, + "step": 793 + }, + { + "epoch": 0.07109519279198612, + "grad_norm": 1.1351398681104958, + "learning_rate": 1.9911906325075844e-05, + "loss": 0.9131, + "step": 794 + }, + { + "epoch": 0.0711847333370642, + "grad_norm": 1.0941497698684952, + "learning_rate": 1.99115217854739e-05, + "loss": 0.9038, + "step": 795 + }, + { + "epoch": 0.07127427388214226, + "grad_norm": 1.1346991099505284, + "learning_rate": 1.9911136412147037e-05, + "loss": 0.9282, + "step": 796 + }, + { + "epoch": 0.07136381442722033, + "grad_norm": 1.1032383197771924, + "learning_rate": 1.991075020512768e-05, + "loss": 0.9722, + "step": 797 + }, + { + "epoch": 0.07145335497229839, + "grad_norm": 0.9687945397059757, + "learning_rate": 1.9910363164448313e-05, + "loss": 0.8917, + "step": 798 + }, + { + "epoch": 0.07154289551737646, + "grad_norm": 1.0943644743553063, + "learning_rate": 1.990997529014149e-05, + "loss": 0.9229, + "step": 799 + }, + { + "epoch": 0.07163243606245454, + "grad_norm": 1.0725468683762778, + "learning_rate": 1.9909586582239835e-05, + "loss": 0.8433, + "step": 800 + }, + { + "epoch": 0.0717219766075326, + "grad_norm": 0.9890577527704585, + "learning_rate": 1.9909197040776055e-05, + "loss": 0.8861, + "step": 801 + }, + { + "epoch": 0.07181151715261067, + "grad_norm": 1.195411864157985, + "learning_rate": 1.9908806665782907e-05, + "loss": 0.9638, + "step": 802 + }, + { + "epoch": 0.07190105769768873, + "grad_norm": 0.9967918875619503, + "learning_rate": 1.9908415457293236e-05, + "loss": 0.98, + "step": 803 + }, + { + "epoch": 0.07199059824276681, + "grad_norm": 1.0812973662883574, + "learning_rate": 1.9908023415339942e-05, + "loss": 0.9884, + "step": 804 + }, + { + "epoch": 0.07208013878784487, + "grad_norm": 1.1885252655924663, + "learning_rate": 1.990763053995601e-05, + "loss": 0.9026, + "step": 805 + }, + { + "epoch": 0.07216967933292294, + "grad_norm": 1.0891739197120993, + "learning_rate": 1.9907236831174478e-05, + "loss": 0.9449, + "step": 806 + }, + { + "epoch": 0.072259219878001, + "grad_norm": 1.147050963805907, + "learning_rate": 1.990684228902847e-05, + "loss": 0.9787, + "step": 807 + }, + { + "epoch": 0.07234876042307907, + "grad_norm": 1.1691899328969124, + "learning_rate": 1.9906446913551175e-05, + "loss": 0.8988, + "step": 808 + }, + { + "epoch": 0.07243830096815715, + "grad_norm": 1.3178311352243741, + "learning_rate": 1.9906050704775843e-05, + "loss": 0.9695, + "step": 809 + }, + { + "epoch": 0.07252784151323521, + "grad_norm": 1.0663062406941355, + "learning_rate": 1.990565366273581e-05, + "loss": 0.9881, + "step": 810 + }, + { + "epoch": 0.07261738205831328, + "grad_norm": 1.0793152584661805, + "learning_rate": 1.9905255787464472e-05, + "loss": 0.8543, + "step": 811 + }, + { + "epoch": 0.07270692260339134, + "grad_norm": 1.0461102867171508, + "learning_rate": 1.990485707899529e-05, + "loss": 0.9698, + "step": 812 + }, + { + "epoch": 0.07279646314846942, + "grad_norm": 1.2109224126389504, + "learning_rate": 1.9904457537361813e-05, + "loss": 0.9961, + "step": 813 + }, + { + "epoch": 0.07288600369354749, + "grad_norm": 0.98085687766607, + "learning_rate": 1.990405716259764e-05, + "loss": 0.9005, + "step": 814 + }, + { + "epoch": 0.07297554423862555, + "grad_norm": 1.069474099020944, + "learning_rate": 1.9903655954736453e-05, + "loss": 0.9127, + "step": 815 + }, + { + "epoch": 0.07306508478370362, + "grad_norm": 1.1862009982987851, + "learning_rate": 1.9903253913812003e-05, + "loss": 0.8805, + "step": 816 + }, + { + "epoch": 0.07315462532878168, + "grad_norm": 1.1064552442642315, + "learning_rate": 1.9902851039858106e-05, + "loss": 1.0002, + "step": 817 + }, + { + "epoch": 0.07324416587385976, + "grad_norm": 0.9780107926806036, + "learning_rate": 1.9902447332908644e-05, + "loss": 0.8877, + "step": 818 + }, + { + "epoch": 0.07333370641893783, + "grad_norm": 1.2882364895710248, + "learning_rate": 1.9902042792997587e-05, + "loss": 0.9507, + "step": 819 + }, + { + "epoch": 0.07342324696401589, + "grad_norm": 1.195830915019672, + "learning_rate": 1.9901637420158954e-05, + "loss": 0.8662, + "step": 820 + }, + { + "epoch": 0.07351278750909396, + "grad_norm": 1.0877331953843028, + "learning_rate": 1.990123121442685e-05, + "loss": 0.9253, + "step": 821 + }, + { + "epoch": 0.07360232805417204, + "grad_norm": 1.1889239438416268, + "learning_rate": 1.9900824175835444e-05, + "loss": 0.9345, + "step": 822 + }, + { + "epoch": 0.0736918685992501, + "grad_norm": 1.2332819647234583, + "learning_rate": 1.990041630441897e-05, + "loss": 0.9167, + "step": 823 + }, + { + "epoch": 0.07378140914432817, + "grad_norm": 1.0893100152241175, + "learning_rate": 1.990000760021174e-05, + "loss": 0.8805, + "step": 824 + }, + { + "epoch": 0.07387094968940623, + "grad_norm": 1.3023400058167218, + "learning_rate": 1.989959806324813e-05, + "loss": 0.9154, + "step": 825 + }, + { + "epoch": 0.0739604902344843, + "grad_norm": 1.1044464403255647, + "learning_rate": 1.989918769356259e-05, + "loss": 0.9626, + "step": 826 + }, + { + "epoch": 0.07405003077956238, + "grad_norm": 1.0409212186922727, + "learning_rate": 1.989877649118964e-05, + "loss": 0.9323, + "step": 827 + }, + { + "epoch": 0.07413957132464044, + "grad_norm": 1.0148919188027719, + "learning_rate": 1.989836445616387e-05, + "loss": 0.9261, + "step": 828 + }, + { + "epoch": 0.0742291118697185, + "grad_norm": 0.9834129070493376, + "learning_rate": 1.989795158851994e-05, + "loss": 0.9019, + "step": 829 + }, + { + "epoch": 0.07431865241479657, + "grad_norm": 1.1172460684844427, + "learning_rate": 1.9897537888292574e-05, + "loss": 0.9054, + "step": 830 + }, + { + "epoch": 0.07440819295987465, + "grad_norm": 1.044811474679815, + "learning_rate": 1.9897123355516573e-05, + "loss": 0.9059, + "step": 831 + }, + { + "epoch": 0.07449773350495272, + "grad_norm": 1.1855525786704262, + "learning_rate": 1.989670799022681e-05, + "loss": 0.9503, + "step": 832 + }, + { + "epoch": 0.07458727405003078, + "grad_norm": 1.3257963130221033, + "learning_rate": 1.9896291792458218e-05, + "loss": 0.851, + "step": 833 + }, + { + "epoch": 0.07467681459510885, + "grad_norm": 1.063757540663316, + "learning_rate": 1.9895874762245812e-05, + "loss": 0.908, + "step": 834 + }, + { + "epoch": 0.07476635514018691, + "grad_norm": 1.0275307848780335, + "learning_rate": 1.989545689962467e-05, + "loss": 0.9003, + "step": 835 + }, + { + "epoch": 0.07485589568526499, + "grad_norm": 1.1221584966859024, + "learning_rate": 1.989503820462994e-05, + "loss": 0.9226, + "step": 836 + }, + { + "epoch": 0.07494543623034305, + "grad_norm": 1.049560766570043, + "learning_rate": 1.989461867729684e-05, + "loss": 0.8622, + "step": 837 + }, + { + "epoch": 0.07503497677542112, + "grad_norm": 0.9460285130519487, + "learning_rate": 1.9894198317660657e-05, + "loss": 0.979, + "step": 838 + }, + { + "epoch": 0.07512451732049918, + "grad_norm": 1.0053222426446038, + "learning_rate": 1.9893777125756755e-05, + "loss": 0.9135, + "step": 839 + }, + { + "epoch": 0.07521405786557726, + "grad_norm": 1.172358860642403, + "learning_rate": 1.9893355101620564e-05, + "loss": 0.9244, + "step": 840 + }, + { + "epoch": 0.07530359841065533, + "grad_norm": 0.986120722221041, + "learning_rate": 1.989293224528758e-05, + "loss": 0.883, + "step": 841 + }, + { + "epoch": 0.0753931389557334, + "grad_norm": 0.979125132554207, + "learning_rate": 1.9892508556793376e-05, + "loss": 0.9187, + "step": 842 + }, + { + "epoch": 0.07548267950081146, + "grad_norm": 1.0469806246332762, + "learning_rate": 1.9892084036173587e-05, + "loss": 0.9008, + "step": 843 + }, + { + "epoch": 0.07557222004588952, + "grad_norm": 1.015302680443969, + "learning_rate": 1.9891658683463926e-05, + "loss": 0.9167, + "step": 844 + }, + { + "epoch": 0.0756617605909676, + "grad_norm": 1.1782112472479447, + "learning_rate": 1.989123249870017e-05, + "loss": 0.9699, + "step": 845 + }, + { + "epoch": 0.07575130113604567, + "grad_norm": 1.16077616347798, + "learning_rate": 1.989080548191817e-05, + "loss": 0.9116, + "step": 846 + }, + { + "epoch": 0.07584084168112373, + "grad_norm": 0.9522964757493606, + "learning_rate": 1.989037763315384e-05, + "loss": 0.9472, + "step": 847 + }, + { + "epoch": 0.0759303822262018, + "grad_norm": 1.398726611683997, + "learning_rate": 1.9889948952443174e-05, + "loss": 0.9338, + "step": 848 + }, + { + "epoch": 0.07601992277127988, + "grad_norm": 1.1083501916564726, + "learning_rate": 1.9889519439822232e-05, + "loss": 0.8741, + "step": 849 + }, + { + "epoch": 0.07610946331635794, + "grad_norm": 1.0855537638641066, + "learning_rate": 1.9889089095327143e-05, + "loss": 0.9401, + "step": 850 + }, + { + "epoch": 0.07619900386143601, + "grad_norm": 1.0898070345910735, + "learning_rate": 1.9888657918994102e-05, + "loss": 0.9068, + "step": 851 + }, + { + "epoch": 0.07628854440651407, + "grad_norm": 1.0136753208067075, + "learning_rate": 1.9888225910859386e-05, + "loss": 0.8943, + "step": 852 + }, + { + "epoch": 0.07637808495159214, + "grad_norm": 1.072756220801226, + "learning_rate": 1.9887793070959325e-05, + "loss": 0.9233, + "step": 853 + }, + { + "epoch": 0.07646762549667022, + "grad_norm": 0.9978351664243232, + "learning_rate": 1.9887359399330335e-05, + "loss": 0.8617, + "step": 854 + }, + { + "epoch": 0.07655716604174828, + "grad_norm": 1.0893068667969263, + "learning_rate": 1.9886924896008887e-05, + "loss": 0.9063, + "step": 855 + }, + { + "epoch": 0.07664670658682635, + "grad_norm": 1.0421004835075962, + "learning_rate": 1.988648956103154e-05, + "loss": 0.9575, + "step": 856 + }, + { + "epoch": 0.07673624713190441, + "grad_norm": 0.9726347044403362, + "learning_rate": 1.988605339443491e-05, + "loss": 0.8479, + "step": 857 + }, + { + "epoch": 0.07682578767698249, + "grad_norm": 0.9524692222340961, + "learning_rate": 1.988561639625568e-05, + "loss": 0.93, + "step": 858 + }, + { + "epoch": 0.07691532822206056, + "grad_norm": 1.1265438692635157, + "learning_rate": 1.9885178566530615e-05, + "loss": 0.9638, + "step": 859 + }, + { + "epoch": 0.07700486876713862, + "grad_norm": 0.9978472712549302, + "learning_rate": 1.988473990529654e-05, + "loss": 0.9611, + "step": 860 + }, + { + "epoch": 0.07709440931221669, + "grad_norm": 1.2762091930965278, + "learning_rate": 1.9884300412590357e-05, + "loss": 0.9169, + "step": 861 + }, + { + "epoch": 0.07718394985729475, + "grad_norm": 1.0698741410776418, + "learning_rate": 1.9883860088449035e-05, + "loss": 0.9678, + "step": 862 + }, + { + "epoch": 0.07727349040237283, + "grad_norm": 1.0051623823314215, + "learning_rate": 1.988341893290961e-05, + "loss": 0.8831, + "step": 863 + }, + { + "epoch": 0.0773630309474509, + "grad_norm": 1.058636369730302, + "learning_rate": 1.9882976946009188e-05, + "loss": 0.9564, + "step": 864 + }, + { + "epoch": 0.07745257149252896, + "grad_norm": 1.2072745181127453, + "learning_rate": 1.9882534127784954e-05, + "loss": 0.9106, + "step": 865 + }, + { + "epoch": 0.07754211203760702, + "grad_norm": 1.154359450731333, + "learning_rate": 1.9882090478274155e-05, + "loss": 0.9099, + "step": 866 + }, + { + "epoch": 0.0776316525826851, + "grad_norm": 1.1964280560949228, + "learning_rate": 1.9881645997514103e-05, + "loss": 1.0146, + "step": 867 + }, + { + "epoch": 0.07772119312776317, + "grad_norm": 1.0275174830566007, + "learning_rate": 1.9881200685542194e-05, + "loss": 0.944, + "step": 868 + }, + { + "epoch": 0.07781073367284123, + "grad_norm": 1.107584853628805, + "learning_rate": 1.9880754542395883e-05, + "loss": 0.9567, + "step": 869 + }, + { + "epoch": 0.0779002742179193, + "grad_norm": 0.9936334902527764, + "learning_rate": 1.98803075681127e-05, + "loss": 0.9024, + "step": 870 + }, + { + "epoch": 0.07798981476299736, + "grad_norm": 1.1440551976412965, + "learning_rate": 1.9879859762730242e-05, + "loss": 0.9362, + "step": 871 + }, + { + "epoch": 0.07807935530807544, + "grad_norm": 1.0233180174699994, + "learning_rate": 1.987941112628617e-05, + "loss": 0.9495, + "step": 872 + }, + { + "epoch": 0.07816889585315351, + "grad_norm": 0.9609663633090297, + "learning_rate": 1.9878961658818232e-05, + "loss": 0.8511, + "step": 873 + }, + { + "epoch": 0.07825843639823157, + "grad_norm": 1.0342393719877254, + "learning_rate": 1.9878511360364234e-05, + "loss": 0.8937, + "step": 874 + }, + { + "epoch": 0.07834797694330964, + "grad_norm": 0.954815428892118, + "learning_rate": 1.9878060230962052e-05, + "loss": 0.9195, + "step": 875 + }, + { + "epoch": 0.07843751748838772, + "grad_norm": 1.2511537339138603, + "learning_rate": 1.987760827064963e-05, + "loss": 0.9031, + "step": 876 + }, + { + "epoch": 0.07852705803346578, + "grad_norm": 1.149015218587212, + "learning_rate": 1.9877155479464986e-05, + "loss": 0.934, + "step": 877 + }, + { + "epoch": 0.07861659857854385, + "grad_norm": 0.9973306217903806, + "learning_rate": 1.9876701857446216e-05, + "loss": 0.8586, + "step": 878 + }, + { + "epoch": 0.07870613912362191, + "grad_norm": 1.091318391136101, + "learning_rate": 1.9876247404631467e-05, + "loss": 0.9178, + "step": 879 + }, + { + "epoch": 0.07879567966869998, + "grad_norm": 1.0190097633580029, + "learning_rate": 1.987579212105897e-05, + "loss": 0.9068, + "step": 880 + }, + { + "epoch": 0.07888522021377806, + "grad_norm": 0.9919129161513033, + "learning_rate": 1.9875336006767022e-05, + "loss": 0.8158, + "step": 881 + }, + { + "epoch": 0.07897476075885612, + "grad_norm": 1.1200371529016633, + "learning_rate": 1.9874879061793992e-05, + "loss": 0.9459, + "step": 882 + }, + { + "epoch": 0.07906430130393419, + "grad_norm": 0.9482865080430126, + "learning_rate": 1.9874421286178312e-05, + "loss": 0.9465, + "step": 883 + }, + { + "epoch": 0.07915384184901225, + "grad_norm": 1.0414767471873674, + "learning_rate": 1.9873962679958496e-05, + "loss": 0.8941, + "step": 884 + }, + { + "epoch": 0.07924338239409033, + "grad_norm": 1.1940635940311715, + "learning_rate": 1.987350324317311e-05, + "loss": 0.8841, + "step": 885 + }, + { + "epoch": 0.0793329229391684, + "grad_norm": 1.1039658120559788, + "learning_rate": 1.987304297586081e-05, + "loss": 0.9095, + "step": 886 + }, + { + "epoch": 0.07942246348424646, + "grad_norm": 1.1060534646017763, + "learning_rate": 1.9872581878060308e-05, + "loss": 0.937, + "step": 887 + }, + { + "epoch": 0.07951200402932453, + "grad_norm": 1.095542849670436, + "learning_rate": 1.9872119949810388e-05, + "loss": 0.9469, + "step": 888 + }, + { + "epoch": 0.07960154457440259, + "grad_norm": 1.3756595992905571, + "learning_rate": 1.987165719114991e-05, + "loss": 0.8979, + "step": 889 + }, + { + "epoch": 0.07969108511948067, + "grad_norm": 1.0765276310332224, + "learning_rate": 1.9871193602117797e-05, + "loss": 0.9172, + "step": 890 + }, + { + "epoch": 0.07978062566455874, + "grad_norm": 1.0442086599616847, + "learning_rate": 1.9870729182753042e-05, + "loss": 0.8942, + "step": 891 + }, + { + "epoch": 0.0798701662096368, + "grad_norm": 1.0289097323592844, + "learning_rate": 1.987026393309472e-05, + "loss": 0.966, + "step": 892 + }, + { + "epoch": 0.07995970675471487, + "grad_norm": 1.1004293616793352, + "learning_rate": 1.986979785318196e-05, + "loss": 0.9621, + "step": 893 + }, + { + "epoch": 0.08004924729979294, + "grad_norm": 0.97487133086226, + "learning_rate": 1.9869330943053963e-05, + "loss": 0.9094, + "step": 894 + }, + { + "epoch": 0.08013878784487101, + "grad_norm": 0.9922116079755481, + "learning_rate": 1.9868863202750012e-05, + "loss": 0.9102, + "step": 895 + }, + { + "epoch": 0.08022832838994907, + "grad_norm": 0.9995009918783716, + "learning_rate": 1.9868394632309443e-05, + "loss": 0.9394, + "step": 896 + }, + { + "epoch": 0.08031786893502714, + "grad_norm": 1.3502338924070718, + "learning_rate": 1.986792523177168e-05, + "loss": 0.9702, + "step": 897 + }, + { + "epoch": 0.0804074094801052, + "grad_norm": 1.0314188606483061, + "learning_rate": 1.9867455001176203e-05, + "loss": 0.9697, + "step": 898 + }, + { + "epoch": 0.08049695002518328, + "grad_norm": 1.01381117466966, + "learning_rate": 1.9866983940562564e-05, + "loss": 0.9302, + "step": 899 + }, + { + "epoch": 0.08058649057026135, + "grad_norm": 1.0049766874986243, + "learning_rate": 1.9866512049970393e-05, + "loss": 0.8975, + "step": 900 + }, + { + "epoch": 0.08067603111533941, + "grad_norm": 1.0668122923505434, + "learning_rate": 1.9866039329439376e-05, + "loss": 0.9539, + "step": 901 + }, + { + "epoch": 0.08076557166041748, + "grad_norm": 1.0762283633960257, + "learning_rate": 1.9865565779009282e-05, + "loss": 0.891, + "step": 902 + }, + { + "epoch": 0.08085511220549556, + "grad_norm": 1.157596894027934, + "learning_rate": 1.986509139871995e-05, + "loss": 0.9734, + "step": 903 + }, + { + "epoch": 0.08094465275057362, + "grad_norm": 0.9713434745409791, + "learning_rate": 1.9864616188611273e-05, + "loss": 0.8772, + "step": 904 + }, + { + "epoch": 0.08103419329565169, + "grad_norm": 1.0674147217625458, + "learning_rate": 1.9864140148723225e-05, + "loss": 0.9998, + "step": 905 + }, + { + "epoch": 0.08112373384072975, + "grad_norm": 1.110490493275662, + "learning_rate": 1.986366327909585e-05, + "loss": 0.9432, + "step": 906 + }, + { + "epoch": 0.08121327438580782, + "grad_norm": 1.0269226247158223, + "learning_rate": 1.986318557976927e-05, + "loss": 0.8966, + "step": 907 + }, + { + "epoch": 0.0813028149308859, + "grad_norm": 0.9354483742041779, + "learning_rate": 1.986270705078366e-05, + "loss": 0.8899, + "step": 908 + }, + { + "epoch": 0.08139235547596396, + "grad_norm": 1.2840740644893676, + "learning_rate": 1.9862227692179266e-05, + "loss": 0.9791, + "step": 909 + }, + { + "epoch": 0.08148189602104203, + "grad_norm": 1.1052827689776052, + "learning_rate": 1.9861747503996423e-05, + "loss": 0.8913, + "step": 910 + }, + { + "epoch": 0.08157143656612009, + "grad_norm": 1.0484833184344298, + "learning_rate": 1.9861266486275516e-05, + "loss": 0.9623, + "step": 911 + }, + { + "epoch": 0.08166097711119816, + "grad_norm": 0.9624154642879219, + "learning_rate": 1.9860784639057e-05, + "loss": 0.9145, + "step": 912 + }, + { + "epoch": 0.08175051765627624, + "grad_norm": 1.1638598847203674, + "learning_rate": 1.986030196238142e-05, + "loss": 0.8488, + "step": 913 + }, + { + "epoch": 0.0818400582013543, + "grad_norm": 1.1421538146287942, + "learning_rate": 1.985981845628937e-05, + "loss": 0.8823, + "step": 914 + }, + { + "epoch": 0.08192959874643237, + "grad_norm": 0.9717725518722011, + "learning_rate": 1.985933412082152e-05, + "loss": 0.9264, + "step": 915 + }, + { + "epoch": 0.08201913929151043, + "grad_norm": 1.0125066079262945, + "learning_rate": 1.9858848956018615e-05, + "loss": 0.9675, + "step": 916 + }, + { + "epoch": 0.08210867983658851, + "grad_norm": 0.9626661384813827, + "learning_rate": 1.985836296192146e-05, + "loss": 0.8714, + "step": 917 + }, + { + "epoch": 0.08219822038166658, + "grad_norm": 1.1893799942898362, + "learning_rate": 1.985787613857094e-05, + "loss": 0.9077, + "step": 918 + }, + { + "epoch": 0.08228776092674464, + "grad_norm": 0.995297789501123, + "learning_rate": 1.9857388486008e-05, + "loss": 0.9568, + "step": 919 + }, + { + "epoch": 0.0823773014718227, + "grad_norm": 1.2055443657267433, + "learning_rate": 1.9856900004273667e-05, + "loss": 0.9707, + "step": 920 + }, + { + "epoch": 0.08246684201690077, + "grad_norm": 1.1798788577781218, + "learning_rate": 1.9856410693409027e-05, + "loss": 0.8836, + "step": 921 + }, + { + "epoch": 0.08255638256197885, + "grad_norm": 0.9974944211547258, + "learning_rate": 1.9855920553455233e-05, + "loss": 0.97, + "step": 922 + }, + { + "epoch": 0.08264592310705692, + "grad_norm": 1.0293306086586178, + "learning_rate": 1.9855429584453525e-05, + "loss": 0.78, + "step": 923 + }, + { + "epoch": 0.08273546365213498, + "grad_norm": 1.0079138553253082, + "learning_rate": 1.9854937786445195e-05, + "loss": 0.9556, + "step": 924 + }, + { + "epoch": 0.08282500419721305, + "grad_norm": 1.0546394442349447, + "learning_rate": 1.9854445159471612e-05, + "loss": 0.9234, + "step": 925 + }, + { + "epoch": 0.08291454474229112, + "grad_norm": 0.9751918705661583, + "learning_rate": 1.9853951703574212e-05, + "loss": 0.8623, + "step": 926 + }, + { + "epoch": 0.08300408528736919, + "grad_norm": 1.027224139591515, + "learning_rate": 1.985345741879451e-05, + "loss": 0.8928, + "step": 927 + }, + { + "epoch": 0.08309362583244725, + "grad_norm": 1.2112814301711503, + "learning_rate": 1.985296230517408e-05, + "loss": 0.9415, + "step": 928 + }, + { + "epoch": 0.08318316637752532, + "grad_norm": 1.0106080884570308, + "learning_rate": 1.9852466362754566e-05, + "loss": 0.8633, + "step": 929 + }, + { + "epoch": 0.08327270692260338, + "grad_norm": 0.9541153973238627, + "learning_rate": 1.9851969591577688e-05, + "loss": 0.9079, + "step": 930 + }, + { + "epoch": 0.08336224746768146, + "grad_norm": 1.0439510120663027, + "learning_rate": 1.985147199168523e-05, + "loss": 0.8783, + "step": 931 + }, + { + "epoch": 0.08345178801275953, + "grad_norm": 0.9664476396941193, + "learning_rate": 1.9850973563119057e-05, + "loss": 0.8979, + "step": 932 + }, + { + "epoch": 0.0835413285578376, + "grad_norm": 0.9895526614269158, + "learning_rate": 1.9850474305921085e-05, + "loss": 0.9285, + "step": 933 + }, + { + "epoch": 0.08363086910291566, + "grad_norm": 0.9934600739152486, + "learning_rate": 1.984997422013332e-05, + "loss": 0.9336, + "step": 934 + }, + { + "epoch": 0.08372040964799374, + "grad_norm": 0.94432367653176, + "learning_rate": 1.9849473305797816e-05, + "loss": 0.9344, + "step": 935 + }, + { + "epoch": 0.0838099501930718, + "grad_norm": 0.9718989759799674, + "learning_rate": 1.9848971562956714e-05, + "loss": 0.9661, + "step": 936 + }, + { + "epoch": 0.08389949073814987, + "grad_norm": 1.103217733103473, + "learning_rate": 1.9848468991652223e-05, + "loss": 0.9605, + "step": 937 + }, + { + "epoch": 0.08398903128322793, + "grad_norm": 1.0776765612303294, + "learning_rate": 1.984796559192661e-05, + "loss": 0.9576, + "step": 938 + }, + { + "epoch": 0.084078571828306, + "grad_norm": 1.0640643135955883, + "learning_rate": 1.9847461363822226e-05, + "loss": 0.9284, + "step": 939 + }, + { + "epoch": 0.08416811237338408, + "grad_norm": 1.0498269360731822, + "learning_rate": 1.9846956307381478e-05, + "loss": 0.9225, + "step": 940 + }, + { + "epoch": 0.08425765291846214, + "grad_norm": 1.0038722167931113, + "learning_rate": 1.9846450422646856e-05, + "loss": 0.8449, + "step": 941 + }, + { + "epoch": 0.08434719346354021, + "grad_norm": 1.1707854737741155, + "learning_rate": 1.984594370966091e-05, + "loss": 0.8808, + "step": 942 + }, + { + "epoch": 0.08443673400861827, + "grad_norm": 1.0075888082366793, + "learning_rate": 1.9845436168466268e-05, + "loss": 0.8595, + "step": 943 + }, + { + "epoch": 0.08452627455369635, + "grad_norm": 1.0611600414896925, + "learning_rate": 1.9844927799105615e-05, + "loss": 0.966, + "step": 944 + }, + { + "epoch": 0.08461581509877442, + "grad_norm": 1.2655662234817153, + "learning_rate": 1.9844418601621717e-05, + "loss": 0.8728, + "step": 945 + }, + { + "epoch": 0.08470535564385248, + "grad_norm": 0.9937763950261357, + "learning_rate": 1.984390857605741e-05, + "loss": 0.8802, + "step": 946 + }, + { + "epoch": 0.08479489618893055, + "grad_norm": 1.1086121999821106, + "learning_rate": 1.984339772245559e-05, + "loss": 0.9178, + "step": 947 + }, + { + "epoch": 0.08488443673400861, + "grad_norm": 1.152711637981438, + "learning_rate": 1.9842886040859227e-05, + "loss": 0.8792, + "step": 948 + }, + { + "epoch": 0.08497397727908669, + "grad_norm": 0.9684161167811586, + "learning_rate": 1.9842373531311368e-05, + "loss": 0.8956, + "step": 949 + }, + { + "epoch": 0.08506351782416476, + "grad_norm": 0.9779956833136649, + "learning_rate": 1.9841860193855123e-05, + "loss": 0.8916, + "step": 950 + }, + { + "epoch": 0.08515305836924282, + "grad_norm": 0.9926653513776225, + "learning_rate": 1.984134602853367e-05, + "loss": 0.9212, + "step": 951 + }, + { + "epoch": 0.08524259891432089, + "grad_norm": 1.0049715602180254, + "learning_rate": 1.9840831035390256e-05, + "loss": 0.9167, + "step": 952 + }, + { + "epoch": 0.08533213945939896, + "grad_norm": 0.9951534227797122, + "learning_rate": 1.9840315214468205e-05, + "loss": 0.9622, + "step": 953 + }, + { + "epoch": 0.08542168000447703, + "grad_norm": 0.9840824273732606, + "learning_rate": 1.9839798565810904e-05, + "loss": 0.9117, + "step": 954 + }, + { + "epoch": 0.0855112205495551, + "grad_norm": 1.1096416555984059, + "learning_rate": 1.9839281089461814e-05, + "loss": 0.9509, + "step": 955 + }, + { + "epoch": 0.08560076109463316, + "grad_norm": 0.9371054583857013, + "learning_rate": 1.9838762785464463e-05, + "loss": 0.8573, + "step": 956 + }, + { + "epoch": 0.08569030163971122, + "grad_norm": 1.0397168721562617, + "learning_rate": 1.9838243653862445e-05, + "loss": 0.8528, + "step": 957 + }, + { + "epoch": 0.0857798421847893, + "grad_norm": 0.9974252072131928, + "learning_rate": 1.9837723694699433e-05, + "loss": 0.9024, + "step": 958 + }, + { + "epoch": 0.08586938272986737, + "grad_norm": 0.9269167540838222, + "learning_rate": 1.9837202908019163e-05, + "loss": 0.8868, + "step": 959 + }, + { + "epoch": 0.08595892327494543, + "grad_norm": 1.026676707058281, + "learning_rate": 1.9836681293865437e-05, + "loss": 0.9318, + "step": 960 + }, + { + "epoch": 0.0860484638200235, + "grad_norm": 1.0231294889452878, + "learning_rate": 1.983615885228214e-05, + "loss": 0.8848, + "step": 961 + }, + { + "epoch": 0.08613800436510158, + "grad_norm": 1.0344469809116108, + "learning_rate": 1.983563558331321e-05, + "loss": 0.8844, + "step": 962 + }, + { + "epoch": 0.08622754491017964, + "grad_norm": 0.9965134612996915, + "learning_rate": 1.983511148700267e-05, + "loss": 0.8785, + "step": 963 + }, + { + "epoch": 0.08631708545525771, + "grad_norm": 1.0534718798171145, + "learning_rate": 1.9834586563394597e-05, + "loss": 1.0106, + "step": 964 + }, + { + "epoch": 0.08640662600033577, + "grad_norm": 1.0481195463158086, + "learning_rate": 1.9834060812533154e-05, + "loss": 0.9701, + "step": 965 + }, + { + "epoch": 0.08649616654541384, + "grad_norm": 0.9899595228445589, + "learning_rate": 1.9833534234462557e-05, + "loss": 0.8952, + "step": 966 + }, + { + "epoch": 0.08658570709049192, + "grad_norm": 1.0868492373640468, + "learning_rate": 1.983300682922711e-05, + "loss": 0.9329, + "step": 967 + }, + { + "epoch": 0.08667524763556998, + "grad_norm": 1.2262011641275323, + "learning_rate": 1.983247859687117e-05, + "loss": 0.9234, + "step": 968 + }, + { + "epoch": 0.08676478818064805, + "grad_norm": 1.0772032862620653, + "learning_rate": 1.983194953743917e-05, + "loss": 0.8953, + "step": 969 + }, + { + "epoch": 0.08685432872572611, + "grad_norm": 1.0675983895005767, + "learning_rate": 1.9831419650975615e-05, + "loss": 0.9733, + "step": 970 + }, + { + "epoch": 0.08694386927080419, + "grad_norm": 1.2501123395676448, + "learning_rate": 1.9830888937525076e-05, + "loss": 0.9397, + "step": 971 + }, + { + "epoch": 0.08703340981588226, + "grad_norm": 1.095557769603638, + "learning_rate": 1.9830357397132195e-05, + "loss": 0.9316, + "step": 972 + }, + { + "epoch": 0.08712295036096032, + "grad_norm": 1.0971694381241326, + "learning_rate": 1.9829825029841685e-05, + "loss": 0.9679, + "step": 973 + }, + { + "epoch": 0.08721249090603839, + "grad_norm": 1.0667984812123603, + "learning_rate": 1.9829291835698327e-05, + "loss": 0.8779, + "step": 974 + }, + { + "epoch": 0.08730203145111645, + "grad_norm": 1.521079951676263, + "learning_rate": 1.982875781474697e-05, + "loss": 0.9467, + "step": 975 + }, + { + "epoch": 0.08739157199619453, + "grad_norm": 1.3260451496365067, + "learning_rate": 1.9828222967032533e-05, + "loss": 0.887, + "step": 976 + }, + { + "epoch": 0.0874811125412726, + "grad_norm": 1.0134691260707183, + "learning_rate": 1.982768729260001e-05, + "loss": 0.9104, + "step": 977 + }, + { + "epoch": 0.08757065308635066, + "grad_norm": 0.9913957574891373, + "learning_rate": 1.9827150791494456e-05, + "loss": 0.8669, + "step": 978 + }, + { + "epoch": 0.08766019363142873, + "grad_norm": 1.1784309301231677, + "learning_rate": 1.9826613463761e-05, + "loss": 0.9756, + "step": 979 + }, + { + "epoch": 0.0877497341765068, + "grad_norm": 1.1074836383849385, + "learning_rate": 1.9826075309444844e-05, + "loss": 0.8943, + "step": 980 + }, + { + "epoch": 0.08783927472158487, + "grad_norm": 1.1385921601241735, + "learning_rate": 1.982553632859125e-05, + "loss": 0.9255, + "step": 981 + }, + { + "epoch": 0.08792881526666294, + "grad_norm": 1.0959945777606708, + "learning_rate": 1.982499652124556e-05, + "loss": 0.9173, + "step": 982 + }, + { + "epoch": 0.088018355811741, + "grad_norm": 0.9969992545068587, + "learning_rate": 1.9824455887453183e-05, + "loss": 0.9662, + "step": 983 + }, + { + "epoch": 0.08810789635681907, + "grad_norm": 1.0181188967985257, + "learning_rate": 1.9823914427259587e-05, + "loss": 0.9067, + "step": 984 + }, + { + "epoch": 0.08819743690189714, + "grad_norm": 1.0875032959411282, + "learning_rate": 1.9823372140710323e-05, + "loss": 0.9194, + "step": 985 + }, + { + "epoch": 0.08828697744697521, + "grad_norm": 1.0299510514153334, + "learning_rate": 1.9822829027851008e-05, + "loss": 0.8837, + "step": 986 + }, + { + "epoch": 0.08837651799205327, + "grad_norm": 1.0798399483776007, + "learning_rate": 1.9822285088727325e-05, + "loss": 0.85, + "step": 987 + }, + { + "epoch": 0.08846605853713134, + "grad_norm": 1.1956424938804886, + "learning_rate": 1.982174032338503e-05, + "loss": 0.9412, + "step": 988 + }, + { + "epoch": 0.08855559908220942, + "grad_norm": 1.0271872795928232, + "learning_rate": 1.982119473186994e-05, + "loss": 0.9272, + "step": 989 + }, + { + "epoch": 0.08864513962728748, + "grad_norm": 0.9585939455906575, + "learning_rate": 1.9820648314227955e-05, + "loss": 0.8847, + "step": 990 + }, + { + "epoch": 0.08873468017236555, + "grad_norm": 1.0072877375774447, + "learning_rate": 1.9820101070505037e-05, + "loss": 0.9752, + "step": 991 + }, + { + "epoch": 0.08882422071744361, + "grad_norm": 0.9466452666562966, + "learning_rate": 1.981955300074722e-05, + "loss": 0.9197, + "step": 992 + }, + { + "epoch": 0.08891376126252168, + "grad_norm": 1.0779060526672624, + "learning_rate": 1.98190041050006e-05, + "loss": 0.9326, + "step": 993 + }, + { + "epoch": 0.08900330180759976, + "grad_norm": 1.110192928947384, + "learning_rate": 1.9818454383311354e-05, + "loss": 0.9118, + "step": 994 + }, + { + "epoch": 0.08909284235267782, + "grad_norm": 1.079618550688469, + "learning_rate": 1.9817903835725722e-05, + "loss": 0.9472, + "step": 995 + }, + { + "epoch": 0.08918238289775589, + "grad_norm": 1.1231999133280581, + "learning_rate": 1.981735246229001e-05, + "loss": 0.8823, + "step": 996 + }, + { + "epoch": 0.08927192344283395, + "grad_norm": 0.9555806211868249, + "learning_rate": 1.98168002630506e-05, + "loss": 0.9189, + "step": 997 + }, + { + "epoch": 0.08936146398791203, + "grad_norm": 1.0599882822921154, + "learning_rate": 1.9816247238053945e-05, + "loss": 0.8937, + "step": 998 + }, + { + "epoch": 0.0894510045329901, + "grad_norm": 1.0330507579481685, + "learning_rate": 1.981569338734656e-05, + "loss": 0.8559, + "step": 999 + }, + { + "epoch": 0.08954054507806816, + "grad_norm": 1.0274329533470439, + "learning_rate": 1.9815138710975034e-05, + "loss": 0.9322, + "step": 1000 + }, + { + "epoch": 0.08963008562314623, + "grad_norm": 1.0234300158613456, + "learning_rate": 1.9814583208986025e-05, + "loss": 0.8729, + "step": 1001 + }, + { + "epoch": 0.08971962616822429, + "grad_norm": 0.9421514095390102, + "learning_rate": 1.9814026881426257e-05, + "loss": 0.9092, + "step": 1002 + }, + { + "epoch": 0.08980916671330237, + "grad_norm": 1.2209412227878513, + "learning_rate": 1.9813469728342528e-05, + "loss": 0.959, + "step": 1003 + }, + { + "epoch": 0.08989870725838044, + "grad_norm": 1.1655560856800042, + "learning_rate": 1.9812911749781708e-05, + "loss": 0.9118, + "step": 1004 + }, + { + "epoch": 0.0899882478034585, + "grad_norm": 1.0597807712499405, + "learning_rate": 1.9812352945790727e-05, + "loss": 0.9842, + "step": 1005 + }, + { + "epoch": 0.09007778834853657, + "grad_norm": 1.0958791052542398, + "learning_rate": 1.981179331641659e-05, + "loss": 0.9567, + "step": 1006 + }, + { + "epoch": 0.09016732889361465, + "grad_norm": 1.046416417326152, + "learning_rate": 1.9811232861706375e-05, + "loss": 0.8955, + "step": 1007 + }, + { + "epoch": 0.09025686943869271, + "grad_norm": 1.0485843963938237, + "learning_rate": 1.9810671581707223e-05, + "loss": 0.9137, + "step": 1008 + }, + { + "epoch": 0.09034640998377078, + "grad_norm": 0.9669841723056106, + "learning_rate": 1.981010947646635e-05, + "loss": 0.9143, + "step": 1009 + }, + { + "epoch": 0.09043595052884884, + "grad_norm": 1.4164449333950715, + "learning_rate": 1.9809546546031034e-05, + "loss": 0.9608, + "step": 1010 + }, + { + "epoch": 0.0905254910739269, + "grad_norm": 1.2457272570540057, + "learning_rate": 1.9808982790448626e-05, + "loss": 0.8898, + "step": 1011 + }, + { + "epoch": 0.09061503161900498, + "grad_norm": 1.1020328166852127, + "learning_rate": 1.9808418209766555e-05, + "loss": 0.9283, + "step": 1012 + }, + { + "epoch": 0.09070457216408305, + "grad_norm": 1.415791903060292, + "learning_rate": 1.9807852804032306e-05, + "loss": 0.9224, + "step": 1013 + }, + { + "epoch": 0.09079411270916111, + "grad_norm": 0.9646842119953011, + "learning_rate": 1.980728657329344e-05, + "loss": 0.8747, + "step": 1014 + }, + { + "epoch": 0.09088365325423918, + "grad_norm": 1.0564722822310322, + "learning_rate": 1.9806719517597585e-05, + "loss": 0.981, + "step": 1015 + }, + { + "epoch": 0.09097319379931726, + "grad_norm": 0.9845211264969549, + "learning_rate": 1.9806151636992442e-05, + "loss": 0.9722, + "step": 1016 + }, + { + "epoch": 0.09106273434439532, + "grad_norm": 1.0403992744328583, + "learning_rate": 1.9805582931525778e-05, + "loss": 0.9104, + "step": 1017 + }, + { + "epoch": 0.09115227488947339, + "grad_norm": 1.0133472160579726, + "learning_rate": 1.9805013401245433e-05, + "loss": 0.8911, + "step": 1018 + }, + { + "epoch": 0.09124181543455145, + "grad_norm": 1.2142596298266948, + "learning_rate": 1.9804443046199312e-05, + "loss": 0.9061, + "step": 1019 + }, + { + "epoch": 0.09133135597962952, + "grad_norm": 0.9486957964706776, + "learning_rate": 1.9803871866435388e-05, + "loss": 0.9635, + "step": 1020 + }, + { + "epoch": 0.0914208965247076, + "grad_norm": 0.9151812311535943, + "learning_rate": 1.9803299862001718e-05, + "loss": 0.8816, + "step": 1021 + }, + { + "epoch": 0.09151043706978566, + "grad_norm": 1.1240229704895737, + "learning_rate": 1.9802727032946403e-05, + "loss": 0.9645, + "step": 1022 + }, + { + "epoch": 0.09159997761486373, + "grad_norm": 1.058999213458839, + "learning_rate": 1.9802153379317637e-05, + "loss": 0.9191, + "step": 1023 + }, + { + "epoch": 0.0916895181599418, + "grad_norm": 1.1658814233499575, + "learning_rate": 1.9801578901163672e-05, + "loss": 0.944, + "step": 1024 + }, + { + "epoch": 0.09177905870501987, + "grad_norm": 1.0605232071772988, + "learning_rate": 1.9801003598532827e-05, + "loss": 0.7986, + "step": 1025 + }, + { + "epoch": 0.09186859925009794, + "grad_norm": 0.955664807178467, + "learning_rate": 1.98004274714735e-05, + "loss": 0.8903, + "step": 1026 + }, + { + "epoch": 0.091958139795176, + "grad_norm": 1.0847315551485432, + "learning_rate": 1.9799850520034153e-05, + "loss": 0.902, + "step": 1027 + }, + { + "epoch": 0.09204768034025407, + "grad_norm": 0.9939200285737662, + "learning_rate": 1.9799272744263313e-05, + "loss": 0.9115, + "step": 1028 + }, + { + "epoch": 0.09213722088533213, + "grad_norm": 1.0532498032742155, + "learning_rate": 1.979869414420958e-05, + "loss": 0.9297, + "step": 1029 + }, + { + "epoch": 0.09222676143041021, + "grad_norm": 0.9622891522514779, + "learning_rate": 1.9798114719921628e-05, + "loss": 0.8777, + "step": 1030 + }, + { + "epoch": 0.09231630197548828, + "grad_norm": 1.0012282236948824, + "learning_rate": 1.9797534471448196e-05, + "loss": 0.8606, + "step": 1031 + }, + { + "epoch": 0.09240584252056634, + "grad_norm": 1.0312431295016427, + "learning_rate": 1.9796953398838093e-05, + "loss": 0.9968, + "step": 1032 + }, + { + "epoch": 0.09249538306564441, + "grad_norm": 0.9830740030757321, + "learning_rate": 1.979637150214019e-05, + "loss": 0.901, + "step": 1033 + }, + { + "epoch": 0.09258492361072249, + "grad_norm": 1.146771052458193, + "learning_rate": 1.9795788781403447e-05, + "loss": 0.8475, + "step": 1034 + }, + { + "epoch": 0.09267446415580055, + "grad_norm": 0.9883362276670867, + "learning_rate": 1.9795205236676865e-05, + "loss": 0.9003, + "step": 1035 + }, + { + "epoch": 0.09276400470087862, + "grad_norm": 1.019018445826406, + "learning_rate": 1.9794620868009545e-05, + "loss": 0.9499, + "step": 1036 + }, + { + "epoch": 0.09285354524595668, + "grad_norm": 1.003740687539369, + "learning_rate": 1.9794035675450635e-05, + "loss": 0.8682, + "step": 1037 + }, + { + "epoch": 0.09294308579103475, + "grad_norm": 1.1111575509548541, + "learning_rate": 1.9793449659049357e-05, + "loss": 0.8974, + "step": 1038 + }, + { + "epoch": 0.09303262633611283, + "grad_norm": 1.086207399449774, + "learning_rate": 1.979286281885501e-05, + "loss": 0.8601, + "step": 1039 + }, + { + "epoch": 0.09312216688119089, + "grad_norm": 0.9864269597188605, + "learning_rate": 1.979227515491695e-05, + "loss": 0.9164, + "step": 1040 + }, + { + "epoch": 0.09321170742626896, + "grad_norm": 1.09340168363352, + "learning_rate": 1.9791686667284618e-05, + "loss": 0.8485, + "step": 1041 + }, + { + "epoch": 0.09330124797134702, + "grad_norm": 1.0355627750293275, + "learning_rate": 1.9791097356007513e-05, + "loss": 0.907, + "step": 1042 + }, + { + "epoch": 0.0933907885164251, + "grad_norm": 1.090475822875002, + "learning_rate": 1.9790507221135202e-05, + "loss": 0.9047, + "step": 1043 + }, + { + "epoch": 0.09348032906150316, + "grad_norm": 1.2004433326352437, + "learning_rate": 1.978991626271733e-05, + "loss": 0.947, + "step": 1044 + }, + { + "epoch": 0.09356986960658123, + "grad_norm": 1.0894461996314844, + "learning_rate": 1.9789324480803605e-05, + "loss": 0.9804, + "step": 1045 + }, + { + "epoch": 0.0936594101516593, + "grad_norm": 1.0098904594767402, + "learning_rate": 1.9788731875443802e-05, + "loss": 0.8698, + "step": 1046 + }, + { + "epoch": 0.09374895069673736, + "grad_norm": 1.0577728695864634, + "learning_rate": 1.9788138446687773e-05, + "loss": 0.8765, + "step": 1047 + }, + { + "epoch": 0.09383849124181544, + "grad_norm": 1.2769421847128455, + "learning_rate": 1.9787544194585437e-05, + "loss": 0.9203, + "step": 1048 + }, + { + "epoch": 0.0939280317868935, + "grad_norm": 0.9849360932620246, + "learning_rate": 1.9786949119186774e-05, + "loss": 0.9374, + "step": 1049 + }, + { + "epoch": 0.09401757233197157, + "grad_norm": 1.0576888252311865, + "learning_rate": 1.978635322054185e-05, + "loss": 0.9129, + "step": 1050 + }, + { + "epoch": 0.09410711287704963, + "grad_norm": 1.0051680354901051, + "learning_rate": 1.9785756498700777e-05, + "loss": 0.9505, + "step": 1051 + }, + { + "epoch": 0.09419665342212771, + "grad_norm": 0.952109883653877, + "learning_rate": 1.978515895371376e-05, + "loss": 0.8648, + "step": 1052 + }, + { + "epoch": 0.09428619396720578, + "grad_norm": 1.0794268734044075, + "learning_rate": 1.9784560585631056e-05, + "loss": 0.9103, + "step": 1053 + }, + { + "epoch": 0.09437573451228384, + "grad_norm": 1.0076834506740375, + "learning_rate": 1.9783961394503006e-05, + "loss": 0.9404, + "step": 1054 + }, + { + "epoch": 0.09446527505736191, + "grad_norm": 1.1272984789338714, + "learning_rate": 1.978336138038e-05, + "loss": 0.9581, + "step": 1055 + }, + { + "epoch": 0.09455481560243997, + "grad_norm": 1.0641271107973076, + "learning_rate": 1.9782760543312516e-05, + "loss": 0.8743, + "step": 1056 + }, + { + "epoch": 0.09464435614751805, + "grad_norm": 1.075565797992441, + "learning_rate": 1.97821588833511e-05, + "loss": 0.9017, + "step": 1057 + }, + { + "epoch": 0.09473389669259612, + "grad_norm": 1.0516850040224077, + "learning_rate": 1.9781556400546353e-05, + "loss": 0.9039, + "step": 1058 + }, + { + "epoch": 0.09482343723767418, + "grad_norm": 1.0503580297337258, + "learning_rate": 1.978095309494896e-05, + "loss": 0.9712, + "step": 1059 + }, + { + "epoch": 0.09491297778275225, + "grad_norm": 0.9516708996642765, + "learning_rate": 1.978034896660966e-05, + "loss": 0.9009, + "step": 1060 + }, + { + "epoch": 0.09500251832783033, + "grad_norm": 1.910174287334749, + "learning_rate": 1.9779744015579277e-05, + "loss": 0.9339, + "step": 1061 + }, + { + "epoch": 0.09509205887290839, + "grad_norm": 1.034851018690442, + "learning_rate": 1.97791382419087e-05, + "loss": 0.8583, + "step": 1062 + }, + { + "epoch": 0.09518159941798646, + "grad_norm": 0.9734652060442432, + "learning_rate": 1.977853164564888e-05, + "loss": 0.8798, + "step": 1063 + }, + { + "epoch": 0.09527113996306452, + "grad_norm": 0.996597694037772, + "learning_rate": 1.9777924226850844e-05, + "loss": 1.0061, + "step": 1064 + }, + { + "epoch": 0.09536068050814259, + "grad_norm": 0.9819965332412642, + "learning_rate": 1.9777315985565683e-05, + "loss": 0.9103, + "step": 1065 + }, + { + "epoch": 0.09545022105322067, + "grad_norm": 1.0127562631858829, + "learning_rate": 1.9776706921844564e-05, + "loss": 0.888, + "step": 1066 + }, + { + "epoch": 0.09553976159829873, + "grad_norm": 0.9380302714651403, + "learning_rate": 1.977609703573872e-05, + "loss": 0.8817, + "step": 1067 + }, + { + "epoch": 0.0956293021433768, + "grad_norm": 0.9862625751950775, + "learning_rate": 1.977548632729945e-05, + "loss": 0.9401, + "step": 1068 + }, + { + "epoch": 0.09571884268845486, + "grad_norm": 1.1309850156196304, + "learning_rate": 1.9774874796578124e-05, + "loss": 0.9306, + "step": 1069 + }, + { + "epoch": 0.09580838323353294, + "grad_norm": 0.9895531720071091, + "learning_rate": 1.9774262443626185e-05, + "loss": 0.9768, + "step": 1070 + }, + { + "epoch": 0.095897923778611, + "grad_norm": 1.1417478118624353, + "learning_rate": 1.977364926849514e-05, + "loss": 0.9471, + "step": 1071 + }, + { + "epoch": 0.09598746432368907, + "grad_norm": 1.0980272794419574, + "learning_rate": 1.9773035271236566e-05, + "loss": 0.9188, + "step": 1072 + }, + { + "epoch": 0.09607700486876714, + "grad_norm": 0.9888380867734908, + "learning_rate": 1.9772420451902115e-05, + "loss": 0.8634, + "step": 1073 + }, + { + "epoch": 0.0961665454138452, + "grad_norm": 1.037767551312556, + "learning_rate": 1.97718048105435e-05, + "loss": 0.8821, + "step": 1074 + }, + { + "epoch": 0.09625608595892328, + "grad_norm": 1.066034715830074, + "learning_rate": 1.977118834721251e-05, + "loss": 0.9147, + "step": 1075 + }, + { + "epoch": 0.09634562650400134, + "grad_norm": 1.0316301053496342, + "learning_rate": 1.9770571061960996e-05, + "loss": 0.9247, + "step": 1076 + }, + { + "epoch": 0.09643516704907941, + "grad_norm": 1.0474911181696074, + "learning_rate": 1.9769952954840882e-05, + "loss": 0.9821, + "step": 1077 + }, + { + "epoch": 0.09652470759415747, + "grad_norm": 1.0092610666110011, + "learning_rate": 1.9769334025904162e-05, + "loss": 0.932, + "step": 1078 + }, + { + "epoch": 0.09661424813923555, + "grad_norm": 1.0203325383301238, + "learning_rate": 1.9768714275202903e-05, + "loss": 0.8728, + "step": 1079 + }, + { + "epoch": 0.09670378868431362, + "grad_norm": 1.259346019100911, + "learning_rate": 1.9768093702789232e-05, + "loss": 0.9368, + "step": 1080 + }, + { + "epoch": 0.09679332922939168, + "grad_norm": 1.0060297315961224, + "learning_rate": 1.9767472308715347e-05, + "loss": 0.9569, + "step": 1081 + }, + { + "epoch": 0.09688286977446975, + "grad_norm": 1.0122703628121168, + "learning_rate": 1.9766850093033524e-05, + "loss": 0.8733, + "step": 1082 + }, + { + "epoch": 0.09697241031954781, + "grad_norm": 1.0590893057428121, + "learning_rate": 1.9766227055796098e-05, + "loss": 0.9278, + "step": 1083 + }, + { + "epoch": 0.09706195086462589, + "grad_norm": 1.159262333022713, + "learning_rate": 1.9765603197055474e-05, + "loss": 0.9562, + "step": 1084 + }, + { + "epoch": 0.09715149140970396, + "grad_norm": 1.0036398522477317, + "learning_rate": 1.9764978516864134e-05, + "loss": 0.9499, + "step": 1085 + }, + { + "epoch": 0.09724103195478202, + "grad_norm": 0.9611113089961691, + "learning_rate": 1.9764353015274625e-05, + "loss": 0.9706, + "step": 1086 + }, + { + "epoch": 0.09733057249986009, + "grad_norm": 1.0257411372994734, + "learning_rate": 1.9763726692339557e-05, + "loss": 0.9178, + "step": 1087 + }, + { + "epoch": 0.09742011304493817, + "grad_norm": 1.0295769059231825, + "learning_rate": 1.9763099548111616e-05, + "loss": 0.9514, + "step": 1088 + }, + { + "epoch": 0.09750965359001623, + "grad_norm": 1.1071447559979999, + "learning_rate": 1.976247158264356e-05, + "loss": 0.9599, + "step": 1089 + }, + { + "epoch": 0.0975991941350943, + "grad_norm": 1.0219363715398784, + "learning_rate": 1.9761842795988203e-05, + "loss": 0.9188, + "step": 1090 + }, + { + "epoch": 0.09768873468017236, + "grad_norm": 1.007994452495011, + "learning_rate": 1.976121318819844e-05, + "loss": 0.8456, + "step": 1091 + }, + { + "epoch": 0.09777827522525043, + "grad_norm": 1.0461179140238144, + "learning_rate": 1.9760582759327235e-05, + "loss": 0.9205, + "step": 1092 + }, + { + "epoch": 0.0978678157703285, + "grad_norm": 0.9338443115476841, + "learning_rate": 1.9759951509427617e-05, + "loss": 0.893, + "step": 1093 + }, + { + "epoch": 0.09795735631540657, + "grad_norm": 1.0303488204276987, + "learning_rate": 1.975931943855268e-05, + "loss": 0.9195, + "step": 1094 + }, + { + "epoch": 0.09804689686048464, + "grad_norm": 1.1332943161797837, + "learning_rate": 1.97586865467556e-05, + "loss": 0.9269, + "step": 1095 + }, + { + "epoch": 0.0981364374055627, + "grad_norm": 0.9467693460557545, + "learning_rate": 1.97580528340896e-05, + "loss": 0.9311, + "step": 1096 + }, + { + "epoch": 0.09822597795064078, + "grad_norm": 0.9737908555982472, + "learning_rate": 1.9757418300608e-05, + "loss": 0.881, + "step": 1097 + }, + { + "epoch": 0.09831551849571885, + "grad_norm": 1.0222661133425628, + "learning_rate": 1.9756782946364167e-05, + "loss": 0.9064, + "step": 1098 + }, + { + "epoch": 0.09840505904079691, + "grad_norm": 1.070488127045209, + "learning_rate": 1.9756146771411548e-05, + "loss": 0.8713, + "step": 1099 + }, + { + "epoch": 0.09849459958587498, + "grad_norm": 1.006387573826333, + "learning_rate": 1.9755509775803655e-05, + "loss": 0.8702, + "step": 1100 + }, + { + "epoch": 0.09858414013095304, + "grad_norm": 1.0776658103075902, + "learning_rate": 1.9754871959594068e-05, + "loss": 0.9183, + "step": 1101 + }, + { + "epoch": 0.09867368067603112, + "grad_norm": 1.1021292886742495, + "learning_rate": 1.9754233322836442e-05, + "loss": 0.9987, + "step": 1102 + }, + { + "epoch": 0.09876322122110918, + "grad_norm": 1.0777557693088786, + "learning_rate": 1.9753593865584494e-05, + "loss": 0.9454, + "step": 1103 + }, + { + "epoch": 0.09885276176618725, + "grad_norm": 1.051129296962062, + "learning_rate": 1.9752953587892013e-05, + "loss": 0.9751, + "step": 1104 + }, + { + "epoch": 0.09894230231126531, + "grad_norm": 1.064424084371974, + "learning_rate": 1.9752312489812858e-05, + "loss": 0.9069, + "step": 1105 + }, + { + "epoch": 0.0990318428563434, + "grad_norm": 1.0717808176527297, + "learning_rate": 1.975167057140096e-05, + "loss": 0.935, + "step": 1106 + }, + { + "epoch": 0.09912138340142146, + "grad_norm": 0.9886460816081393, + "learning_rate": 1.975102783271031e-05, + "loss": 0.9105, + "step": 1107 + }, + { + "epoch": 0.09921092394649952, + "grad_norm": 0.9541678205642731, + "learning_rate": 1.9750384273794973e-05, + "loss": 0.8864, + "step": 1108 + }, + { + "epoch": 0.09930046449157759, + "grad_norm": 1.036816717341618, + "learning_rate": 1.9749739894709086e-05, + "loss": 0.865, + "step": 1109 + }, + { + "epoch": 0.09939000503665565, + "grad_norm": 1.1418725226503275, + "learning_rate": 1.974909469550685e-05, + "loss": 0.9053, + "step": 1110 + }, + { + "epoch": 0.09947954558173373, + "grad_norm": 1.1069408548954163, + "learning_rate": 1.9748448676242537e-05, + "loss": 0.9581, + "step": 1111 + }, + { + "epoch": 0.0995690861268118, + "grad_norm": 1.054975568639669, + "learning_rate": 1.9747801836970488e-05, + "loss": 0.8699, + "step": 1112 + }, + { + "epoch": 0.09965862667188986, + "grad_norm": 1.0890106441783503, + "learning_rate": 1.9747154177745114e-05, + "loss": 0.8498, + "step": 1113 + }, + { + "epoch": 0.09974816721696793, + "grad_norm": 1.1323011383718826, + "learning_rate": 1.9746505698620895e-05, + "loss": 0.9866, + "step": 1114 + }, + { + "epoch": 0.09983770776204601, + "grad_norm": 1.0241738730740941, + "learning_rate": 1.9745856399652377e-05, + "loss": 0.8983, + "step": 1115 + }, + { + "epoch": 0.09992724830712407, + "grad_norm": 1.1240433898033322, + "learning_rate": 1.974520628089418e-05, + "loss": 0.9776, + "step": 1116 + }, + { + "epoch": 0.10001678885220214, + "grad_norm": 1.0650535772906575, + "learning_rate": 1.9744555342400984e-05, + "loss": 0.847, + "step": 1117 + }, + { + "epoch": 0.1001063293972802, + "grad_norm": 0.9777548495138415, + "learning_rate": 1.9743903584227546e-05, + "loss": 0.9401, + "step": 1118 + }, + { + "epoch": 0.10019586994235827, + "grad_norm": 0.9959217337503538, + "learning_rate": 1.9743251006428693e-05, + "loss": 0.9555, + "step": 1119 + }, + { + "epoch": 0.10028541048743635, + "grad_norm": 0.9817017279641013, + "learning_rate": 1.9742597609059317e-05, + "loss": 0.8934, + "step": 1120 + }, + { + "epoch": 0.10037495103251441, + "grad_norm": 0.9835651836478607, + "learning_rate": 1.9741943392174377e-05, + "loss": 0.88, + "step": 1121 + }, + { + "epoch": 0.10046449157759248, + "grad_norm": 0.977627600993251, + "learning_rate": 1.9741288355828906e-05, + "loss": 0.9089, + "step": 1122 + }, + { + "epoch": 0.10055403212267054, + "grad_norm": 1.131363326208526, + "learning_rate": 1.9740632500078e-05, + "loss": 0.9504, + "step": 1123 + }, + { + "epoch": 0.10064357266774862, + "grad_norm": 1.0834079387161248, + "learning_rate": 1.9739975824976832e-05, + "loss": 0.9591, + "step": 1124 + }, + { + "epoch": 0.10073311321282669, + "grad_norm": 0.9589963755139915, + "learning_rate": 1.9739318330580637e-05, + "loss": 0.9139, + "step": 1125 + }, + { + "epoch": 0.10082265375790475, + "grad_norm": 0.9409126984197141, + "learning_rate": 1.973866001694472e-05, + "loss": 0.8619, + "step": 1126 + }, + { + "epoch": 0.10091219430298282, + "grad_norm": 1.0591025019406468, + "learning_rate": 1.973800088412446e-05, + "loss": 0.8933, + "step": 1127 + }, + { + "epoch": 0.10100173484806088, + "grad_norm": 1.0481879420224454, + "learning_rate": 1.9737340932175297e-05, + "loss": 0.9378, + "step": 1128 + }, + { + "epoch": 0.10109127539313896, + "grad_norm": 0.9861865493268669, + "learning_rate": 1.9736680161152747e-05, + "loss": 0.8456, + "step": 1129 + }, + { + "epoch": 0.10118081593821703, + "grad_norm": 1.034652246288241, + "learning_rate": 1.9736018571112393e-05, + "loss": 0.9027, + "step": 1130 + }, + { + "epoch": 0.10127035648329509, + "grad_norm": 1.0819514775286645, + "learning_rate": 1.973535616210988e-05, + "loss": 0.9308, + "step": 1131 + }, + { + "epoch": 0.10135989702837316, + "grad_norm": 1.0264013999120254, + "learning_rate": 1.9734692934200936e-05, + "loss": 0.9381, + "step": 1132 + }, + { + "epoch": 0.10144943757345123, + "grad_norm": 0.9786435371653626, + "learning_rate": 1.9734028887441336e-05, + "loss": 0.9589, + "step": 1133 + }, + { + "epoch": 0.1015389781185293, + "grad_norm": 1.064483474996282, + "learning_rate": 1.9733364021886953e-05, + "loss": 0.8995, + "step": 1134 + }, + { + "epoch": 0.10162851866360736, + "grad_norm": 1.0417357242274723, + "learning_rate": 1.973269833759371e-05, + "loss": 0.954, + "step": 1135 + }, + { + "epoch": 0.10171805920868543, + "grad_norm": 1.0192819587711033, + "learning_rate": 1.973203183461759e-05, + "loss": 0.907, + "step": 1136 + }, + { + "epoch": 0.1018075997537635, + "grad_norm": 1.0036681947326171, + "learning_rate": 1.9731364513014673e-05, + "loss": 0.8687, + "step": 1137 + }, + { + "epoch": 0.10189714029884157, + "grad_norm": 0.9484731881705861, + "learning_rate": 1.973069637284108e-05, + "loss": 0.9013, + "step": 1138 + }, + { + "epoch": 0.10198668084391964, + "grad_norm": 1.0322437328572343, + "learning_rate": 1.973002741415302e-05, + "loss": 0.9365, + "step": 1139 + }, + { + "epoch": 0.1020762213889977, + "grad_norm": 1.1618378607753725, + "learning_rate": 1.9729357637006758e-05, + "loss": 0.9173, + "step": 1140 + }, + { + "epoch": 0.10216576193407577, + "grad_norm": 1.0109044867943355, + "learning_rate": 1.972868704145864e-05, + "loss": 0.9307, + "step": 1141 + }, + { + "epoch": 0.10225530247915385, + "grad_norm": 1.2838042114930606, + "learning_rate": 1.972801562756507e-05, + "loss": 0.8625, + "step": 1142 + }, + { + "epoch": 0.10234484302423191, + "grad_norm": 0.9872604215141734, + "learning_rate": 1.972734339538253e-05, + "loss": 0.9257, + "step": 1143 + }, + { + "epoch": 0.10243438356930998, + "grad_norm": 1.0917688054282646, + "learning_rate": 1.9726670344967558e-05, + "loss": 0.9373, + "step": 1144 + }, + { + "epoch": 0.10252392411438804, + "grad_norm": 1.0259275639408205, + "learning_rate": 1.972599647637677e-05, + "loss": 0.8999, + "step": 1145 + }, + { + "epoch": 0.10261346465946611, + "grad_norm": 0.98610979625717, + "learning_rate": 1.9725321789666858e-05, + "loss": 0.9178, + "step": 1146 + }, + { + "epoch": 0.10270300520454419, + "grad_norm": 1.0290554851743896, + "learning_rate": 1.9724646284894565e-05, + "loss": 0.8958, + "step": 1147 + }, + { + "epoch": 0.10279254574962225, + "grad_norm": 0.949912473371854, + "learning_rate": 1.9723969962116723e-05, + "loss": 0.9462, + "step": 1148 + }, + { + "epoch": 0.10288208629470032, + "grad_norm": 1.0109177267552307, + "learning_rate": 1.972329282139021e-05, + "loss": 0.8549, + "step": 1149 + }, + { + "epoch": 0.10297162683977838, + "grad_norm": 1.068537105194316, + "learning_rate": 1.972261486277199e-05, + "loss": 0.8918, + "step": 1150 + }, + { + "epoch": 0.10306116738485646, + "grad_norm": 1.0629665724590318, + "learning_rate": 1.972193608631909e-05, + "loss": 0.8754, + "step": 1151 + }, + { + "epoch": 0.10315070792993453, + "grad_norm": 0.9839002607992869, + "learning_rate": 1.9721256492088612e-05, + "loss": 0.8914, + "step": 1152 + }, + { + "epoch": 0.10324024847501259, + "grad_norm": 0.9379596512612858, + "learning_rate": 1.9720576080137712e-05, + "loss": 0.953, + "step": 1153 + }, + { + "epoch": 0.10332978902009066, + "grad_norm": 1.0249004898873135, + "learning_rate": 1.9719894850523632e-05, + "loss": 0.8928, + "step": 1154 + }, + { + "epoch": 0.10341932956516872, + "grad_norm": 1.0652426568227717, + "learning_rate": 1.9719212803303667e-05, + "loss": 0.8851, + "step": 1155 + }, + { + "epoch": 0.1035088701102468, + "grad_norm": 0.9785425929421279, + "learning_rate": 1.97185299385352e-05, + "loss": 0.9825, + "step": 1156 + }, + { + "epoch": 0.10359841065532487, + "grad_norm": 1.119670890099895, + "learning_rate": 1.9717846256275658e-05, + "loss": 0.8895, + "step": 1157 + }, + { + "epoch": 0.10368795120040293, + "grad_norm": 0.9543151647224134, + "learning_rate": 1.9717161756582556e-05, + "loss": 0.9026, + "step": 1158 + }, + { + "epoch": 0.103777491745481, + "grad_norm": 1.043367843043276, + "learning_rate": 1.9716476439513475e-05, + "loss": 0.9232, + "step": 1159 + }, + { + "epoch": 0.10386703229055907, + "grad_norm": 0.9736616098318307, + "learning_rate": 1.971579030512606e-05, + "loss": 0.9333, + "step": 1160 + }, + { + "epoch": 0.10395657283563714, + "grad_norm": 0.9769493635721329, + "learning_rate": 1.9715103353478025e-05, + "loss": 0.9446, + "step": 1161 + }, + { + "epoch": 0.1040461133807152, + "grad_norm": 1.0398216882607856, + "learning_rate": 1.9714415584627154e-05, + "loss": 0.896, + "step": 1162 + }, + { + "epoch": 0.10413565392579327, + "grad_norm": 1.0670522282771877, + "learning_rate": 1.97137269986313e-05, + "loss": 0.8979, + "step": 1163 + }, + { + "epoch": 0.10422519447087134, + "grad_norm": 1.0388046666302806, + "learning_rate": 1.9713037595548384e-05, + "loss": 0.9799, + "step": 1164 + }, + { + "epoch": 0.10431473501594941, + "grad_norm": 1.0583555233844038, + "learning_rate": 1.97123473754364e-05, + "loss": 0.8833, + "step": 1165 + }, + { + "epoch": 0.10440427556102748, + "grad_norm": 1.1093430023141209, + "learning_rate": 1.9711656338353405e-05, + "loss": 0.9151, + "step": 1166 + }, + { + "epoch": 0.10449381610610554, + "grad_norm": 1.1563792817894711, + "learning_rate": 1.9710964484357525e-05, + "loss": 0.9366, + "step": 1167 + }, + { + "epoch": 0.10458335665118361, + "grad_norm": 0.9504001200600805, + "learning_rate": 1.9710271813506954e-05, + "loss": 0.8996, + "step": 1168 + }, + { + "epoch": 0.10467289719626169, + "grad_norm": 1.0381207129895476, + "learning_rate": 1.9709578325859966e-05, + "loss": 0.8413, + "step": 1169 + }, + { + "epoch": 0.10476243774133975, + "grad_norm": 1.0776500750960065, + "learning_rate": 1.9708884021474887e-05, + "loss": 0.941, + "step": 1170 + }, + { + "epoch": 0.10485197828641782, + "grad_norm": 0.8768290045595767, + "learning_rate": 1.9708188900410124e-05, + "loss": 0.9412, + "step": 1171 + }, + { + "epoch": 0.10494151883149588, + "grad_norm": 1.3607932869922454, + "learning_rate": 1.9707492962724145e-05, + "loss": 0.9074, + "step": 1172 + }, + { + "epoch": 0.10503105937657395, + "grad_norm": 1.0274254118100763, + "learning_rate": 1.9706796208475494e-05, + "loss": 0.9784, + "step": 1173 + }, + { + "epoch": 0.10512059992165203, + "grad_norm": 0.9784190327116986, + "learning_rate": 1.9706098637722777e-05, + "loss": 0.8839, + "step": 1174 + }, + { + "epoch": 0.10521014046673009, + "grad_norm": 1.2148588628092742, + "learning_rate": 1.970540025052467e-05, + "loss": 0.9178, + "step": 1175 + }, + { + "epoch": 0.10529968101180816, + "grad_norm": 1.0851605430794924, + "learning_rate": 1.9704701046939924e-05, + "loss": 0.9373, + "step": 1176 + }, + { + "epoch": 0.10538922155688622, + "grad_norm": 1.0293826814610691, + "learning_rate": 1.970400102702735e-05, + "loss": 0.9305, + "step": 1177 + }, + { + "epoch": 0.1054787621019643, + "grad_norm": 1.057856097232794, + "learning_rate": 1.9703300190845832e-05, + "loss": 0.9592, + "step": 1178 + }, + { + "epoch": 0.10556830264704237, + "grad_norm": 0.9613266217718636, + "learning_rate": 1.970259853845432e-05, + "loss": 0.9335, + "step": 1179 + }, + { + "epoch": 0.10565784319212043, + "grad_norm": 1.0505166946126554, + "learning_rate": 1.9701896069911837e-05, + "loss": 0.8769, + "step": 1180 + }, + { + "epoch": 0.1057473837371985, + "grad_norm": 1.0470387979497533, + "learning_rate": 1.9701192785277474e-05, + "loss": 0.8985, + "step": 1181 + }, + { + "epoch": 0.10583692428227656, + "grad_norm": 1.075553118941208, + "learning_rate": 1.9700488684610384e-05, + "loss": 0.9204, + "step": 1182 + }, + { + "epoch": 0.10592646482735464, + "grad_norm": 1.1046751641836459, + "learning_rate": 1.9699783767969802e-05, + "loss": 0.896, + "step": 1183 + }, + { + "epoch": 0.1060160053724327, + "grad_norm": 0.8720513561211994, + "learning_rate": 1.9699078035415016e-05, + "loss": 0.8709, + "step": 1184 + }, + { + "epoch": 0.10610554591751077, + "grad_norm": 1.0955988736273328, + "learning_rate": 1.9698371487005393e-05, + "loss": 0.8522, + "step": 1185 + }, + { + "epoch": 0.10619508646258884, + "grad_norm": 0.9512189929963133, + "learning_rate": 1.9697664122800364e-05, + "loss": 0.9689, + "step": 1186 + }, + { + "epoch": 0.10628462700766692, + "grad_norm": 0.9939746933502719, + "learning_rate": 1.969695594285943e-05, + "loss": 0.8877, + "step": 1187 + }, + { + "epoch": 0.10637416755274498, + "grad_norm": 1.0442084088085233, + "learning_rate": 1.969624694724216e-05, + "loss": 0.927, + "step": 1188 + }, + { + "epoch": 0.10646370809782305, + "grad_norm": 1.100768922037487, + "learning_rate": 1.9695537136008198e-05, + "loss": 0.9042, + "step": 1189 + }, + { + "epoch": 0.10655324864290111, + "grad_norm": 0.9857780037114541, + "learning_rate": 1.9694826509217246e-05, + "loss": 0.9408, + "step": 1190 + }, + { + "epoch": 0.10664278918797918, + "grad_norm": 1.0793850672267609, + "learning_rate": 1.9694115066929077e-05, + "loss": 0.859, + "step": 1191 + }, + { + "epoch": 0.10673232973305725, + "grad_norm": 1.049658191831442, + "learning_rate": 1.969340280920354e-05, + "loss": 0.888, + "step": 1192 + }, + { + "epoch": 0.10682187027813532, + "grad_norm": 1.236077198601478, + "learning_rate": 1.969268973610055e-05, + "loss": 0.9171, + "step": 1193 + }, + { + "epoch": 0.10691141082321338, + "grad_norm": 1.0645498495100685, + "learning_rate": 1.9691975847680083e-05, + "loss": 0.9539, + "step": 1194 + }, + { + "epoch": 0.10700095136829145, + "grad_norm": 1.121622986724315, + "learning_rate": 1.969126114400219e-05, + "loss": 0.9562, + "step": 1195 + }, + { + "epoch": 0.10709049191336953, + "grad_norm": 1.0356234207089117, + "learning_rate": 1.9690545625126992e-05, + "loss": 0.8937, + "step": 1196 + }, + { + "epoch": 0.1071800324584476, + "grad_norm": 0.9323487948990646, + "learning_rate": 1.9689829291114672e-05, + "loss": 0.9112, + "step": 1197 + }, + { + "epoch": 0.10726957300352566, + "grad_norm": 1.0351496136265128, + "learning_rate": 1.968911214202549e-05, + "loss": 0.8923, + "step": 1198 + }, + { + "epoch": 0.10735911354860372, + "grad_norm": 1.0053938729950094, + "learning_rate": 1.968839417791977e-05, + "loss": 0.8822, + "step": 1199 + }, + { + "epoch": 0.10744865409368179, + "grad_norm": 0.9521780714901025, + "learning_rate": 1.96876753988579e-05, + "loss": 0.8733, + "step": 1200 + }, + { + "epoch": 0.10753819463875987, + "grad_norm": 1.0557986448112182, + "learning_rate": 1.968695580490035e-05, + "loss": 0.9224, + "step": 1201 + }, + { + "epoch": 0.10762773518383793, + "grad_norm": 1.0233107602760776, + "learning_rate": 1.9686235396107643e-05, + "loss": 0.9881, + "step": 1202 + }, + { + "epoch": 0.107717275728916, + "grad_norm": 1.1013271469703025, + "learning_rate": 1.9685514172540376e-05, + "loss": 0.893, + "step": 1203 + }, + { + "epoch": 0.10780681627399406, + "grad_norm": 1.025278197486952, + "learning_rate": 1.968479213425922e-05, + "loss": 0.9139, + "step": 1204 + }, + { + "epoch": 0.10789635681907214, + "grad_norm": 1.0934839232056313, + "learning_rate": 1.968406928132491e-05, + "loss": 0.9483, + "step": 1205 + }, + { + "epoch": 0.10798589736415021, + "grad_norm": 1.111228569236409, + "learning_rate": 1.968334561379825e-05, + "loss": 0.9196, + "step": 1206 + }, + { + "epoch": 0.10807543790922827, + "grad_norm": 1.0331827908027558, + "learning_rate": 1.9682621131740113e-05, + "loss": 0.966, + "step": 1207 + }, + { + "epoch": 0.10816497845430634, + "grad_norm": 0.9575784559686565, + "learning_rate": 1.968189583521144e-05, + "loss": 0.9089, + "step": 1208 + }, + { + "epoch": 0.1082545189993844, + "grad_norm": 1.0059004166608105, + "learning_rate": 1.9681169724273234e-05, + "loss": 0.8681, + "step": 1209 + }, + { + "epoch": 0.10834405954446248, + "grad_norm": 1.0402474580728576, + "learning_rate": 1.9680442798986583e-05, + "loss": 0.8892, + "step": 1210 + }, + { + "epoch": 0.10843360008954055, + "grad_norm": 1.119499429680588, + "learning_rate": 1.967971505941263e-05, + "loss": 0.9499, + "step": 1211 + }, + { + "epoch": 0.10852314063461861, + "grad_norm": 1.0433341773204021, + "learning_rate": 1.9678986505612588e-05, + "loss": 0.9099, + "step": 1212 + }, + { + "epoch": 0.10861268117969668, + "grad_norm": 1.0373608720394272, + "learning_rate": 1.9678257137647743e-05, + "loss": 0.9815, + "step": 1213 + }, + { + "epoch": 0.10870222172477476, + "grad_norm": 1.1026693588643004, + "learning_rate": 1.9677526955579447e-05, + "loss": 0.9411, + "step": 1214 + }, + { + "epoch": 0.10879176226985282, + "grad_norm": 1.1355303994980288, + "learning_rate": 1.9676795959469118e-05, + "loss": 0.9029, + "step": 1215 + }, + { + "epoch": 0.10888130281493089, + "grad_norm": 1.151370074061366, + "learning_rate": 1.9676064149378246e-05, + "loss": 0.9007, + "step": 1216 + }, + { + "epoch": 0.10897084336000895, + "grad_norm": 0.9464784551112853, + "learning_rate": 1.9675331525368393e-05, + "loss": 0.8788, + "step": 1217 + }, + { + "epoch": 0.10906038390508702, + "grad_norm": 0.9992943285997412, + "learning_rate": 1.9674598087501178e-05, + "loss": 0.95, + "step": 1218 + }, + { + "epoch": 0.1091499244501651, + "grad_norm": 0.9700550999863214, + "learning_rate": 1.96738638358383e-05, + "loss": 0.8586, + "step": 1219 + }, + { + "epoch": 0.10923946499524316, + "grad_norm": 1.0514072744605174, + "learning_rate": 1.9673128770441517e-05, + "loss": 0.9006, + "step": 1220 + }, + { + "epoch": 0.10932900554032123, + "grad_norm": 1.065278865721725, + "learning_rate": 1.9672392891372665e-05, + "loss": 0.9489, + "step": 1221 + }, + { + "epoch": 0.10941854608539929, + "grad_norm": 1.0641722812386099, + "learning_rate": 1.9671656198693644e-05, + "loss": 0.9231, + "step": 1222 + }, + { + "epoch": 0.10950808663047737, + "grad_norm": 0.9797263632262364, + "learning_rate": 1.9670918692466423e-05, + "loss": 0.923, + "step": 1223 + }, + { + "epoch": 0.10959762717555543, + "grad_norm": 1.0830307286486993, + "learning_rate": 1.9670180372753032e-05, + "loss": 0.9225, + "step": 1224 + }, + { + "epoch": 0.1096871677206335, + "grad_norm": 1.0118130084972117, + "learning_rate": 1.9669441239615582e-05, + "loss": 0.9758, + "step": 1225 + }, + { + "epoch": 0.10977670826571156, + "grad_norm": 1.0992328513356622, + "learning_rate": 1.9668701293116242e-05, + "loss": 0.9025, + "step": 1226 + }, + { + "epoch": 0.10986624881078963, + "grad_norm": 1.0747676542516822, + "learning_rate": 1.9667960533317262e-05, + "loss": 0.9033, + "step": 1227 + }, + { + "epoch": 0.10995578935586771, + "grad_norm": 1.0246617639121685, + "learning_rate": 1.9667218960280944e-05, + "loss": 0.8871, + "step": 1228 + }, + { + "epoch": 0.11004532990094577, + "grad_norm": 1.1254608814943894, + "learning_rate": 1.966647657406967e-05, + "loss": 0.9509, + "step": 1229 + }, + { + "epoch": 0.11013487044602384, + "grad_norm": 0.9452480528440533, + "learning_rate": 1.966573337474589e-05, + "loss": 0.9192, + "step": 1230 + }, + { + "epoch": 0.1102244109911019, + "grad_norm": 1.1344532791201427, + "learning_rate": 1.966498936237211e-05, + "loss": 0.8675, + "step": 1231 + }, + { + "epoch": 0.11031395153617998, + "grad_norm": 1.092476633311408, + "learning_rate": 1.9664244537010924e-05, + "loss": 0.9328, + "step": 1232 + }, + { + "epoch": 0.11040349208125805, + "grad_norm": 0.9830555593313395, + "learning_rate": 1.9663498898724976e-05, + "loss": 0.9252, + "step": 1233 + }, + { + "epoch": 0.11049303262633611, + "grad_norm": 0.9786953216543333, + "learning_rate": 1.9662752447576996e-05, + "loss": 0.9117, + "step": 1234 + }, + { + "epoch": 0.11058257317141418, + "grad_norm": 0.9475314214421442, + "learning_rate": 1.966200518362977e-05, + "loss": 0.8858, + "step": 1235 + }, + { + "epoch": 0.11067211371649224, + "grad_norm": 0.9040971276887072, + "learning_rate": 1.9661257106946146e-05, + "loss": 0.9135, + "step": 1236 + }, + { + "epoch": 0.11076165426157032, + "grad_norm": 0.9044584768865382, + "learning_rate": 1.9660508217589064e-05, + "loss": 0.9115, + "step": 1237 + }, + { + "epoch": 0.11085119480664839, + "grad_norm": 1.0430566794140101, + "learning_rate": 1.965975851562151e-05, + "loss": 0.9192, + "step": 1238 + }, + { + "epoch": 0.11094073535172645, + "grad_norm": 0.9559080000154662, + "learning_rate": 1.9659008001106548e-05, + "loss": 0.934, + "step": 1239 + }, + { + "epoch": 0.11103027589680452, + "grad_norm": 1.0633370194896092, + "learning_rate": 1.9658256674107306e-05, + "loss": 0.9443, + "step": 1240 + }, + { + "epoch": 0.1111198164418826, + "grad_norm": 0.9743264823192463, + "learning_rate": 1.965750453468699e-05, + "loss": 0.9485, + "step": 1241 + }, + { + "epoch": 0.11120935698696066, + "grad_norm": 1.0840768942277546, + "learning_rate": 1.965675158290886e-05, + "loss": 0.866, + "step": 1242 + }, + { + "epoch": 0.11129889753203873, + "grad_norm": 0.9560330327922378, + "learning_rate": 1.9655997818836255e-05, + "loss": 0.854, + "step": 1243 + }, + { + "epoch": 0.11138843807711679, + "grad_norm": 1.0010794767547186, + "learning_rate": 1.9655243242532586e-05, + "loss": 0.8588, + "step": 1244 + }, + { + "epoch": 0.11147797862219486, + "grad_norm": 1.074962805523423, + "learning_rate": 1.9654487854061312e-05, + "loss": 0.9025, + "step": 1245 + }, + { + "epoch": 0.11156751916727294, + "grad_norm": 1.0563225838759038, + "learning_rate": 1.9653731653485983e-05, + "loss": 0.9225, + "step": 1246 + }, + { + "epoch": 0.111657059712351, + "grad_norm": 1.0501217229968427, + "learning_rate": 1.9652974640870205e-05, + "loss": 0.9209, + "step": 1247 + }, + { + "epoch": 0.11174660025742907, + "grad_norm": 0.9483180350747387, + "learning_rate": 1.9652216816277657e-05, + "loss": 0.8596, + "step": 1248 + }, + { + "epoch": 0.11183614080250713, + "grad_norm": 0.9817309708807991, + "learning_rate": 1.9651458179772086e-05, + "loss": 0.9526, + "step": 1249 + }, + { + "epoch": 0.11192568134758521, + "grad_norm": 1.2195318914924007, + "learning_rate": 1.9650698731417303e-05, + "loss": 0.9498, + "step": 1250 + }, + { + "epoch": 0.11201522189266327, + "grad_norm": 1.130307496339976, + "learning_rate": 1.964993847127719e-05, + "loss": 0.9311, + "step": 1251 + }, + { + "epoch": 0.11210476243774134, + "grad_norm": 1.008420338131407, + "learning_rate": 1.96491773994157e-05, + "loss": 0.9409, + "step": 1252 + }, + { + "epoch": 0.1121943029828194, + "grad_norm": 1.0715620898182732, + "learning_rate": 1.9648415515896856e-05, + "loss": 0.8776, + "step": 1253 + }, + { + "epoch": 0.11228384352789747, + "grad_norm": 0.9533874022368671, + "learning_rate": 1.964765282078473e-05, + "loss": 0.9018, + "step": 1254 + }, + { + "epoch": 0.11237338407297555, + "grad_norm": 1.0056522970358104, + "learning_rate": 1.9646889314143497e-05, + "loss": 0.9187, + "step": 1255 + }, + { + "epoch": 0.11246292461805361, + "grad_norm": 1.0602916349108247, + "learning_rate": 1.9646124996037366e-05, + "loss": 0.809, + "step": 1256 + }, + { + "epoch": 0.11255246516313168, + "grad_norm": 1.0903747948514444, + "learning_rate": 1.9645359866530637e-05, + "loss": 0.9285, + "step": 1257 + }, + { + "epoch": 0.11264200570820974, + "grad_norm": 1.139057600192617, + "learning_rate": 1.9644593925687664e-05, + "loss": 0.8864, + "step": 1258 + }, + { + "epoch": 0.11273154625328782, + "grad_norm": 1.0728366758513683, + "learning_rate": 1.964382717357288e-05, + "loss": 0.9195, + "step": 1259 + }, + { + "epoch": 0.11282108679836589, + "grad_norm": 0.982301522296523, + "learning_rate": 1.9643059610250782e-05, + "loss": 0.9798, + "step": 1260 + }, + { + "epoch": 0.11291062734344395, + "grad_norm": 1.0579189148034154, + "learning_rate": 1.9642291235785934e-05, + "loss": 0.8847, + "step": 1261 + }, + { + "epoch": 0.11300016788852202, + "grad_norm": 1.0315195463976252, + "learning_rate": 1.9641522050242967e-05, + "loss": 0.9224, + "step": 1262 + }, + { + "epoch": 0.11308970843360008, + "grad_norm": 0.9928912917214777, + "learning_rate": 1.9640752053686583e-05, + "loss": 0.8708, + "step": 1263 + }, + { + "epoch": 0.11317924897867816, + "grad_norm": 1.038513303491386, + "learning_rate": 1.9639981246181557e-05, + "loss": 0.9055, + "step": 1264 + }, + { + "epoch": 0.11326878952375623, + "grad_norm": 0.9414946277870256, + "learning_rate": 1.9639209627792717e-05, + "loss": 0.9221, + "step": 1265 + }, + { + "epoch": 0.11335833006883429, + "grad_norm": 0.9990236547935908, + "learning_rate": 1.9638437198584977e-05, + "loss": 0.9065, + "step": 1266 + }, + { + "epoch": 0.11344787061391236, + "grad_norm": 1.2040427413386114, + "learning_rate": 1.9637663958623306e-05, + "loss": 0.8889, + "step": 1267 + }, + { + "epoch": 0.11353741115899044, + "grad_norm": 1.0203027446154496, + "learning_rate": 1.9636889907972755e-05, + "loss": 0.9152, + "step": 1268 + }, + { + "epoch": 0.1136269517040685, + "grad_norm": 0.9526450534387981, + "learning_rate": 1.9636115046698425e-05, + "loss": 0.9374, + "step": 1269 + }, + { + "epoch": 0.11371649224914657, + "grad_norm": 0.9658103267865827, + "learning_rate": 1.9635339374865498e-05, + "loss": 0.9298, + "step": 1270 + }, + { + "epoch": 0.11380603279422463, + "grad_norm": 1.000474720218233, + "learning_rate": 1.9634562892539223e-05, + "loss": 0.925, + "step": 1271 + }, + { + "epoch": 0.1138955733393027, + "grad_norm": 1.0189020642376136, + "learning_rate": 1.9633785599784915e-05, + "loss": 0.9059, + "step": 1272 + }, + { + "epoch": 0.11398511388438078, + "grad_norm": 1.0329732228244708, + "learning_rate": 1.9633007496667952e-05, + "loss": 0.8741, + "step": 1273 + }, + { + "epoch": 0.11407465442945884, + "grad_norm": 0.960745478530226, + "learning_rate": 1.963222858325379e-05, + "loss": 0.9007, + "step": 1274 + }, + { + "epoch": 0.1141641949745369, + "grad_norm": 0.9432458237189475, + "learning_rate": 1.9631448859607952e-05, + "loss": 0.8629, + "step": 1275 + }, + { + "epoch": 0.11425373551961497, + "grad_norm": 1.0785546845689313, + "learning_rate": 1.9630668325796018e-05, + "loss": 0.9023, + "step": 1276 + }, + { + "epoch": 0.11434327606469305, + "grad_norm": 0.986932891460453, + "learning_rate": 1.962988698188365e-05, + "loss": 0.964, + "step": 1277 + }, + { + "epoch": 0.11443281660977112, + "grad_norm": 0.9930103543877402, + "learning_rate": 1.9629104827936568e-05, + "loss": 0.9789, + "step": 1278 + }, + { + "epoch": 0.11452235715484918, + "grad_norm": 1.3197895204871661, + "learning_rate": 1.962832186402057e-05, + "loss": 0.9482, + "step": 1279 + }, + { + "epoch": 0.11461189769992725, + "grad_norm": 1.0023922177161164, + "learning_rate": 1.962753809020151e-05, + "loss": 0.9381, + "step": 1280 + }, + { + "epoch": 0.11470143824500531, + "grad_norm": 1.0796816078717577, + "learning_rate": 1.962675350654532e-05, + "loss": 0.984, + "step": 1281 + }, + { + "epoch": 0.11479097879008339, + "grad_norm": 1.0019777684476319, + "learning_rate": 1.9625968113117995e-05, + "loss": 0.9128, + "step": 1282 + }, + { + "epoch": 0.11488051933516145, + "grad_norm": 0.9195471247574172, + "learning_rate": 1.96251819099856e-05, + "loss": 0.9241, + "step": 1283 + }, + { + "epoch": 0.11497005988023952, + "grad_norm": 1.0017246281437422, + "learning_rate": 1.962439489721427e-05, + "loss": 0.9037, + "step": 1284 + }, + { + "epoch": 0.11505960042531758, + "grad_norm": 1.0563661871155432, + "learning_rate": 1.9623607074870203e-05, + "loss": 0.9244, + "step": 1285 + }, + { + "epoch": 0.11514914097039566, + "grad_norm": 0.9967000872367829, + "learning_rate": 1.9622818443019672e-05, + "loss": 0.867, + "step": 1286 + }, + { + "epoch": 0.11523868151547373, + "grad_norm": 1.0444741091111438, + "learning_rate": 1.962202900172901e-05, + "loss": 0.9055, + "step": 1287 + }, + { + "epoch": 0.1153282220605518, + "grad_norm": 1.0007276453154084, + "learning_rate": 1.962123875106462e-05, + "loss": 0.9484, + "step": 1288 + }, + { + "epoch": 0.11541776260562986, + "grad_norm": 0.9484499221437401, + "learning_rate": 1.9620447691092984e-05, + "loss": 0.8488, + "step": 1289 + }, + { + "epoch": 0.11550730315070792, + "grad_norm": 1.0568259400726043, + "learning_rate": 1.9619655821880634e-05, + "loss": 0.918, + "step": 1290 + }, + { + "epoch": 0.115596843695786, + "grad_norm": 0.9607336072178856, + "learning_rate": 1.961886314349419e-05, + "loss": 0.945, + "step": 1291 + }, + { + "epoch": 0.11568638424086407, + "grad_norm": 0.9911020404746291, + "learning_rate": 1.961806965600032e-05, + "loss": 0.8589, + "step": 1292 + }, + { + "epoch": 0.11577592478594213, + "grad_norm": 1.0640787527727469, + "learning_rate": 1.961727535946577e-05, + "loss": 0.8809, + "step": 1293 + }, + { + "epoch": 0.1158654653310202, + "grad_norm": 1.049525796813032, + "learning_rate": 1.961648025395736e-05, + "loss": 0.9131, + "step": 1294 + }, + { + "epoch": 0.11595500587609828, + "grad_norm": 0.8800093257356222, + "learning_rate": 1.9615684339541968e-05, + "loss": 0.8469, + "step": 1295 + }, + { + "epoch": 0.11604454642117634, + "grad_norm": 1.0011524451971945, + "learning_rate": 1.9614887616286544e-05, + "loss": 0.917, + "step": 1296 + }, + { + "epoch": 0.11613408696625441, + "grad_norm": 0.9938437228070213, + "learning_rate": 1.9614090084258106e-05, + "loss": 0.9394, + "step": 1297 + }, + { + "epoch": 0.11622362751133247, + "grad_norm": 1.1706007213667857, + "learning_rate": 1.961329174352374e-05, + "loss": 0.9289, + "step": 1298 + }, + { + "epoch": 0.11631316805641054, + "grad_norm": 0.9135298725831902, + "learning_rate": 1.9612492594150597e-05, + "loss": 0.8945, + "step": 1299 + }, + { + "epoch": 0.11640270860148862, + "grad_norm": 1.1327584467114007, + "learning_rate": 1.9611692636205903e-05, + "loss": 0.9087, + "step": 1300 + }, + { + "epoch": 0.11649224914656668, + "grad_norm": 0.9293213619614189, + "learning_rate": 1.9610891869756945e-05, + "loss": 0.8751, + "step": 1301 + }, + { + "epoch": 0.11658178969164475, + "grad_norm": 0.9517342838468502, + "learning_rate": 1.961009029487108e-05, + "loss": 0.8847, + "step": 1302 + }, + { + "epoch": 0.11667133023672281, + "grad_norm": 1.268999077738142, + "learning_rate": 1.9609287911615743e-05, + "loss": 0.8826, + "step": 1303 + }, + { + "epoch": 0.11676087078180089, + "grad_norm": 1.0774037052649448, + "learning_rate": 1.9608484720058416e-05, + "loss": 0.9087, + "step": 1304 + }, + { + "epoch": 0.11685041132687896, + "grad_norm": 0.917636695883539, + "learning_rate": 1.9607680720266664e-05, + "loss": 0.9503, + "step": 1305 + }, + { + "epoch": 0.11693995187195702, + "grad_norm": 1.0041451981443772, + "learning_rate": 1.960687591230812e-05, + "loss": 0.9535, + "step": 1306 + }, + { + "epoch": 0.11702949241703509, + "grad_norm": 1.178052741132566, + "learning_rate": 1.9606070296250485e-05, + "loss": 0.9291, + "step": 1307 + }, + { + "epoch": 0.11711903296211315, + "grad_norm": 1.1387933577252016, + "learning_rate": 1.9605263872161513e-05, + "loss": 0.8966, + "step": 1308 + }, + { + "epoch": 0.11720857350719123, + "grad_norm": 0.9580981245675096, + "learning_rate": 1.9604456640109047e-05, + "loss": 0.8317, + "step": 1309 + }, + { + "epoch": 0.1172981140522693, + "grad_norm": 1.0492772508419754, + "learning_rate": 1.9603648600160988e-05, + "loss": 0.9076, + "step": 1310 + }, + { + "epoch": 0.11738765459734736, + "grad_norm": 0.9685112528271055, + "learning_rate": 1.96028397523853e-05, + "loss": 0.8614, + "step": 1311 + }, + { + "epoch": 0.11747719514242543, + "grad_norm": 0.9979387068071756, + "learning_rate": 1.960203009685003e-05, + "loss": 0.929, + "step": 1312 + }, + { + "epoch": 0.1175667356875035, + "grad_norm": 1.0871400666474973, + "learning_rate": 1.9601219633623277e-05, + "loss": 0.9635, + "step": 1313 + }, + { + "epoch": 0.11765627623258157, + "grad_norm": 0.9707767008056238, + "learning_rate": 1.9600408362773215e-05, + "loss": 0.8943, + "step": 1314 + }, + { + "epoch": 0.11774581677765963, + "grad_norm": 1.029009711331632, + "learning_rate": 1.9599596284368087e-05, + "loss": 0.9128, + "step": 1315 + }, + { + "epoch": 0.1178353573227377, + "grad_norm": 1.0253709226875778, + "learning_rate": 1.95987833984762e-05, + "loss": 0.8756, + "step": 1316 + }, + { + "epoch": 0.11792489786781576, + "grad_norm": 1.0468990731319678, + "learning_rate": 1.9597969705165936e-05, + "loss": 0.9011, + "step": 1317 + }, + { + "epoch": 0.11801443841289384, + "grad_norm": 0.9523541487052847, + "learning_rate": 1.9597155204505737e-05, + "loss": 0.8866, + "step": 1318 + }, + { + "epoch": 0.11810397895797191, + "grad_norm": 1.0977667673280584, + "learning_rate": 1.9596339896564114e-05, + "loss": 0.8663, + "step": 1319 + }, + { + "epoch": 0.11819351950304997, + "grad_norm": 0.9868904828494608, + "learning_rate": 1.9595523781409654e-05, + "loss": 0.8761, + "step": 1320 + }, + { + "epoch": 0.11828306004812804, + "grad_norm": 1.1474701193617396, + "learning_rate": 1.9594706859110997e-05, + "loss": 0.9371, + "step": 1321 + }, + { + "epoch": 0.11837260059320612, + "grad_norm": 0.997464603543136, + "learning_rate": 1.959388912973687e-05, + "loss": 0.9388, + "step": 1322 + }, + { + "epoch": 0.11846214113828418, + "grad_norm": 0.9898154160231575, + "learning_rate": 1.959307059335605e-05, + "loss": 0.9189, + "step": 1323 + }, + { + "epoch": 0.11855168168336225, + "grad_norm": 1.1182368383827372, + "learning_rate": 1.9592251250037395e-05, + "loss": 0.9144, + "step": 1324 + }, + { + "epoch": 0.11864122222844031, + "grad_norm": 1.0422720169200772, + "learning_rate": 1.959143109984982e-05, + "loss": 0.9105, + "step": 1325 + }, + { + "epoch": 0.11873076277351838, + "grad_norm": 1.0456592228955999, + "learning_rate": 1.9590610142862324e-05, + "loss": 0.9929, + "step": 1326 + }, + { + "epoch": 0.11882030331859646, + "grad_norm": 1.0598323873598947, + "learning_rate": 1.9589788379143952e-05, + "loss": 0.8422, + "step": 1327 + }, + { + "epoch": 0.11890984386367452, + "grad_norm": 0.980231010678184, + "learning_rate": 1.958896580876383e-05, + "loss": 0.9093, + "step": 1328 + }, + { + "epoch": 0.11899938440875259, + "grad_norm": 1.164696223390671, + "learning_rate": 1.958814243179115e-05, + "loss": 0.9115, + "step": 1329 + }, + { + "epoch": 0.11908892495383065, + "grad_norm": 1.0256176481410755, + "learning_rate": 1.9587318248295176e-05, + "loss": 0.9427, + "step": 1330 + }, + { + "epoch": 0.11917846549890873, + "grad_norm": 1.1037358444667853, + "learning_rate": 1.9586493258345232e-05, + "loss": 0.8661, + "step": 1331 + }, + { + "epoch": 0.1192680060439868, + "grad_norm": 1.0967941877583305, + "learning_rate": 1.9585667462010717e-05, + "loss": 0.9429, + "step": 1332 + }, + { + "epoch": 0.11935754658906486, + "grad_norm": 1.0338266025151217, + "learning_rate": 1.9584840859361094e-05, + "loss": 0.902, + "step": 1333 + }, + { + "epoch": 0.11944708713414293, + "grad_norm": 0.9354979339617655, + "learning_rate": 1.9584013450465887e-05, + "loss": 0.916, + "step": 1334 + }, + { + "epoch": 0.11953662767922099, + "grad_norm": 0.9315103323360198, + "learning_rate": 1.9583185235394703e-05, + "loss": 0.9199, + "step": 1335 + }, + { + "epoch": 0.11962616822429907, + "grad_norm": 1.2879183953016171, + "learning_rate": 1.9582356214217204e-05, + "loss": 0.8869, + "step": 1336 + }, + { + "epoch": 0.11971570876937714, + "grad_norm": 0.9695556840439387, + "learning_rate": 1.9581526387003126e-05, + "loss": 0.8468, + "step": 1337 + }, + { + "epoch": 0.1198052493144552, + "grad_norm": 1.0231523228703185, + "learning_rate": 1.9580695753822274e-05, + "loss": 0.9181, + "step": 1338 + }, + { + "epoch": 0.11989478985953327, + "grad_norm": 1.1355268343581768, + "learning_rate": 1.9579864314744514e-05, + "loss": 0.8865, + "step": 1339 + }, + { + "epoch": 0.11998433040461134, + "grad_norm": 0.912833529452868, + "learning_rate": 1.9579032069839785e-05, + "loss": 0.9134, + "step": 1340 + }, + { + "epoch": 0.12007387094968941, + "grad_norm": 1.4615830579029223, + "learning_rate": 1.9578199019178095e-05, + "loss": 0.9369, + "step": 1341 + }, + { + "epoch": 0.12016341149476747, + "grad_norm": 1.040844642944266, + "learning_rate": 1.957736516282952e-05, + "loss": 0.8588, + "step": 1342 + }, + { + "epoch": 0.12025295203984554, + "grad_norm": 1.105762657959043, + "learning_rate": 1.9576530500864192e-05, + "loss": 0.8451, + "step": 1343 + }, + { + "epoch": 0.1203424925849236, + "grad_norm": 1.0083957740387428, + "learning_rate": 1.9575695033352325e-05, + "loss": 0.8598, + "step": 1344 + }, + { + "epoch": 0.12043203313000168, + "grad_norm": 0.9735755367126849, + "learning_rate": 1.9574858760364197e-05, + "loss": 0.8555, + "step": 1345 + }, + { + "epoch": 0.12052157367507975, + "grad_norm": 0.9619789573848628, + "learning_rate": 1.9574021681970153e-05, + "loss": 0.8936, + "step": 1346 + }, + { + "epoch": 0.12061111422015781, + "grad_norm": 1.0684423416476119, + "learning_rate": 1.95731837982406e-05, + "loss": 0.8959, + "step": 1347 + }, + { + "epoch": 0.12070065476523588, + "grad_norm": 1.2905960845220332, + "learning_rate": 1.957234510924603e-05, + "loss": 0.9335, + "step": 1348 + }, + { + "epoch": 0.12079019531031396, + "grad_norm": 1.070410605663533, + "learning_rate": 1.9571505615056977e-05, + "loss": 0.912, + "step": 1349 + }, + { + "epoch": 0.12087973585539202, + "grad_norm": 1.3565165539778345, + "learning_rate": 1.957066531574406e-05, + "loss": 0.9237, + "step": 1350 + }, + { + "epoch": 0.12096927640047009, + "grad_norm": 1.081582842643077, + "learning_rate": 1.9569824211377972e-05, + "loss": 0.9423, + "step": 1351 + }, + { + "epoch": 0.12105881694554815, + "grad_norm": 0.942909315005756, + "learning_rate": 1.956898230202945e-05, + "loss": 0.961, + "step": 1352 + }, + { + "epoch": 0.12114835749062622, + "grad_norm": 0.9762582587043057, + "learning_rate": 1.9568139587769325e-05, + "loss": 0.9822, + "step": 1353 + }, + { + "epoch": 0.1212378980357043, + "grad_norm": 1.1937028301107047, + "learning_rate": 1.9567296068668474e-05, + "loss": 0.8534, + "step": 1354 + }, + { + "epoch": 0.12132743858078236, + "grad_norm": 0.9728571119574848, + "learning_rate": 1.9566451744797855e-05, + "loss": 0.9113, + "step": 1355 + }, + { + "epoch": 0.12141697912586043, + "grad_norm": 1.0412336952219956, + "learning_rate": 1.956560661622849e-05, + "loss": 0.8391, + "step": 1356 + }, + { + "epoch": 0.12150651967093849, + "grad_norm": 1.0081667447099796, + "learning_rate": 1.9564760683031468e-05, + "loss": 0.8843, + "step": 1357 + }, + { + "epoch": 0.12159606021601657, + "grad_norm": 1.0776103925833755, + "learning_rate": 1.9563913945277947e-05, + "loss": 0.9138, + "step": 1358 + }, + { + "epoch": 0.12168560076109464, + "grad_norm": 0.9802067978216537, + "learning_rate": 1.9563066403039147e-05, + "loss": 0.9422, + "step": 1359 + }, + { + "epoch": 0.1217751413061727, + "grad_norm": 1.0721933551598724, + "learning_rate": 1.9562218056386366e-05, + "loss": 0.915, + "step": 1360 + }, + { + "epoch": 0.12186468185125077, + "grad_norm": 3.6529779386806465, + "learning_rate": 1.9561368905390964e-05, + "loss": 0.9146, + "step": 1361 + }, + { + "epoch": 0.12195422239632883, + "grad_norm": 1.0660970137140113, + "learning_rate": 1.9560518950124368e-05, + "loss": 0.9248, + "step": 1362 + }, + { + "epoch": 0.12204376294140691, + "grad_norm": 1.014861806715312, + "learning_rate": 1.955966819065807e-05, + "loss": 0.9326, + "step": 1363 + }, + { + "epoch": 0.12213330348648498, + "grad_norm": 1.0998755985273443, + "learning_rate": 1.9558816627063638e-05, + "loss": 0.9175, + "step": 1364 + }, + { + "epoch": 0.12222284403156304, + "grad_norm": 1.058809204649994, + "learning_rate": 1.9557964259412703e-05, + "loss": 0.8788, + "step": 1365 + }, + { + "epoch": 0.1223123845766411, + "grad_norm": 0.9609168163702838, + "learning_rate": 1.955711108777696e-05, + "loss": 0.8697, + "step": 1366 + }, + { + "epoch": 0.12240192512171919, + "grad_norm": 1.1223672412545525, + "learning_rate": 1.9556257112228173e-05, + "loss": 0.8563, + "step": 1367 + }, + { + "epoch": 0.12249146566679725, + "grad_norm": 0.9801982052958138, + "learning_rate": 1.955540233283818e-05, + "loss": 0.9284, + "step": 1368 + }, + { + "epoch": 0.12258100621187532, + "grad_norm": 0.8696421486641737, + "learning_rate": 1.955454674967888e-05, + "loss": 0.8915, + "step": 1369 + }, + { + "epoch": 0.12267054675695338, + "grad_norm": 1.1238639911121264, + "learning_rate": 1.9553690362822245e-05, + "loss": 0.8764, + "step": 1370 + }, + { + "epoch": 0.12276008730203145, + "grad_norm": 1.0568310077230139, + "learning_rate": 1.955283317234031e-05, + "loss": 0.8866, + "step": 1371 + }, + { + "epoch": 0.12284962784710952, + "grad_norm": 1.0167342829540726, + "learning_rate": 1.9551975178305172e-05, + "loss": 0.9173, + "step": 1372 + }, + { + "epoch": 0.12293916839218759, + "grad_norm": 1.2826334745425008, + "learning_rate": 1.9551116380789015e-05, + "loss": 0.89, + "step": 1373 + }, + { + "epoch": 0.12302870893726565, + "grad_norm": 1.2400165128867031, + "learning_rate": 1.9550256779864073e-05, + "loss": 0.8928, + "step": 1374 + }, + { + "epoch": 0.12311824948234372, + "grad_norm": 1.0205867079465514, + "learning_rate": 1.954939637560265e-05, + "loss": 0.9495, + "step": 1375 + }, + { + "epoch": 0.1232077900274218, + "grad_norm": 1.0033611091567889, + "learning_rate": 1.9548535168077124e-05, + "loss": 0.9175, + "step": 1376 + }, + { + "epoch": 0.12329733057249986, + "grad_norm": 1.001156894696269, + "learning_rate": 1.9547673157359933e-05, + "loss": 0.9021, + "step": 1377 + }, + { + "epoch": 0.12338687111757793, + "grad_norm": 0.9831636288095823, + "learning_rate": 1.954681034352359e-05, + "loss": 0.8808, + "step": 1378 + }, + { + "epoch": 0.123476411662656, + "grad_norm": 1.1729743070737861, + "learning_rate": 1.9545946726640673e-05, + "loss": 0.9301, + "step": 1379 + }, + { + "epoch": 0.12356595220773406, + "grad_norm": 1.0761998970688234, + "learning_rate": 1.954508230678382e-05, + "loss": 0.872, + "step": 1380 + }, + { + "epoch": 0.12365549275281214, + "grad_norm": 1.0859356517130991, + "learning_rate": 1.9544217084025755e-05, + "loss": 0.932, + "step": 1381 + }, + { + "epoch": 0.1237450332978902, + "grad_norm": 0.9370717100137363, + "learning_rate": 1.9543351058439245e-05, + "loss": 0.9105, + "step": 1382 + }, + { + "epoch": 0.12383457384296827, + "grad_norm": 0.9773938441864269, + "learning_rate": 1.9542484230097145e-05, + "loss": 0.9565, + "step": 1383 + }, + { + "epoch": 0.12392411438804633, + "grad_norm": 0.9875338546039725, + "learning_rate": 1.954161659907237e-05, + "loss": 0.9357, + "step": 1384 + }, + { + "epoch": 0.12401365493312441, + "grad_norm": 1.1173362097876427, + "learning_rate": 1.9540748165437897e-05, + "loss": 0.8907, + "step": 1385 + }, + { + "epoch": 0.12410319547820248, + "grad_norm": 1.1458961068103404, + "learning_rate": 1.9539878929266777e-05, + "loss": 0.9128, + "step": 1386 + }, + { + "epoch": 0.12419273602328054, + "grad_norm": 1.0168128724233172, + "learning_rate": 1.953900889063213e-05, + "loss": 0.8657, + "step": 1387 + }, + { + "epoch": 0.12428227656835861, + "grad_norm": 1.1026914557965029, + "learning_rate": 1.9538138049607144e-05, + "loss": 0.9586, + "step": 1388 + }, + { + "epoch": 0.12437181711343667, + "grad_norm": 1.0329069955871129, + "learning_rate": 1.9537266406265062e-05, + "loss": 0.9554, + "step": 1389 + }, + { + "epoch": 0.12446135765851475, + "grad_norm": 0.9926753658126571, + "learning_rate": 1.953639396067921e-05, + "loss": 0.9469, + "step": 1390 + }, + { + "epoch": 0.12455089820359282, + "grad_norm": 1.0645791773515578, + "learning_rate": 1.953552071292298e-05, + "loss": 0.8637, + "step": 1391 + }, + { + "epoch": 0.12464043874867088, + "grad_norm": 0.9658738677847174, + "learning_rate": 1.9534646663069816e-05, + "loss": 0.8595, + "step": 1392 + }, + { + "epoch": 0.12472997929374895, + "grad_norm": 1.0925703672691132, + "learning_rate": 1.953377181119325e-05, + "loss": 0.9256, + "step": 1393 + }, + { + "epoch": 0.12481951983882703, + "grad_norm": 1.1074894473625458, + "learning_rate": 1.953289615736686e-05, + "loss": 0.989, + "step": 1394 + }, + { + "epoch": 0.12490906038390509, + "grad_norm": 1.1368889039931307, + "learning_rate": 1.9532019701664313e-05, + "loss": 0.8866, + "step": 1395 + }, + { + "epoch": 0.12499860092898316, + "grad_norm": 1.0068562492262372, + "learning_rate": 1.9531142444159332e-05, + "loss": 0.8895, + "step": 1396 + }, + { + "epoch": 0.12508814147406122, + "grad_norm": 0.940322014456406, + "learning_rate": 1.9530264384925707e-05, + "loss": 0.8959, + "step": 1397 + }, + { + "epoch": 0.12517768201913929, + "grad_norm": 1.1503138338272139, + "learning_rate": 1.9529385524037298e-05, + "loss": 0.9052, + "step": 1398 + }, + { + "epoch": 0.12526722256421735, + "grad_norm": 1.0431312140629057, + "learning_rate": 1.952850586156803e-05, + "loss": 0.9529, + "step": 1399 + }, + { + "epoch": 0.12535676310929542, + "grad_norm": 1.1144455328212037, + "learning_rate": 1.9527625397591903e-05, + "loss": 0.9728, + "step": 1400 + }, + { + "epoch": 0.1254463036543735, + "grad_norm": 1.0079998690513767, + "learning_rate": 1.9526744132182975e-05, + "loss": 0.8823, + "step": 1401 + }, + { + "epoch": 0.12553584419945157, + "grad_norm": 0.9052617579464834, + "learning_rate": 1.9525862065415374e-05, + "loss": 0.9248, + "step": 1402 + }, + { + "epoch": 0.12562538474452964, + "grad_norm": 1.0468757009788687, + "learning_rate": 1.9524979197363298e-05, + "loss": 0.9499, + "step": 1403 + }, + { + "epoch": 0.1257149252896077, + "grad_norm": 1.2404775812989024, + "learning_rate": 1.9524095528101012e-05, + "loss": 0.907, + "step": 1404 + }, + { + "epoch": 0.12580446583468577, + "grad_norm": 1.1383673603748692, + "learning_rate": 1.9523211057702845e-05, + "loss": 0.9525, + "step": 1405 + }, + { + "epoch": 0.12589400637976383, + "grad_norm": 1.0176565772048503, + "learning_rate": 1.9522325786243198e-05, + "loss": 0.9264, + "step": 1406 + }, + { + "epoch": 0.1259835469248419, + "grad_norm": 0.9901489944462893, + "learning_rate": 1.9521439713796537e-05, + "loss": 0.9125, + "step": 1407 + }, + { + "epoch": 0.12607308746991996, + "grad_norm": 0.9662831001645319, + "learning_rate": 1.9520552840437396e-05, + "loss": 0.8835, + "step": 1408 + }, + { + "epoch": 0.12616262801499803, + "grad_norm": 1.0184823752753038, + "learning_rate": 1.951966516624037e-05, + "loss": 0.8911, + "step": 1409 + }, + { + "epoch": 0.12625216856007612, + "grad_norm": 0.9928569316203307, + "learning_rate": 1.9518776691280137e-05, + "loss": 0.9155, + "step": 1410 + }, + { + "epoch": 0.1263417091051542, + "grad_norm": 1.0746244904606723, + "learning_rate": 1.9517887415631426e-05, + "loss": 0.983, + "step": 1411 + }, + { + "epoch": 0.12643124965023225, + "grad_norm": 1.0825778456784905, + "learning_rate": 1.951699733936904e-05, + "loss": 0.8769, + "step": 1412 + }, + { + "epoch": 0.12652079019531032, + "grad_norm": 1.1072741663857915, + "learning_rate": 1.951610646256785e-05, + "loss": 0.9278, + "step": 1413 + }, + { + "epoch": 0.12661033074038838, + "grad_norm": 1.0622384816018422, + "learning_rate": 1.95152147853028e-05, + "loss": 0.898, + "step": 1414 + }, + { + "epoch": 0.12669987128546645, + "grad_norm": 1.0448712321114952, + "learning_rate": 1.9514322307648886e-05, + "loss": 0.9751, + "step": 1415 + }, + { + "epoch": 0.1267894118305445, + "grad_norm": 1.0428131779013292, + "learning_rate": 1.9513429029681184e-05, + "loss": 0.8597, + "step": 1416 + }, + { + "epoch": 0.12687895237562258, + "grad_norm": 0.9950711560265061, + "learning_rate": 1.951253495147483e-05, + "loss": 0.8856, + "step": 1417 + }, + { + "epoch": 0.12696849292070064, + "grad_norm": 0.982205498762089, + "learning_rate": 1.951164007310504e-05, + "loss": 0.9317, + "step": 1418 + }, + { + "epoch": 0.12705803346577874, + "grad_norm": 0.9758720834731823, + "learning_rate": 1.951074439464708e-05, + "loss": 0.88, + "step": 1419 + }, + { + "epoch": 0.1271475740108568, + "grad_norm": 0.9216274708561601, + "learning_rate": 1.9509847916176294e-05, + "loss": 0.9068, + "step": 1420 + }, + { + "epoch": 0.12723711455593487, + "grad_norm": 1.0548263490445868, + "learning_rate": 1.9508950637768093e-05, + "loss": 0.9412, + "step": 1421 + }, + { + "epoch": 0.12732665510101293, + "grad_norm": 0.9347688074901511, + "learning_rate": 1.950805255949795e-05, + "loss": 0.8875, + "step": 1422 + }, + { + "epoch": 0.127416195646091, + "grad_norm": 1.0193098894139327, + "learning_rate": 1.9507153681441408e-05, + "loss": 0.8538, + "step": 1423 + }, + { + "epoch": 0.12750573619116906, + "grad_norm": 1.09266989261539, + "learning_rate": 1.9506254003674084e-05, + "loss": 0.9565, + "step": 1424 + }, + { + "epoch": 0.12759527673624713, + "grad_norm": 0.953919130552437, + "learning_rate": 1.9505353526271646e-05, + "loss": 0.9209, + "step": 1425 + }, + { + "epoch": 0.1276848172813252, + "grad_norm": 1.0471619911738836, + "learning_rate": 1.9504452249309848e-05, + "loss": 0.8724, + "step": 1426 + }, + { + "epoch": 0.12777435782640326, + "grad_norm": 0.9677614920010378, + "learning_rate": 1.9503550172864497e-05, + "loss": 0.9344, + "step": 1427 + }, + { + "epoch": 0.12786389837148135, + "grad_norm": 1.0019501723097841, + "learning_rate": 1.9502647297011473e-05, + "loss": 0.9137, + "step": 1428 + }, + { + "epoch": 0.12795343891655941, + "grad_norm": 0.9721084506596254, + "learning_rate": 1.950174362182673e-05, + "loss": 0.8924, + "step": 1429 + }, + { + "epoch": 0.12804297946163748, + "grad_norm": 0.9689075518443421, + "learning_rate": 1.9500839147386275e-05, + "loss": 0.9036, + "step": 1430 + }, + { + "epoch": 0.12813252000671554, + "grad_norm": 0.9895744158611558, + "learning_rate": 1.9499933873766188e-05, + "loss": 0.8925, + "step": 1431 + }, + { + "epoch": 0.1282220605517936, + "grad_norm": 0.920255863937801, + "learning_rate": 1.9499027801042624e-05, + "loss": 0.8846, + "step": 1432 + }, + { + "epoch": 0.12831160109687167, + "grad_norm": 1.0509384374278654, + "learning_rate": 1.9498120929291797e-05, + "loss": 0.929, + "step": 1433 + }, + { + "epoch": 0.12840114164194974, + "grad_norm": 1.0193063834041702, + "learning_rate": 1.9497213258589983e-05, + "loss": 0.902, + "step": 1434 + }, + { + "epoch": 0.1284906821870278, + "grad_norm": 0.999295865258048, + "learning_rate": 1.9496304789013544e-05, + "loss": 0.9176, + "step": 1435 + }, + { + "epoch": 0.12858022273210587, + "grad_norm": 0.9971365977577392, + "learning_rate": 1.949539552063889e-05, + "loss": 0.8513, + "step": 1436 + }, + { + "epoch": 0.12866976327718396, + "grad_norm": 0.9684297453249247, + "learning_rate": 1.9494485453542508e-05, + "loss": 0.8508, + "step": 1437 + }, + { + "epoch": 0.12875930382226203, + "grad_norm": 0.9316713142048046, + "learning_rate": 1.949357458780095e-05, + "loss": 0.8609, + "step": 1438 + }, + { + "epoch": 0.1288488443673401, + "grad_norm": 0.9471396520544554, + "learning_rate": 1.9492662923490834e-05, + "loss": 0.8167, + "step": 1439 + }, + { + "epoch": 0.12893838491241816, + "grad_norm": 1.0408102054668609, + "learning_rate": 1.9491750460688845e-05, + "loss": 0.8962, + "step": 1440 + }, + { + "epoch": 0.12902792545749622, + "grad_norm": 0.9637514342113481, + "learning_rate": 1.949083719947174e-05, + "loss": 0.86, + "step": 1441 + }, + { + "epoch": 0.1291174660025743, + "grad_norm": 1.0275215280399723, + "learning_rate": 1.948992313991634e-05, + "loss": 0.9447, + "step": 1442 + }, + { + "epoch": 0.12920700654765235, + "grad_norm": 1.0616604776106664, + "learning_rate": 1.9489008282099523e-05, + "loss": 0.8897, + "step": 1443 + }, + { + "epoch": 0.12929654709273042, + "grad_norm": 1.0239220021055173, + "learning_rate": 1.9488092626098256e-05, + "loss": 0.8867, + "step": 1444 + }, + { + "epoch": 0.12938608763780848, + "grad_norm": 1.211101786405548, + "learning_rate": 1.9487176171989555e-05, + "loss": 0.912, + "step": 1445 + }, + { + "epoch": 0.12947562818288658, + "grad_norm": 1.0345748790552884, + "learning_rate": 1.948625891985051e-05, + "loss": 0.9375, + "step": 1446 + }, + { + "epoch": 0.12956516872796464, + "grad_norm": 1.0814639896029998, + "learning_rate": 1.948534086975828e-05, + "loss": 0.8756, + "step": 1447 + }, + { + "epoch": 0.1296547092730427, + "grad_norm": 1.0923445547440713, + "learning_rate": 1.9484422021790085e-05, + "loss": 0.9106, + "step": 1448 + }, + { + "epoch": 0.12974424981812077, + "grad_norm": 1.0503854170455027, + "learning_rate": 1.9483502376023217e-05, + "loss": 0.9183, + "step": 1449 + }, + { + "epoch": 0.12983379036319884, + "grad_norm": 0.9757969244328735, + "learning_rate": 1.9482581932535028e-05, + "loss": 0.8987, + "step": 1450 + }, + { + "epoch": 0.1299233309082769, + "grad_norm": 0.8523331483993133, + "learning_rate": 1.9481660691402956e-05, + "loss": 0.8727, + "step": 1451 + }, + { + "epoch": 0.13001287145335497, + "grad_norm": 0.9723063006219292, + "learning_rate": 1.948073865270448e-05, + "loss": 0.902, + "step": 1452 + }, + { + "epoch": 0.13010241199843303, + "grad_norm": 0.9851324298269891, + "learning_rate": 1.9479815816517163e-05, + "loss": 0.9167, + "step": 1453 + }, + { + "epoch": 0.1301919525435111, + "grad_norm": 0.9429330901331978, + "learning_rate": 1.947889218291863e-05, + "loss": 0.9174, + "step": 1454 + }, + { + "epoch": 0.1302814930885892, + "grad_norm": 1.042165108015757, + "learning_rate": 1.9477967751986576e-05, + "loss": 0.9068, + "step": 1455 + }, + { + "epoch": 0.13037103363366725, + "grad_norm": 1.0664973925487689, + "learning_rate": 1.9477042523798762e-05, + "loss": 0.95, + "step": 1456 + }, + { + "epoch": 0.13046057417874532, + "grad_norm": 1.0387430566533364, + "learning_rate": 1.9476116498433016e-05, + "loss": 0.9417, + "step": 1457 + }, + { + "epoch": 0.13055011472382338, + "grad_norm": 1.1152744512934578, + "learning_rate": 1.9475189675967226e-05, + "loss": 0.8765, + "step": 1458 + }, + { + "epoch": 0.13063965526890145, + "grad_norm": 1.0485207324014405, + "learning_rate": 1.9474262056479364e-05, + "loss": 0.9255, + "step": 1459 + }, + { + "epoch": 0.13072919581397952, + "grad_norm": 0.918454917245906, + "learning_rate": 1.9473333640047442e-05, + "loss": 0.9252, + "step": 1460 + }, + { + "epoch": 0.13081873635905758, + "grad_norm": 1.0407250514771502, + "learning_rate": 1.9472404426749572e-05, + "loss": 0.8931, + "step": 1461 + }, + { + "epoch": 0.13090827690413565, + "grad_norm": 0.9369344038027542, + "learning_rate": 1.9471474416663906e-05, + "loss": 0.8986, + "step": 1462 + }, + { + "epoch": 0.1309978174492137, + "grad_norm": 1.2269047348485984, + "learning_rate": 1.947054360986868e-05, + "loss": 0.9321, + "step": 1463 + }, + { + "epoch": 0.1310873579942918, + "grad_norm": 1.0219488757101256, + "learning_rate": 1.9469612006442184e-05, + "loss": 0.91, + "step": 1464 + }, + { + "epoch": 0.13117689853936987, + "grad_norm": 0.982429351361952, + "learning_rate": 1.9468679606462784e-05, + "loss": 0.9306, + "step": 1465 + }, + { + "epoch": 0.13126643908444793, + "grad_norm": 1.1181929588730766, + "learning_rate": 1.9467746410008916e-05, + "loss": 0.8895, + "step": 1466 + }, + { + "epoch": 0.131355979629526, + "grad_norm": 0.9858865418958391, + "learning_rate": 1.946681241715907e-05, + "loss": 0.898, + "step": 1467 + }, + { + "epoch": 0.13144552017460406, + "grad_norm": 1.0271586454792119, + "learning_rate": 1.9465877627991813e-05, + "loss": 0.9706, + "step": 1468 + }, + { + "epoch": 0.13153506071968213, + "grad_norm": 0.9952111706689362, + "learning_rate": 1.9464942042585776e-05, + "loss": 0.923, + "step": 1469 + }, + { + "epoch": 0.1316246012647602, + "grad_norm": 1.1117014468500008, + "learning_rate": 1.9464005661019656e-05, + "loss": 0.8851, + "step": 1470 + }, + { + "epoch": 0.13171414180983826, + "grad_norm": 1.0546826662691957, + "learning_rate": 1.9463068483372222e-05, + "loss": 0.9396, + "step": 1471 + }, + { + "epoch": 0.13180368235491632, + "grad_norm": 1.0473801423027123, + "learning_rate": 1.9462130509722307e-05, + "loss": 0.8828, + "step": 1472 + }, + { + "epoch": 0.13189322289999442, + "grad_norm": 1.0884043717294627, + "learning_rate": 1.9461191740148805e-05, + "loss": 0.8727, + "step": 1473 + }, + { + "epoch": 0.13198276344507248, + "grad_norm": 1.084270235299537, + "learning_rate": 1.9460252174730682e-05, + "loss": 0.926, + "step": 1474 + }, + { + "epoch": 0.13207230399015055, + "grad_norm": 0.9634262768410355, + "learning_rate": 1.945931181354698e-05, + "loss": 0.9041, + "step": 1475 + }, + { + "epoch": 0.1321618445352286, + "grad_norm": 1.9828797268357217, + "learning_rate": 1.945837065667679e-05, + "loss": 0.9037, + "step": 1476 + }, + { + "epoch": 0.13225138508030668, + "grad_norm": 1.0758670212932726, + "learning_rate": 1.9457428704199283e-05, + "loss": 0.931, + "step": 1477 + }, + { + "epoch": 0.13234092562538474, + "grad_norm": 1.0160275806626584, + "learning_rate": 1.9456485956193693e-05, + "loss": 0.9077, + "step": 1478 + }, + { + "epoch": 0.1324304661704628, + "grad_norm": 0.9700076012393773, + "learning_rate": 1.945554241273932e-05, + "loss": 0.9021, + "step": 1479 + }, + { + "epoch": 0.13252000671554087, + "grad_norm": 0.9927651797145578, + "learning_rate": 1.9454598073915534e-05, + "loss": 0.8443, + "step": 1480 + }, + { + "epoch": 0.13260954726061894, + "grad_norm": 1.0915633602469332, + "learning_rate": 1.9453652939801766e-05, + "loss": 0.8678, + "step": 1481 + }, + { + "epoch": 0.13269908780569703, + "grad_norm": 1.0347345850308496, + "learning_rate": 1.945270701047752e-05, + "loss": 0.964, + "step": 1482 + }, + { + "epoch": 0.1327886283507751, + "grad_norm": 1.0275382379088425, + "learning_rate": 1.945176028602236e-05, + "loss": 0.902, + "step": 1483 + }, + { + "epoch": 0.13287816889585316, + "grad_norm": 0.9694285280511057, + "learning_rate": 1.945081276651593e-05, + "loss": 0.9423, + "step": 1484 + }, + { + "epoch": 0.13296770944093123, + "grad_norm": 0.9397546016874349, + "learning_rate": 1.9449864452037926e-05, + "loss": 0.9141, + "step": 1485 + }, + { + "epoch": 0.1330572499860093, + "grad_norm": 0.9760908531669296, + "learning_rate": 1.9448915342668118e-05, + "loss": 0.8978, + "step": 1486 + }, + { + "epoch": 0.13314679053108736, + "grad_norm": 1.2270016597732376, + "learning_rate": 1.9447965438486343e-05, + "loss": 0.8957, + "step": 1487 + }, + { + "epoch": 0.13323633107616542, + "grad_norm": 1.0279238363884968, + "learning_rate": 1.9447014739572503e-05, + "loss": 0.953, + "step": 1488 + }, + { + "epoch": 0.13332587162124349, + "grad_norm": 1.011348740484823, + "learning_rate": 1.944606324600657e-05, + "loss": 0.8799, + "step": 1489 + }, + { + "epoch": 0.13341541216632155, + "grad_norm": 1.0785657113335414, + "learning_rate": 1.9445110957868576e-05, + "loss": 0.8869, + "step": 1490 + }, + { + "epoch": 0.13350495271139964, + "grad_norm": 1.092623790544124, + "learning_rate": 1.9444157875238628e-05, + "loss": 0.9208, + "step": 1491 + }, + { + "epoch": 0.1335944932564777, + "grad_norm": 1.0083250738153173, + "learning_rate": 1.9443203998196895e-05, + "loss": 0.9502, + "step": 1492 + }, + { + "epoch": 0.13368403380155577, + "grad_norm": 1.0534469587509614, + "learning_rate": 1.9442249326823613e-05, + "loss": 0.9315, + "step": 1493 + }, + { + "epoch": 0.13377357434663384, + "grad_norm": 0.8623868913924277, + "learning_rate": 1.944129386119909e-05, + "loss": 0.8555, + "step": 1494 + }, + { + "epoch": 0.1338631148917119, + "grad_norm": 1.0743877080394968, + "learning_rate": 1.9440337601403695e-05, + "loss": 0.8852, + "step": 1495 + }, + { + "epoch": 0.13395265543678997, + "grad_norm": 1.086542869961554, + "learning_rate": 1.943938054751786e-05, + "loss": 0.9165, + "step": 1496 + }, + { + "epoch": 0.13404219598186803, + "grad_norm": 0.9654041398149188, + "learning_rate": 1.9438422699622096e-05, + "loss": 0.9048, + "step": 1497 + }, + { + "epoch": 0.1341317365269461, + "grad_norm": 1.0769297040831751, + "learning_rate": 1.943746405779697e-05, + "loss": 0.9125, + "step": 1498 + }, + { + "epoch": 0.13422127707202416, + "grad_norm": 0.8987234635955466, + "learning_rate": 1.943650462212312e-05, + "loss": 0.9021, + "step": 1499 + }, + { + "epoch": 0.13431081761710226, + "grad_norm": 0.9997745296951533, + "learning_rate": 1.9435544392681257e-05, + "loss": 0.9669, + "step": 1500 + }, + { + "epoch": 0.13440035816218032, + "grad_norm": 0.9589663355029894, + "learning_rate": 1.9434583369552146e-05, + "loss": 0.9197, + "step": 1501 + }, + { + "epoch": 0.1344898987072584, + "grad_norm": 0.9612325544024343, + "learning_rate": 1.9433621552816623e-05, + "loss": 0.8853, + "step": 1502 + }, + { + "epoch": 0.13457943925233645, + "grad_norm": 0.979263392994081, + "learning_rate": 1.9432658942555597e-05, + "loss": 0.9618, + "step": 1503 + }, + { + "epoch": 0.13466897979741452, + "grad_norm": 1.363251020659175, + "learning_rate": 1.943169553885004e-05, + "loss": 0.9072, + "step": 1504 + }, + { + "epoch": 0.13475852034249258, + "grad_norm": 0.9979329837967914, + "learning_rate": 1.943073134178099e-05, + "loss": 0.9248, + "step": 1505 + }, + { + "epoch": 0.13484806088757065, + "grad_norm": 0.9559618222497475, + "learning_rate": 1.9429766351429554e-05, + "loss": 0.8848, + "step": 1506 + }, + { + "epoch": 0.1349376014326487, + "grad_norm": 1.1167959431368581, + "learning_rate": 1.9428800567876898e-05, + "loss": 0.8352, + "step": 1507 + }, + { + "epoch": 0.13502714197772678, + "grad_norm": 0.978643743219982, + "learning_rate": 1.9427833991204264e-05, + "loss": 0.9145, + "step": 1508 + }, + { + "epoch": 0.13511668252280487, + "grad_norm": 0.9612792399454821, + "learning_rate": 1.9426866621492958e-05, + "loss": 0.9054, + "step": 1509 + }, + { + "epoch": 0.13520622306788294, + "grad_norm": 0.9326269527761527, + "learning_rate": 1.9425898458824352e-05, + "loss": 0.8592, + "step": 1510 + }, + { + "epoch": 0.135295763612961, + "grad_norm": 1.1163662805630303, + "learning_rate": 1.9424929503279883e-05, + "loss": 0.9027, + "step": 1511 + }, + { + "epoch": 0.13538530415803907, + "grad_norm": 0.961668852243405, + "learning_rate": 1.9423959754941055e-05, + "loss": 0.8605, + "step": 1512 + }, + { + "epoch": 0.13547484470311713, + "grad_norm": 1.0053554854834659, + "learning_rate": 1.9422989213889446e-05, + "loss": 0.8904, + "step": 1513 + }, + { + "epoch": 0.1355643852481952, + "grad_norm": 1.298556905990335, + "learning_rate": 1.9422017880206686e-05, + "loss": 0.8567, + "step": 1514 + }, + { + "epoch": 0.13565392579327326, + "grad_norm": 1.0926006421905428, + "learning_rate": 1.942104575397449e-05, + "loss": 0.9233, + "step": 1515 + }, + { + "epoch": 0.13574346633835133, + "grad_norm": 1.0868330635087227, + "learning_rate": 1.9420072835274623e-05, + "loss": 0.8515, + "step": 1516 + }, + { + "epoch": 0.1358330068834294, + "grad_norm": 1.0867937686581675, + "learning_rate": 1.941909912418893e-05, + "loss": 0.8212, + "step": 1517 + }, + { + "epoch": 0.13592254742850748, + "grad_norm": 0.9451992243311593, + "learning_rate": 1.941812462079931e-05, + "loss": 0.8571, + "step": 1518 + }, + { + "epoch": 0.13601208797358555, + "grad_norm": 0.9987910849183542, + "learning_rate": 1.9417149325187737e-05, + "loss": 0.9381, + "step": 1519 + }, + { + "epoch": 0.13610162851866361, + "grad_norm": 1.0320960529311347, + "learning_rate": 1.9416173237436252e-05, + "loss": 0.937, + "step": 1520 + }, + { + "epoch": 0.13619116906374168, + "grad_norm": 0.9321398916032981, + "learning_rate": 1.941519635762696e-05, + "loss": 0.9431, + "step": 1521 + }, + { + "epoch": 0.13628070960881974, + "grad_norm": 0.9727937328557554, + "learning_rate": 1.941421868584203e-05, + "loss": 0.9432, + "step": 1522 + }, + { + "epoch": 0.1363702501538978, + "grad_norm": 1.021323779000358, + "learning_rate": 1.94132402221637e-05, + "loss": 0.9389, + "step": 1523 + }, + { + "epoch": 0.13645979069897587, + "grad_norm": 1.101850070063544, + "learning_rate": 1.9412260966674282e-05, + "loss": 0.8924, + "step": 1524 + }, + { + "epoch": 0.13654933124405394, + "grad_norm": 1.0080311600151963, + "learning_rate": 1.9411280919456138e-05, + "loss": 0.9171, + "step": 1525 + }, + { + "epoch": 0.136638871789132, + "grad_norm": 0.9274133464499409, + "learning_rate": 1.941030008059172e-05, + "loss": 0.9201, + "step": 1526 + }, + { + "epoch": 0.1367284123342101, + "grad_norm": 0.948262034092094, + "learning_rate": 1.9409318450163517e-05, + "loss": 0.9076, + "step": 1527 + }, + { + "epoch": 0.13681795287928816, + "grad_norm": 0.9645324280251374, + "learning_rate": 1.9408336028254112e-05, + "loss": 0.928, + "step": 1528 + }, + { + "epoch": 0.13690749342436623, + "grad_norm": 0.8925693454397264, + "learning_rate": 1.9407352814946135e-05, + "loss": 0.8593, + "step": 1529 + }, + { + "epoch": 0.1369970339694443, + "grad_norm": 1.029891293607414, + "learning_rate": 1.94063688103223e-05, + "loss": 0.861, + "step": 1530 + }, + { + "epoch": 0.13708657451452236, + "grad_norm": 0.9824803984408358, + "learning_rate": 1.9405384014465373e-05, + "loss": 0.8912, + "step": 1531 + }, + { + "epoch": 0.13717611505960042, + "grad_norm": 1.0356839904104131, + "learning_rate": 1.9404398427458187e-05, + "loss": 0.816, + "step": 1532 + }, + { + "epoch": 0.1372656556046785, + "grad_norm": 0.9566100266281806, + "learning_rate": 1.9403412049383658e-05, + "loss": 0.8613, + "step": 1533 + }, + { + "epoch": 0.13735519614975655, + "grad_norm": 1.0029574257539415, + "learning_rate": 1.9402424880324745e-05, + "loss": 0.8475, + "step": 1534 + }, + { + "epoch": 0.13744473669483462, + "grad_norm": 1.2308159477896594, + "learning_rate": 1.940143692036449e-05, + "loss": 0.9555, + "step": 1535 + }, + { + "epoch": 0.1375342772399127, + "grad_norm": 1.0559521304390151, + "learning_rate": 1.9400448169586004e-05, + "loss": 0.9003, + "step": 1536 + }, + { + "epoch": 0.13762381778499078, + "grad_norm": 1.036587298614136, + "learning_rate": 1.9399458628072448e-05, + "loss": 0.9092, + "step": 1537 + }, + { + "epoch": 0.13771335833006884, + "grad_norm": 0.955024888380107, + "learning_rate": 1.939846829590706e-05, + "loss": 0.8447, + "step": 1538 + }, + { + "epoch": 0.1378028988751469, + "grad_norm": 1.1413416664229863, + "learning_rate": 1.9397477173173147e-05, + "loss": 0.828, + "step": 1539 + }, + { + "epoch": 0.13789243942022497, + "grad_norm": 0.9241568895247805, + "learning_rate": 1.9396485259954078e-05, + "loss": 0.8859, + "step": 1540 + }, + { + "epoch": 0.13798197996530304, + "grad_norm": 0.944342542022803, + "learning_rate": 1.9395492556333292e-05, + "loss": 0.818, + "step": 1541 + }, + { + "epoch": 0.1380715205103811, + "grad_norm": 0.9973154382109269, + "learning_rate": 1.9394499062394286e-05, + "loss": 0.9294, + "step": 1542 + }, + { + "epoch": 0.13816106105545917, + "grad_norm": 1.2433425100122892, + "learning_rate": 1.9393504778220635e-05, + "loss": 0.9763, + "step": 1543 + }, + { + "epoch": 0.13825060160053723, + "grad_norm": 0.9701117005029266, + "learning_rate": 1.9392509703895972e-05, + "loss": 0.9085, + "step": 1544 + }, + { + "epoch": 0.13834014214561532, + "grad_norm": 0.9997288267167611, + "learning_rate": 1.9391513839503998e-05, + "loss": 0.8332, + "step": 1545 + }, + { + "epoch": 0.1384296826906934, + "grad_norm": 1.0245934642596468, + "learning_rate": 1.9390517185128487e-05, + "loss": 0.8924, + "step": 1546 + }, + { + "epoch": 0.13851922323577145, + "grad_norm": 0.9556787713400058, + "learning_rate": 1.9389519740853268e-05, + "loss": 0.8947, + "step": 1547 + }, + { + "epoch": 0.13860876378084952, + "grad_norm": 0.9222217238737335, + "learning_rate": 1.9388521506762248e-05, + "loss": 0.9183, + "step": 1548 + }, + { + "epoch": 0.13869830432592758, + "grad_norm": 0.8465551370127095, + "learning_rate": 1.9387522482939393e-05, + "loss": 0.8105, + "step": 1549 + }, + { + "epoch": 0.13878784487100565, + "grad_norm": 0.9720122169627724, + "learning_rate": 1.9386522669468738e-05, + "loss": 0.8891, + "step": 1550 + }, + { + "epoch": 0.13887738541608372, + "grad_norm": 1.016018093699156, + "learning_rate": 1.9385522066434386e-05, + "loss": 0.9012, + "step": 1551 + }, + { + "epoch": 0.13896692596116178, + "grad_norm": 0.9945374041768229, + "learning_rate": 1.9384520673920502e-05, + "loss": 0.8822, + "step": 1552 + }, + { + "epoch": 0.13905646650623985, + "grad_norm": 1.0344474643228478, + "learning_rate": 1.9383518492011316e-05, + "loss": 0.9141, + "step": 1553 + }, + { + "epoch": 0.13914600705131794, + "grad_norm": 1.0593081677283829, + "learning_rate": 1.9382515520791137e-05, + "loss": 0.8734, + "step": 1554 + }, + { + "epoch": 0.139235547596396, + "grad_norm": 0.8936251075463839, + "learning_rate": 1.9381511760344323e-05, + "loss": 0.9138, + "step": 1555 + }, + { + "epoch": 0.13932508814147407, + "grad_norm": 1.0302397511557242, + "learning_rate": 1.9380507210755314e-05, + "loss": 0.8864, + "step": 1556 + }, + { + "epoch": 0.13941462868655213, + "grad_norm": 0.9713819991914739, + "learning_rate": 1.9379501872108608e-05, + "loss": 0.8549, + "step": 1557 + }, + { + "epoch": 0.1395041692316302, + "grad_norm": 1.2490431897457857, + "learning_rate": 1.937849574448877e-05, + "loss": 0.8783, + "step": 1558 + }, + { + "epoch": 0.13959370977670826, + "grad_norm": 0.9854464394177337, + "learning_rate": 1.9377488827980428e-05, + "loss": 0.942, + "step": 1559 + }, + { + "epoch": 0.13968325032178633, + "grad_norm": 1.0171704098643424, + "learning_rate": 1.937648112266829e-05, + "loss": 0.8679, + "step": 1560 + }, + { + "epoch": 0.1397727908668644, + "grad_norm": 1.0275669360245716, + "learning_rate": 1.9375472628637107e-05, + "loss": 0.9118, + "step": 1561 + }, + { + "epoch": 0.13986233141194246, + "grad_norm": 1.0690846120342186, + "learning_rate": 1.9374463345971723e-05, + "loss": 0.9674, + "step": 1562 + }, + { + "epoch": 0.13995187195702055, + "grad_norm": 0.9874260358139031, + "learning_rate": 1.9373453274757032e-05, + "loss": 0.8597, + "step": 1563 + }, + { + "epoch": 0.14004141250209862, + "grad_norm": 1.260386220711374, + "learning_rate": 1.9372442415077995e-05, + "loss": 0.908, + "step": 1564 + }, + { + "epoch": 0.14013095304717668, + "grad_norm": 1.0933525690089914, + "learning_rate": 1.9371430767019644e-05, + "loss": 0.892, + "step": 1565 + }, + { + "epoch": 0.14022049359225475, + "grad_norm": 0.9588774858687872, + "learning_rate": 1.9370418330667076e-05, + "loss": 0.9241, + "step": 1566 + }, + { + "epoch": 0.1403100341373328, + "grad_norm": 0.9626222986840648, + "learning_rate": 1.9369405106105454e-05, + "loss": 0.9299, + "step": 1567 + }, + { + "epoch": 0.14039957468241088, + "grad_norm": 1.0362420842252216, + "learning_rate": 1.9368391093420004e-05, + "loss": 0.9011, + "step": 1568 + }, + { + "epoch": 0.14048911522748894, + "grad_norm": 1.0089279233651063, + "learning_rate": 1.9367376292696028e-05, + "loss": 0.9741, + "step": 1569 + }, + { + "epoch": 0.140578655772567, + "grad_norm": 1.0704996227198464, + "learning_rate": 1.936636070401888e-05, + "loss": 0.905, + "step": 1570 + }, + { + "epoch": 0.14066819631764507, + "grad_norm": 0.9967860295408286, + "learning_rate": 1.9365344327473996e-05, + "loss": 0.9043, + "step": 1571 + }, + { + "epoch": 0.14075773686272317, + "grad_norm": 0.9960395702834391, + "learning_rate": 1.9364327163146864e-05, + "loss": 0.9469, + "step": 1572 + }, + { + "epoch": 0.14084727740780123, + "grad_norm": 1.0661750366501428, + "learning_rate": 1.9363309211123046e-05, + "loss": 0.9432, + "step": 1573 + }, + { + "epoch": 0.1409368179528793, + "grad_norm": 0.9358561870698854, + "learning_rate": 1.936229047148817e-05, + "loss": 0.9408, + "step": 1574 + }, + { + "epoch": 0.14102635849795736, + "grad_norm": 0.9528100492527942, + "learning_rate": 1.9361270944327927e-05, + "loss": 0.8017, + "step": 1575 + }, + { + "epoch": 0.14111589904303543, + "grad_norm": 0.973697849413657, + "learning_rate": 1.936025062972808e-05, + "loss": 0.9283, + "step": 1576 + }, + { + "epoch": 0.1412054395881135, + "grad_norm": 0.9737801540220953, + "learning_rate": 1.935922952777445e-05, + "loss": 0.903, + "step": 1577 + }, + { + "epoch": 0.14129498013319156, + "grad_norm": 1.0446359434220713, + "learning_rate": 1.9358207638552934e-05, + "loss": 0.9159, + "step": 1578 + }, + { + "epoch": 0.14138452067826962, + "grad_norm": 1.461482645941444, + "learning_rate": 1.9357184962149483e-05, + "loss": 0.9669, + "step": 1579 + }, + { + "epoch": 0.14147406122334769, + "grad_norm": 0.9171066580256352, + "learning_rate": 1.935616149865013e-05, + "loss": 0.8946, + "step": 1580 + }, + { + "epoch": 0.14156360176842578, + "grad_norm": 1.0517842281944485, + "learning_rate": 1.935513724814096e-05, + "loss": 0.8995, + "step": 1581 + }, + { + "epoch": 0.14165314231350384, + "grad_norm": 1.0243279650484274, + "learning_rate": 1.9354112210708127e-05, + "loss": 0.9061, + "step": 1582 + }, + { + "epoch": 0.1417426828585819, + "grad_norm": 1.0013327753506995, + "learning_rate": 1.9353086386437858e-05, + "loss": 0.8611, + "step": 1583 + }, + { + "epoch": 0.14183222340365997, + "grad_norm": 0.9311046332129168, + "learning_rate": 1.9352059775416442e-05, + "loss": 0.9309, + "step": 1584 + }, + { + "epoch": 0.14192176394873804, + "grad_norm": 1.009360119571293, + "learning_rate": 1.9351032377730235e-05, + "loss": 0.8946, + "step": 1585 + }, + { + "epoch": 0.1420113044938161, + "grad_norm": 0.9596941736964932, + "learning_rate": 1.9350004193465653e-05, + "loss": 0.8689, + "step": 1586 + }, + { + "epoch": 0.14210084503889417, + "grad_norm": 0.9497722216304163, + "learning_rate": 1.934897522270919e-05, + "loss": 0.8827, + "step": 1587 + }, + { + "epoch": 0.14219038558397223, + "grad_norm": 1.0664829199808332, + "learning_rate": 1.9347945465547395e-05, + "loss": 0.9353, + "step": 1588 + }, + { + "epoch": 0.1422799261290503, + "grad_norm": 0.9409816815283192, + "learning_rate": 1.934691492206689e-05, + "loss": 0.9044, + "step": 1589 + }, + { + "epoch": 0.1423694666741284, + "grad_norm": 0.9974303083329258, + "learning_rate": 1.9345883592354362e-05, + "loss": 0.8679, + "step": 1590 + }, + { + "epoch": 0.14245900721920646, + "grad_norm": 1.0105461364280715, + "learning_rate": 1.9344851476496563e-05, + "loss": 0.9275, + "step": 1591 + }, + { + "epoch": 0.14254854776428452, + "grad_norm": 1.007867732092796, + "learning_rate": 1.9343818574580306e-05, + "loss": 0.9605, + "step": 1592 + }, + { + "epoch": 0.1426380883093626, + "grad_norm": 1.006724469234831, + "learning_rate": 1.934278488669248e-05, + "loss": 0.9408, + "step": 1593 + }, + { + "epoch": 0.14272762885444065, + "grad_norm": 0.9193185720500515, + "learning_rate": 1.9341750412920035e-05, + "loss": 0.8704, + "step": 1594 + }, + { + "epoch": 0.14281716939951872, + "grad_norm": 1.0620570933177556, + "learning_rate": 1.934071515334999e-05, + "loss": 0.8807, + "step": 1595 + }, + { + "epoch": 0.14290670994459678, + "grad_norm": 1.0364289883575133, + "learning_rate": 1.933967910806942e-05, + "loss": 0.9204, + "step": 1596 + }, + { + "epoch": 0.14299625048967485, + "grad_norm": 1.1257155746584762, + "learning_rate": 1.9338642277165484e-05, + "loss": 0.8554, + "step": 1597 + }, + { + "epoch": 0.1430857910347529, + "grad_norm": 1.004293766866379, + "learning_rate": 1.9337604660725388e-05, + "loss": 0.9113, + "step": 1598 + }, + { + "epoch": 0.143175331579831, + "grad_norm": 1.3246645356078093, + "learning_rate": 1.9336566258836417e-05, + "loss": 0.936, + "step": 1599 + }, + { + "epoch": 0.14326487212490907, + "grad_norm": 0.9392777809248289, + "learning_rate": 1.9335527071585918e-05, + "loss": 0.8597, + "step": 1600 + }, + { + "epoch": 0.14335441266998714, + "grad_norm": 0.8796597263190294, + "learning_rate": 1.9334487099061303e-05, + "loss": 0.8656, + "step": 1601 + }, + { + "epoch": 0.1434439532150652, + "grad_norm": 1.0527805696378545, + "learning_rate": 1.9333446341350052e-05, + "loss": 0.9208, + "step": 1602 + }, + { + "epoch": 0.14353349376014327, + "grad_norm": 0.9592535446678568, + "learning_rate": 1.933240479853971e-05, + "loss": 0.8565, + "step": 1603 + }, + { + "epoch": 0.14362303430522133, + "grad_norm": 1.0842584074530972, + "learning_rate": 1.9331362470717888e-05, + "loss": 0.9211, + "step": 1604 + }, + { + "epoch": 0.1437125748502994, + "grad_norm": 1.165562016191776, + "learning_rate": 1.9330319357972263e-05, + "loss": 0.9289, + "step": 1605 + }, + { + "epoch": 0.14380211539537746, + "grad_norm": 1.0079348278471336, + "learning_rate": 1.9329275460390575e-05, + "loss": 0.9174, + "step": 1606 + }, + { + "epoch": 0.14389165594045553, + "grad_norm": 1.2910558565204018, + "learning_rate": 1.9328230778060638e-05, + "loss": 0.9156, + "step": 1607 + }, + { + "epoch": 0.14398119648553362, + "grad_norm": 0.9808700500735781, + "learning_rate": 1.932718531107033e-05, + "loss": 0.867, + "step": 1608 + }, + { + "epoch": 0.14407073703061168, + "grad_norm": 0.9664932419539713, + "learning_rate": 1.9326139059507586e-05, + "loss": 0.9202, + "step": 1609 + }, + { + "epoch": 0.14416027757568975, + "grad_norm": 0.9050791304164366, + "learning_rate": 1.9325092023460414e-05, + "loss": 0.8673, + "step": 1610 + }, + { + "epoch": 0.14424981812076781, + "grad_norm": 1.110942641231669, + "learning_rate": 1.932404420301689e-05, + "loss": 0.9282, + "step": 1611 + }, + { + "epoch": 0.14433935866584588, + "grad_norm": 1.0176081708631357, + "learning_rate": 1.932299559826515e-05, + "loss": 0.9428, + "step": 1612 + }, + { + "epoch": 0.14442889921092394, + "grad_norm": 1.0077685018374516, + "learning_rate": 1.9321946209293406e-05, + "loss": 0.8898, + "step": 1613 + }, + { + "epoch": 0.144518439756002, + "grad_norm": 1.2406058275683514, + "learning_rate": 1.932089603618992e-05, + "loss": 0.9397, + "step": 1614 + }, + { + "epoch": 0.14460798030108007, + "grad_norm": 1.0652400703307328, + "learning_rate": 1.9319845079043035e-05, + "loss": 0.9077, + "step": 1615 + }, + { + "epoch": 0.14469752084615814, + "grad_norm": 1.0742662346584966, + "learning_rate": 1.931879333794115e-05, + "loss": 0.8476, + "step": 1616 + }, + { + "epoch": 0.14478706139123623, + "grad_norm": 1.035706885899711, + "learning_rate": 1.9317740812972742e-05, + "loss": 0.8648, + "step": 1617 + }, + { + "epoch": 0.1448766019363143, + "grad_norm": 1.0067839058283325, + "learning_rate": 1.9316687504226335e-05, + "loss": 0.9214, + "step": 1618 + }, + { + "epoch": 0.14496614248139236, + "grad_norm": 0.9531947853533249, + "learning_rate": 1.9315633411790538e-05, + "loss": 0.8785, + "step": 1619 + }, + { + "epoch": 0.14505568302647043, + "grad_norm": 1.091467169579033, + "learning_rate": 1.9314578535754017e-05, + "loss": 0.8625, + "step": 1620 + }, + { + "epoch": 0.1451452235715485, + "grad_norm": 0.9099326325941713, + "learning_rate": 1.93135228762055e-05, + "loss": 0.8704, + "step": 1621 + }, + { + "epoch": 0.14523476411662656, + "grad_norm": 1.0170926000704643, + "learning_rate": 1.931246643323379e-05, + "loss": 0.9667, + "step": 1622 + }, + { + "epoch": 0.14532430466170462, + "grad_norm": 1.0040015915710157, + "learning_rate": 1.9311409206927748e-05, + "loss": 0.9239, + "step": 1623 + }, + { + "epoch": 0.1454138452067827, + "grad_norm": 0.9409678691498216, + "learning_rate": 1.9310351197376312e-05, + "loss": 0.9248, + "step": 1624 + }, + { + "epoch": 0.14550338575186075, + "grad_norm": 1.012496135506889, + "learning_rate": 1.930929240466847e-05, + "loss": 0.8981, + "step": 1625 + }, + { + "epoch": 0.14559292629693885, + "grad_norm": 0.9347466760101097, + "learning_rate": 1.9308232828893283e-05, + "loss": 0.9085, + "step": 1626 + }, + { + "epoch": 0.1456824668420169, + "grad_norm": 1.0049308782716457, + "learning_rate": 1.930717247013989e-05, + "loss": 0.86, + "step": 1627 + }, + { + "epoch": 0.14577200738709498, + "grad_norm": 1.1140220633251008, + "learning_rate": 1.930611132849747e-05, + "loss": 0.9966, + "step": 1628 + }, + { + "epoch": 0.14586154793217304, + "grad_norm": 0.9831739867859024, + "learning_rate": 1.9305049404055302e-05, + "loss": 0.8787, + "step": 1629 + }, + { + "epoch": 0.1459510884772511, + "grad_norm": 1.01481799373667, + "learning_rate": 1.930398669690269e-05, + "loss": 0.9152, + "step": 1630 + }, + { + "epoch": 0.14604062902232917, + "grad_norm": 1.0070583090543324, + "learning_rate": 1.9302923207129043e-05, + "loss": 0.8129, + "step": 1631 + }, + { + "epoch": 0.14613016956740724, + "grad_norm": 0.8688964721845012, + "learning_rate": 1.930185893482381e-05, + "loss": 0.8434, + "step": 1632 + }, + { + "epoch": 0.1462197101124853, + "grad_norm": 0.9552916009119464, + "learning_rate": 1.9300793880076513e-05, + "loss": 0.9256, + "step": 1633 + }, + { + "epoch": 0.14630925065756337, + "grad_norm": 1.1242482708284693, + "learning_rate": 1.9299728042976745e-05, + "loss": 0.9126, + "step": 1634 + }, + { + "epoch": 0.14639879120264146, + "grad_norm": 1.0639759991311433, + "learning_rate": 1.929866142361416e-05, + "loss": 0.8704, + "step": 1635 + }, + { + "epoch": 0.14648833174771952, + "grad_norm": 1.085683289026062, + "learning_rate": 1.9297594022078473e-05, + "loss": 0.9189, + "step": 1636 + }, + { + "epoch": 0.1465778722927976, + "grad_norm": 0.9204699197360561, + "learning_rate": 1.929652583845948e-05, + "loss": 0.8562, + "step": 1637 + }, + { + "epoch": 0.14666741283787565, + "grad_norm": 1.2474992675095748, + "learning_rate": 1.9295456872847027e-05, + "loss": 0.928, + "step": 1638 + }, + { + "epoch": 0.14675695338295372, + "grad_norm": 1.3276942361495088, + "learning_rate": 1.929438712533103e-05, + "loss": 0.9217, + "step": 1639 + }, + { + "epoch": 0.14684649392803178, + "grad_norm": 0.9826261683964727, + "learning_rate": 1.929331659600148e-05, + "loss": 0.8575, + "step": 1640 + }, + { + "epoch": 0.14693603447310985, + "grad_norm": 1.3021351143971271, + "learning_rate": 1.929224528494842e-05, + "loss": 0.8863, + "step": 1641 + }, + { + "epoch": 0.14702557501818792, + "grad_norm": 0.9634260094680092, + "learning_rate": 1.9291173192261966e-05, + "loss": 0.8803, + "step": 1642 + }, + { + "epoch": 0.14711511556326598, + "grad_norm": 0.9643633518283496, + "learning_rate": 1.9290100318032303e-05, + "loss": 0.9194, + "step": 1643 + }, + { + "epoch": 0.14720465610834407, + "grad_norm": 0.9393342938255379, + "learning_rate": 1.9289026662349674e-05, + "loss": 0.87, + "step": 1644 + }, + { + "epoch": 0.14729419665342214, + "grad_norm": 1.064576242808001, + "learning_rate": 1.9287952225304392e-05, + "loss": 0.9743, + "step": 1645 + }, + { + "epoch": 0.1473837371985002, + "grad_norm": 1.1252698317003016, + "learning_rate": 1.9286877006986833e-05, + "loss": 0.8377, + "step": 1646 + }, + { + "epoch": 0.14747327774357827, + "grad_norm": 1.0449420888633874, + "learning_rate": 1.9285801007487446e-05, + "loss": 0.878, + "step": 1647 + }, + { + "epoch": 0.14756281828865633, + "grad_norm": 1.0862417024625208, + "learning_rate": 1.928472422689674e-05, + "loss": 0.9638, + "step": 1648 + }, + { + "epoch": 0.1476523588337344, + "grad_norm": 1.0384229027745993, + "learning_rate": 1.9283646665305283e-05, + "loss": 0.8814, + "step": 1649 + }, + { + "epoch": 0.14774189937881246, + "grad_norm": 1.2214679936034576, + "learning_rate": 1.9282568322803724e-05, + "loss": 0.9657, + "step": 1650 + }, + { + "epoch": 0.14783143992389053, + "grad_norm": 1.0548244429113125, + "learning_rate": 1.928148919948277e-05, + "loss": 0.8795, + "step": 1651 + }, + { + "epoch": 0.1479209804689686, + "grad_norm": 0.9866989311189773, + "learning_rate": 1.9280409295433187e-05, + "loss": 0.8788, + "step": 1652 + }, + { + "epoch": 0.1480105210140467, + "grad_norm": 0.9706257870362636, + "learning_rate": 1.9279328610745812e-05, + "loss": 0.8655, + "step": 1653 + }, + { + "epoch": 0.14810006155912475, + "grad_norm": 1.1083910929669207, + "learning_rate": 1.927824714551156e-05, + "loss": 0.8737, + "step": 1654 + }, + { + "epoch": 0.14818960210420282, + "grad_norm": 1.2928505373657686, + "learning_rate": 1.927716489982139e-05, + "loss": 0.9181, + "step": 1655 + }, + { + "epoch": 0.14827914264928088, + "grad_norm": 0.9399123850283069, + "learning_rate": 1.9276081873766342e-05, + "loss": 0.8435, + "step": 1656 + }, + { + "epoch": 0.14836868319435895, + "grad_norm": 1.0866699905959638, + "learning_rate": 1.9274998067437513e-05, + "loss": 0.943, + "step": 1657 + }, + { + "epoch": 0.148458223739437, + "grad_norm": 1.0342047835482897, + "learning_rate": 1.927391348092607e-05, + "loss": 0.938, + "step": 1658 + }, + { + "epoch": 0.14854776428451508, + "grad_norm": 0.9354046794640771, + "learning_rate": 1.9272828114323247e-05, + "loss": 0.8734, + "step": 1659 + }, + { + "epoch": 0.14863730482959314, + "grad_norm": 1.1138804707617767, + "learning_rate": 1.9271741967720342e-05, + "loss": 0.9539, + "step": 1660 + }, + { + "epoch": 0.1487268453746712, + "grad_norm": 1.0314683170449572, + "learning_rate": 1.9270655041208714e-05, + "loss": 0.8866, + "step": 1661 + }, + { + "epoch": 0.1488163859197493, + "grad_norm": 1.3574802110382618, + "learning_rate": 1.9269567334879794e-05, + "loss": 0.9521, + "step": 1662 + }, + { + "epoch": 0.14890592646482737, + "grad_norm": 0.9467197932898966, + "learning_rate": 1.926847884882508e-05, + "loss": 0.8892, + "step": 1663 + }, + { + "epoch": 0.14899546700990543, + "grad_norm": 1.0826583505192637, + "learning_rate": 1.9267389583136124e-05, + "loss": 0.8893, + "step": 1664 + }, + { + "epoch": 0.1490850075549835, + "grad_norm": 0.9967726748430142, + "learning_rate": 1.926629953790456e-05, + "loss": 0.9929, + "step": 1665 + }, + { + "epoch": 0.14917454810006156, + "grad_norm": 1.454136198969318, + "learning_rate": 1.9265208713222075e-05, + "loss": 0.9938, + "step": 1666 + }, + { + "epoch": 0.14926408864513963, + "grad_norm": 1.3076142784518345, + "learning_rate": 1.9264117109180423e-05, + "loss": 0.921, + "step": 1667 + }, + { + "epoch": 0.1493536291902177, + "grad_norm": 0.9624831595207629, + "learning_rate": 1.9263024725871427e-05, + "loss": 0.8635, + "step": 1668 + }, + { + "epoch": 0.14944316973529576, + "grad_norm": 1.0900153773481214, + "learning_rate": 1.926193156338698e-05, + "loss": 0.9409, + "step": 1669 + }, + { + "epoch": 0.14953271028037382, + "grad_norm": 1.1687275268025108, + "learning_rate": 1.9260837621819035e-05, + "loss": 0.8564, + "step": 1670 + }, + { + "epoch": 0.1496222508254519, + "grad_norm": 0.9683242942917771, + "learning_rate": 1.92597429012596e-05, + "loss": 0.8841, + "step": 1671 + }, + { + "epoch": 0.14971179137052998, + "grad_norm": 0.9708117550467407, + "learning_rate": 1.9258647401800772e-05, + "loss": 0.8573, + "step": 1672 + }, + { + "epoch": 0.14980133191560804, + "grad_norm": 1.049451884123498, + "learning_rate": 1.9257551123534696e-05, + "loss": 0.8921, + "step": 1673 + }, + { + "epoch": 0.1498908724606861, + "grad_norm": 1.0402536247413583, + "learning_rate": 1.9256454066553583e-05, + "loss": 0.9018, + "step": 1674 + }, + { + "epoch": 0.14998041300576417, + "grad_norm": 0.909739770322449, + "learning_rate": 1.925535623094972e-05, + "loss": 0.8054, + "step": 1675 + }, + { + "epoch": 0.15006995355084224, + "grad_norm": 1.0172632156567232, + "learning_rate": 1.9254257616815452e-05, + "loss": 0.9592, + "step": 1676 + }, + { + "epoch": 0.1501594940959203, + "grad_norm": 1.072175189305115, + "learning_rate": 1.925315822424319e-05, + "loss": 0.9451, + "step": 1677 + }, + { + "epoch": 0.15024903464099837, + "grad_norm": 1.0373673257059377, + "learning_rate": 1.925205805332541e-05, + "loss": 0.9224, + "step": 1678 + }, + { + "epoch": 0.15033857518607643, + "grad_norm": 1.1765660537447373, + "learning_rate": 1.925095710415466e-05, + "loss": 0.8962, + "step": 1679 + }, + { + "epoch": 0.15042811573115453, + "grad_norm": 1.1048910546103297, + "learning_rate": 1.9249855376823542e-05, + "loss": 0.9237, + "step": 1680 + }, + { + "epoch": 0.1505176562762326, + "grad_norm": 0.9904288374472184, + "learning_rate": 1.924875287142473e-05, + "loss": 0.9093, + "step": 1681 + }, + { + "epoch": 0.15060719682131066, + "grad_norm": 0.9862771249616881, + "learning_rate": 1.924764958805097e-05, + "loss": 0.8445, + "step": 1682 + }, + { + "epoch": 0.15069673736638872, + "grad_norm": 1.0272249353101568, + "learning_rate": 1.924654552679506e-05, + "loss": 0.9106, + "step": 1683 + }, + { + "epoch": 0.1507862779114668, + "grad_norm": 1.2453594745514973, + "learning_rate": 1.9245440687749872e-05, + "loss": 0.9209, + "step": 1684 + }, + { + "epoch": 0.15087581845654485, + "grad_norm": 1.0942652481282462, + "learning_rate": 1.924433507100834e-05, + "loss": 0.8245, + "step": 1685 + }, + { + "epoch": 0.15096535900162292, + "grad_norm": 1.1398269743143796, + "learning_rate": 1.9243228676663467e-05, + "loss": 0.9486, + "step": 1686 + }, + { + "epoch": 0.15105489954670098, + "grad_norm": 1.0078284916476308, + "learning_rate": 1.924212150480832e-05, + "loss": 0.9377, + "step": 1687 + }, + { + "epoch": 0.15114444009177905, + "grad_norm": 0.9781319299042506, + "learning_rate": 1.924101355553603e-05, + "loss": 0.9015, + "step": 1688 + }, + { + "epoch": 0.15123398063685714, + "grad_norm": 1.3356990811091403, + "learning_rate": 1.923990482893979e-05, + "loss": 0.9382, + "step": 1689 + }, + { + "epoch": 0.1513235211819352, + "grad_norm": 0.9432762623182328, + "learning_rate": 1.9238795325112867e-05, + "loss": 0.8906, + "step": 1690 + }, + { + "epoch": 0.15141306172701327, + "grad_norm": 0.9372007524023076, + "learning_rate": 1.923768504414859e-05, + "loss": 0.8947, + "step": 1691 + }, + { + "epoch": 0.15150260227209134, + "grad_norm": 0.9416501743965463, + "learning_rate": 1.923657398614035e-05, + "loss": 0.8744, + "step": 1692 + }, + { + "epoch": 0.1515921428171694, + "grad_norm": 1.1262780696943868, + "learning_rate": 1.9235462151181603e-05, + "loss": 0.91, + "step": 1693 + }, + { + "epoch": 0.15168168336224747, + "grad_norm": 0.9304155595549114, + "learning_rate": 1.923434953936588e-05, + "loss": 0.8882, + "step": 1694 + }, + { + "epoch": 0.15177122390732553, + "grad_norm": 1.2335686477408923, + "learning_rate": 1.923323615078676e-05, + "loss": 0.8617, + "step": 1695 + }, + { + "epoch": 0.1518607644524036, + "grad_norm": 1.0874521287515853, + "learning_rate": 1.9232121985537907e-05, + "loss": 0.9733, + "step": 1696 + }, + { + "epoch": 0.15195030499748166, + "grad_norm": 1.10016197907857, + "learning_rate": 1.9231007043713034e-05, + "loss": 0.8738, + "step": 1697 + }, + { + "epoch": 0.15203984554255975, + "grad_norm": 0.9389593837329341, + "learning_rate": 1.9229891325405934e-05, + "loss": 0.9086, + "step": 1698 + }, + { + "epoch": 0.15212938608763782, + "grad_norm": 1.0037799400450909, + "learning_rate": 1.922877483071045e-05, + "loss": 0.9211, + "step": 1699 + }, + { + "epoch": 0.15221892663271588, + "grad_norm": 1.0682228841498402, + "learning_rate": 1.9227657559720504e-05, + "loss": 0.9358, + "step": 1700 + }, + { + "epoch": 0.15230846717779395, + "grad_norm": 0.928431560949346, + "learning_rate": 1.922653951253007e-05, + "loss": 0.9146, + "step": 1701 + }, + { + "epoch": 0.15239800772287201, + "grad_norm": 1.004864152360824, + "learning_rate": 1.92254206892332e-05, + "loss": 0.867, + "step": 1702 + }, + { + "epoch": 0.15248754826795008, + "grad_norm": 1.0107481486628573, + "learning_rate": 1.922430108992401e-05, + "loss": 0.8737, + "step": 1703 + }, + { + "epoch": 0.15257708881302814, + "grad_norm": 0.8596512905076935, + "learning_rate": 1.9223180714696664e-05, + "loss": 0.8334, + "step": 1704 + }, + { + "epoch": 0.1526666293581062, + "grad_norm": 0.9201486337002881, + "learning_rate": 1.9222059563645418e-05, + "loss": 0.8519, + "step": 1705 + }, + { + "epoch": 0.15275616990318427, + "grad_norm": 0.9600246831311577, + "learning_rate": 1.922093763686457e-05, + "loss": 0.9317, + "step": 1706 + }, + { + "epoch": 0.15284571044826237, + "grad_norm": 1.454375072559627, + "learning_rate": 1.9219814934448496e-05, + "loss": 0.9027, + "step": 1707 + }, + { + "epoch": 0.15293525099334043, + "grad_norm": 1.0454228167947963, + "learning_rate": 1.9218691456491637e-05, + "loss": 0.9104, + "step": 1708 + }, + { + "epoch": 0.1530247915384185, + "grad_norm": 0.9883197470373759, + "learning_rate": 1.921756720308849e-05, + "loss": 0.8084, + "step": 1709 + }, + { + "epoch": 0.15311433208349656, + "grad_norm": 1.0893429584820449, + "learning_rate": 1.921644217433363e-05, + "loss": 0.9321, + "step": 1710 + }, + { + "epoch": 0.15320387262857463, + "grad_norm": 0.9689447935480849, + "learning_rate": 1.9215316370321686e-05, + "loss": 0.9323, + "step": 1711 + }, + { + "epoch": 0.1532934131736527, + "grad_norm": 1.1843863349688082, + "learning_rate": 1.9214189791147363e-05, + "loss": 0.865, + "step": 1712 + }, + { + "epoch": 0.15338295371873076, + "grad_norm": 0.9267532787454216, + "learning_rate": 1.9213062436905415e-05, + "loss": 0.909, + "step": 1713 + }, + { + "epoch": 0.15347249426380882, + "grad_norm": 0.9782882450590263, + "learning_rate": 1.9211934307690682e-05, + "loss": 0.9246, + "step": 1714 + }, + { + "epoch": 0.1535620348088869, + "grad_norm": 0.9095113387660075, + "learning_rate": 1.9210805403598053e-05, + "loss": 0.8637, + "step": 1715 + }, + { + "epoch": 0.15365157535396498, + "grad_norm": 1.1724356192394525, + "learning_rate": 1.9209675724722486e-05, + "loss": 0.8924, + "step": 1716 + }, + { + "epoch": 0.15374111589904305, + "grad_norm": 0.9738665955886789, + "learning_rate": 1.920854527115901e-05, + "loss": 0.9243, + "step": 1717 + }, + { + "epoch": 0.1538306564441211, + "grad_norm": 1.0246825992957984, + "learning_rate": 1.9207414043002718e-05, + "loss": 0.8655, + "step": 1718 + }, + { + "epoch": 0.15392019698919918, + "grad_norm": 1.0482124032108133, + "learning_rate": 1.9206282040348757e-05, + "loss": 0.9375, + "step": 1719 + }, + { + "epoch": 0.15400973753427724, + "grad_norm": 1.0704145063796735, + "learning_rate": 1.9205149263292352e-05, + "loss": 0.9305, + "step": 1720 + }, + { + "epoch": 0.1540992780793553, + "grad_norm": 1.0371058897114473, + "learning_rate": 1.920401571192879e-05, + "loss": 0.8676, + "step": 1721 + }, + { + "epoch": 0.15418881862443337, + "grad_norm": 1.0286335240610645, + "learning_rate": 1.9202881386353415e-05, + "loss": 0.9735, + "step": 1722 + }, + { + "epoch": 0.15427835916951144, + "grad_norm": 1.0513961457189702, + "learning_rate": 1.920174628666165e-05, + "loss": 0.9022, + "step": 1723 + }, + { + "epoch": 0.1543678997145895, + "grad_norm": 0.9770094298286088, + "learning_rate": 1.920061041294897e-05, + "loss": 0.8881, + "step": 1724 + }, + { + "epoch": 0.1544574402596676, + "grad_norm": 0.9990047190345827, + "learning_rate": 1.9199473765310928e-05, + "loss": 0.9214, + "step": 1725 + }, + { + "epoch": 0.15454698080474566, + "grad_norm": 0.9384725549469383, + "learning_rate": 1.919833634384313e-05, + "loss": 0.9048, + "step": 1726 + }, + { + "epoch": 0.15463652134982372, + "grad_norm": 1.1731562245797693, + "learning_rate": 1.9197198148641252e-05, + "loss": 0.9057, + "step": 1727 + }, + { + "epoch": 0.1547260618949018, + "grad_norm": 1.0448253936372807, + "learning_rate": 1.9196059179801038e-05, + "loss": 0.9146, + "step": 1728 + }, + { + "epoch": 0.15481560243997985, + "grad_norm": 1.138080988090882, + "learning_rate": 1.9194919437418297e-05, + "loss": 0.8877, + "step": 1729 + }, + { + "epoch": 0.15490514298505792, + "grad_norm": 1.0972501186985062, + "learning_rate": 1.919377892158889e-05, + "loss": 0.9143, + "step": 1730 + }, + { + "epoch": 0.15499468353013598, + "grad_norm": 1.0017073773753558, + "learning_rate": 1.9192637632408765e-05, + "loss": 0.895, + "step": 1731 + }, + { + "epoch": 0.15508422407521405, + "grad_norm": 0.959223867180494, + "learning_rate": 1.9191495569973915e-05, + "loss": 0.8925, + "step": 1732 + }, + { + "epoch": 0.15517376462029212, + "grad_norm": 1.0759538408104188, + "learning_rate": 1.919035273438041e-05, + "loss": 0.8484, + "step": 1733 + }, + { + "epoch": 0.1552633051653702, + "grad_norm": 0.9958439562387594, + "learning_rate": 1.9189209125724383e-05, + "loss": 0.9161, + "step": 1734 + }, + { + "epoch": 0.15535284571044827, + "grad_norm": 1.1272260402792358, + "learning_rate": 1.9188064744102027e-05, + "loss": 0.9292, + "step": 1735 + }, + { + "epoch": 0.15544238625552634, + "grad_norm": 0.9798695817442161, + "learning_rate": 1.918691958960961e-05, + "loss": 0.9102, + "step": 1736 + }, + { + "epoch": 0.1555319268006044, + "grad_norm": 0.9581948105339737, + "learning_rate": 1.918577366234345e-05, + "loss": 0.9464, + "step": 1737 + }, + { + "epoch": 0.15562146734568247, + "grad_norm": 1.014761371939899, + "learning_rate": 1.9184626962399946e-05, + "loss": 0.8301, + "step": 1738 + }, + { + "epoch": 0.15571100789076053, + "grad_norm": 1.0417808289977908, + "learning_rate": 1.918347948987555e-05, + "loss": 0.9079, + "step": 1739 + }, + { + "epoch": 0.1558005484358386, + "grad_norm": 1.0583141139207035, + "learning_rate": 1.918233124486679e-05, + "loss": 0.8481, + "step": 1740 + }, + { + "epoch": 0.15589008898091666, + "grad_norm": 1.0765333402178028, + "learning_rate": 1.9181182227470243e-05, + "loss": 0.9526, + "step": 1741 + }, + { + "epoch": 0.15597962952599473, + "grad_norm": 1.0105388316886106, + "learning_rate": 1.918003243778257e-05, + "loss": 0.878, + "step": 1742 + }, + { + "epoch": 0.15606917007107282, + "grad_norm": 0.9561199474333818, + "learning_rate": 1.917888187590048e-05, + "loss": 0.8757, + "step": 1743 + }, + { + "epoch": 0.1561587106161509, + "grad_norm": 1.0567663791856519, + "learning_rate": 1.917773054192076e-05, + "loss": 0.9316, + "step": 1744 + }, + { + "epoch": 0.15624825116122895, + "grad_norm": 1.1955711681783978, + "learning_rate": 1.9176578435940253e-05, + "loss": 0.9656, + "step": 1745 + }, + { + "epoch": 0.15633779170630702, + "grad_norm": 1.0858473664831918, + "learning_rate": 1.917542555805587e-05, + "loss": 0.9149, + "step": 1746 + }, + { + "epoch": 0.15642733225138508, + "grad_norm": 1.1120073447556666, + "learning_rate": 1.917427190836459e-05, + "loss": 0.8436, + "step": 1747 + }, + { + "epoch": 0.15651687279646315, + "grad_norm": 0.9249862821127601, + "learning_rate": 1.9173117486963457e-05, + "loss": 0.8907, + "step": 1748 + }, + { + "epoch": 0.1566064133415412, + "grad_norm": 1.03137665728002, + "learning_rate": 1.9171962293949572e-05, + "loss": 0.8836, + "step": 1749 + }, + { + "epoch": 0.15669595388661928, + "grad_norm": 0.9754914537185936, + "learning_rate": 1.9170806329420105e-05, + "loss": 0.9083, + "step": 1750 + }, + { + "epoch": 0.15678549443169734, + "grad_norm": 1.0829965051577897, + "learning_rate": 1.9169649593472297e-05, + "loss": 0.8615, + "step": 1751 + }, + { + "epoch": 0.15687503497677543, + "grad_norm": 1.0353806850141412, + "learning_rate": 1.9168492086203444e-05, + "loss": 0.8456, + "step": 1752 + }, + { + "epoch": 0.1569645755218535, + "grad_norm": 0.9325991040514573, + "learning_rate": 1.9167333807710915e-05, + "loss": 0.9073, + "step": 1753 + }, + { + "epoch": 0.15705411606693157, + "grad_norm": 0.9753712552157462, + "learning_rate": 1.916617475809214e-05, + "loss": 0.928, + "step": 1754 + }, + { + "epoch": 0.15714365661200963, + "grad_norm": 0.9348701748376285, + "learning_rate": 1.9165014937444616e-05, + "loss": 0.9043, + "step": 1755 + }, + { + "epoch": 0.1572331971570877, + "grad_norm": 1.0317541602875142, + "learning_rate": 1.91638543458659e-05, + "loss": 0.9441, + "step": 1756 + }, + { + "epoch": 0.15732273770216576, + "grad_norm": 0.9895142936683405, + "learning_rate": 1.9162692983453617e-05, + "loss": 0.9033, + "step": 1757 + }, + { + "epoch": 0.15741227824724383, + "grad_norm": 0.9642096118727083, + "learning_rate": 1.9161530850305464e-05, + "loss": 0.9002, + "step": 1758 + }, + { + "epoch": 0.1575018187923219, + "grad_norm": 1.0232302914839753, + "learning_rate": 1.9160367946519186e-05, + "loss": 0.9242, + "step": 1759 + }, + { + "epoch": 0.15759135933739996, + "grad_norm": 1.1157461658286578, + "learning_rate": 1.915920427219261e-05, + "loss": 0.9536, + "step": 1760 + }, + { + "epoch": 0.15768089988247805, + "grad_norm": 1.0899057415992095, + "learning_rate": 1.9158039827423615e-05, + "loss": 0.902, + "step": 1761 + }, + { + "epoch": 0.1577704404275561, + "grad_norm": 1.0019860379641987, + "learning_rate": 1.915687461231015e-05, + "loss": 0.8649, + "step": 1762 + }, + { + "epoch": 0.15785998097263418, + "grad_norm": 1.0592047089991492, + "learning_rate": 1.915570862695024e-05, + "loss": 0.9045, + "step": 1763 + }, + { + "epoch": 0.15794952151771224, + "grad_norm": 1.118022235655546, + "learning_rate": 1.915454187144195e-05, + "loss": 0.8882, + "step": 1764 + }, + { + "epoch": 0.1580390620627903, + "grad_norm": 1.1065302640531012, + "learning_rate": 1.915337434588343e-05, + "loss": 0.8864, + "step": 1765 + }, + { + "epoch": 0.15812860260786837, + "grad_norm": 0.9711734405211765, + "learning_rate": 1.9152206050372896e-05, + "loss": 0.884, + "step": 1766 + }, + { + "epoch": 0.15821814315294644, + "grad_norm": 1.0951625441336368, + "learning_rate": 1.9151036985008606e-05, + "loss": 0.8569, + "step": 1767 + }, + { + "epoch": 0.1583076836980245, + "grad_norm": 0.9608988518669533, + "learning_rate": 1.9149867149888905e-05, + "loss": 0.8928, + "step": 1768 + }, + { + "epoch": 0.15839722424310257, + "grad_norm": 0.9135475004102169, + "learning_rate": 1.91486965451122e-05, + "loss": 0.8761, + "step": 1769 + }, + { + "epoch": 0.15848676478818066, + "grad_norm": 0.9720708661546296, + "learning_rate": 1.914752517077695e-05, + "loss": 0.9435, + "step": 1770 + }, + { + "epoch": 0.15857630533325873, + "grad_norm": 1.0096825964317873, + "learning_rate": 1.9146353026981694e-05, + "loss": 0.8708, + "step": 1771 + }, + { + "epoch": 0.1586658458783368, + "grad_norm": 1.1587247379357897, + "learning_rate": 1.914518011382503e-05, + "loss": 0.8976, + "step": 1772 + }, + { + "epoch": 0.15875538642341486, + "grad_norm": 0.9706324214839399, + "learning_rate": 1.914400643140561e-05, + "loss": 0.8366, + "step": 1773 + }, + { + "epoch": 0.15884492696849292, + "grad_norm": 0.9899641933223498, + "learning_rate": 1.914283197982217e-05, + "loss": 0.8812, + "step": 1774 + }, + { + "epoch": 0.158934467513571, + "grad_norm": 1.0513731266360786, + "learning_rate": 1.9141656759173496e-05, + "loss": 0.8886, + "step": 1775 + }, + { + "epoch": 0.15902400805864905, + "grad_norm": 1.2126002470755233, + "learning_rate": 1.9140480769558448e-05, + "loss": 0.9247, + "step": 1776 + }, + { + "epoch": 0.15911354860372712, + "grad_norm": 1.2239739020225335, + "learning_rate": 1.9139304011075944e-05, + "loss": 0.9514, + "step": 1777 + }, + { + "epoch": 0.15920308914880518, + "grad_norm": 0.9826377993678783, + "learning_rate": 1.9138126483824965e-05, + "loss": 0.9733, + "step": 1778 + }, + { + "epoch": 0.15929262969388328, + "grad_norm": 0.9262648217731771, + "learning_rate": 1.913694818790457e-05, + "loss": 0.8388, + "step": 1779 + }, + { + "epoch": 0.15938217023896134, + "grad_norm": 1.182564110672693, + "learning_rate": 1.9135769123413862e-05, + "loss": 0.9113, + "step": 1780 + }, + { + "epoch": 0.1594717107840394, + "grad_norm": 1.0588149240165425, + "learning_rate": 1.913458929045203e-05, + "loss": 0.8948, + "step": 1781 + }, + { + "epoch": 0.15956125132911747, + "grad_norm": 1.0502516062560021, + "learning_rate": 1.9133408689118312e-05, + "loss": 0.8756, + "step": 1782 + }, + { + "epoch": 0.15965079187419554, + "grad_norm": 1.0688992063889948, + "learning_rate": 1.913222731951202e-05, + "loss": 0.918, + "step": 1783 + }, + { + "epoch": 0.1597403324192736, + "grad_norm": 1.0948674189639584, + "learning_rate": 1.9131045181732525e-05, + "loss": 0.9795, + "step": 1784 + }, + { + "epoch": 0.15982987296435167, + "grad_norm": 1.1447905760481059, + "learning_rate": 1.9129862275879262e-05, + "loss": 0.9086, + "step": 1785 + }, + { + "epoch": 0.15991941350942973, + "grad_norm": 0.9379086436814146, + "learning_rate": 1.912867860205174e-05, + "loss": 0.8887, + "step": 1786 + }, + { + "epoch": 0.1600089540545078, + "grad_norm": 1.0287472385780494, + "learning_rate": 1.9127494160349517e-05, + "loss": 0.9246, + "step": 1787 + }, + { + "epoch": 0.1600984945995859, + "grad_norm": 0.8672738727128856, + "learning_rate": 1.9126308950872233e-05, + "loss": 0.9389, + "step": 1788 + }, + { + "epoch": 0.16018803514466395, + "grad_norm": 1.166187739527242, + "learning_rate": 1.912512297371958e-05, + "loss": 0.8844, + "step": 1789 + }, + { + "epoch": 0.16027757568974202, + "grad_norm": 1.3506284664552248, + "learning_rate": 1.9123936228991312e-05, + "loss": 0.9404, + "step": 1790 + }, + { + "epoch": 0.16036711623482008, + "grad_norm": 1.0262532356156928, + "learning_rate": 1.9122748716787266e-05, + "loss": 0.9149, + "step": 1791 + }, + { + "epoch": 0.16045665677989815, + "grad_norm": 0.9453563141447522, + "learning_rate": 1.912156043720733e-05, + "loss": 0.8695, + "step": 1792 + }, + { + "epoch": 0.16054619732497621, + "grad_norm": 0.9029191295061255, + "learning_rate": 1.9120371390351446e-05, + "loss": 0.9587, + "step": 1793 + }, + { + "epoch": 0.16063573787005428, + "grad_norm": 1.0136423533455607, + "learning_rate": 1.9119181576319648e-05, + "loss": 0.9501, + "step": 1794 + }, + { + "epoch": 0.16072527841513234, + "grad_norm": 1.0274118793379396, + "learning_rate": 1.9117990995212012e-05, + "loss": 0.8758, + "step": 1795 + }, + { + "epoch": 0.1608148189602104, + "grad_norm": 1.024427619480751, + "learning_rate": 1.9116799647128683e-05, + "loss": 0.9066, + "step": 1796 + }, + { + "epoch": 0.1609043595052885, + "grad_norm": 0.9686678313654561, + "learning_rate": 1.911560753216988e-05, + "loss": 0.9292, + "step": 1797 + }, + { + "epoch": 0.16099390005036657, + "grad_norm": 1.0041898095009703, + "learning_rate": 1.9114414650435875e-05, + "loss": 0.9043, + "step": 1798 + }, + { + "epoch": 0.16108344059544463, + "grad_norm": 0.9024253253045971, + "learning_rate": 1.9113221002027007e-05, + "loss": 0.915, + "step": 1799 + }, + { + "epoch": 0.1611729811405227, + "grad_norm": 1.1326755850562251, + "learning_rate": 1.911202658704369e-05, + "loss": 0.915, + "step": 1800 + }, + { + "epoch": 0.16126252168560076, + "grad_norm": 0.9072375486139627, + "learning_rate": 1.9110831405586387e-05, + "loss": 0.8906, + "step": 1801 + }, + { + "epoch": 0.16135206223067883, + "grad_norm": 0.958710214489495, + "learning_rate": 1.910963545775564e-05, + "loss": 0.8819, + "step": 1802 + }, + { + "epoch": 0.1614416027757569, + "grad_norm": 0.9624361526271846, + "learning_rate": 1.910843874365204e-05, + "loss": 0.897, + "step": 1803 + }, + { + "epoch": 0.16153114332083496, + "grad_norm": 0.9528834239750904, + "learning_rate": 1.9107241263376256e-05, + "loss": 0.8714, + "step": 1804 + }, + { + "epoch": 0.16162068386591302, + "grad_norm": 0.9384984165218986, + "learning_rate": 1.9106043017029012e-05, + "loss": 0.8853, + "step": 1805 + }, + { + "epoch": 0.16171022441099112, + "grad_norm": 0.9883283282398443, + "learning_rate": 1.9104844004711107e-05, + "loss": 0.9357, + "step": 1806 + }, + { + "epoch": 0.16179976495606918, + "grad_norm": 0.9645956168311687, + "learning_rate": 1.9103644226523395e-05, + "loss": 0.9237, + "step": 1807 + }, + { + "epoch": 0.16188930550114725, + "grad_norm": 1.0387433363731493, + "learning_rate": 1.9102443682566792e-05, + "loss": 0.8613, + "step": 1808 + }, + { + "epoch": 0.1619788460462253, + "grad_norm": 0.9014205844391221, + "learning_rate": 1.9101242372942292e-05, + "loss": 0.8921, + "step": 1809 + }, + { + "epoch": 0.16206838659130338, + "grad_norm": 1.029366396147913, + "learning_rate": 1.9100040297750942e-05, + "loss": 0.9768, + "step": 1810 + }, + { + "epoch": 0.16215792713638144, + "grad_norm": 0.9672532183859828, + "learning_rate": 1.9098837457093858e-05, + "loss": 0.8835, + "step": 1811 + }, + { + "epoch": 0.1622474676814595, + "grad_norm": 0.8894161130914849, + "learning_rate": 1.9097633851072212e-05, + "loss": 0.8687, + "step": 1812 + }, + { + "epoch": 0.16233700822653757, + "grad_norm": 1.0813919692184535, + "learning_rate": 1.9096429479787256e-05, + "loss": 0.8396, + "step": 1813 + }, + { + "epoch": 0.16242654877161564, + "grad_norm": 1.0204990139340124, + "learning_rate": 1.9095224343340298e-05, + "loss": 0.9005, + "step": 1814 + }, + { + "epoch": 0.1625160893166937, + "grad_norm": 1.0300138051134917, + "learning_rate": 1.9094018441832704e-05, + "loss": 0.9384, + "step": 1815 + }, + { + "epoch": 0.1626056298617718, + "grad_norm": 0.8883632712759655, + "learning_rate": 1.9092811775365914e-05, + "loss": 0.8535, + "step": 1816 + }, + { + "epoch": 0.16269517040684986, + "grad_norm": 0.914692354156227, + "learning_rate": 1.9091604344041425e-05, + "loss": 0.8711, + "step": 1817 + }, + { + "epoch": 0.16278471095192792, + "grad_norm": 1.0493945611899447, + "learning_rate": 1.9090396147960808e-05, + "loss": 0.9119, + "step": 1818 + }, + { + "epoch": 0.162874251497006, + "grad_norm": 1.000402712180523, + "learning_rate": 1.908918718722569e-05, + "loss": 0.9041, + "step": 1819 + }, + { + "epoch": 0.16296379204208405, + "grad_norm": 1.1090771392608443, + "learning_rate": 1.9087977461937764e-05, + "loss": 0.8712, + "step": 1820 + }, + { + "epoch": 0.16305333258716212, + "grad_norm": 0.9203066789039771, + "learning_rate": 1.908676697219879e-05, + "loss": 0.8495, + "step": 1821 + }, + { + "epoch": 0.16314287313224018, + "grad_norm": 1.0515644618841369, + "learning_rate": 1.908555571811059e-05, + "loss": 0.8867, + "step": 1822 + }, + { + "epoch": 0.16323241367731825, + "grad_norm": 1.0059108139988986, + "learning_rate": 1.908434369977505e-05, + "loss": 0.9524, + "step": 1823 + }, + { + "epoch": 0.16332195422239631, + "grad_norm": 0.854045888912817, + "learning_rate": 1.908313091729412e-05, + "loss": 0.8607, + "step": 1824 + }, + { + "epoch": 0.1634114947674744, + "grad_norm": 0.9739556033902297, + "learning_rate": 1.908191737076982e-05, + "loss": 0.865, + "step": 1825 + }, + { + "epoch": 0.16350103531255247, + "grad_norm": 1.0662952962059198, + "learning_rate": 1.908070306030422e-05, + "loss": 0.9309, + "step": 1826 + }, + { + "epoch": 0.16359057585763054, + "grad_norm": 1.0493589792741702, + "learning_rate": 1.9079487985999473e-05, + "loss": 0.9374, + "step": 1827 + }, + { + "epoch": 0.1636801164027086, + "grad_norm": 0.9216282710286423, + "learning_rate": 1.9078272147957784e-05, + "loss": 0.8839, + "step": 1828 + }, + { + "epoch": 0.16376965694778667, + "grad_norm": 1.0301010288935466, + "learning_rate": 1.9077055546281425e-05, + "loss": 0.9774, + "step": 1829 + }, + { + "epoch": 0.16385919749286473, + "grad_norm": 1.00434117354553, + "learning_rate": 1.9075838181072732e-05, + "loss": 0.9358, + "step": 1830 + }, + { + "epoch": 0.1639487380379428, + "grad_norm": 0.9171998718000218, + "learning_rate": 1.9074620052434108e-05, + "loss": 0.8609, + "step": 1831 + }, + { + "epoch": 0.16403827858302086, + "grad_norm": 1.1183297616882255, + "learning_rate": 1.9073401160468016e-05, + "loss": 0.8675, + "step": 1832 + }, + { + "epoch": 0.16412781912809893, + "grad_norm": 0.9090755397112024, + "learning_rate": 1.9072181505276988e-05, + "loss": 0.9263, + "step": 1833 + }, + { + "epoch": 0.16421735967317702, + "grad_norm": 1.0546326090785478, + "learning_rate": 1.907096108696361e-05, + "loss": 0.8868, + "step": 1834 + }, + { + "epoch": 0.1643069002182551, + "grad_norm": 1.0339442292007854, + "learning_rate": 1.9069739905630552e-05, + "loss": 0.9539, + "step": 1835 + }, + { + "epoch": 0.16439644076333315, + "grad_norm": 1.0192500250164835, + "learning_rate": 1.9068517961380523e-05, + "loss": 0.8636, + "step": 1836 + }, + { + "epoch": 0.16448598130841122, + "grad_norm": 0.9635828736683073, + "learning_rate": 1.9067295254316315e-05, + "loss": 0.9346, + "step": 1837 + }, + { + "epoch": 0.16457552185348928, + "grad_norm": 1.0662192135547275, + "learning_rate": 1.9066071784540782e-05, + "loss": 0.8873, + "step": 1838 + }, + { + "epoch": 0.16466506239856735, + "grad_norm": 0.9329442247300944, + "learning_rate": 1.9064847552156834e-05, + "loss": 0.9159, + "step": 1839 + }, + { + "epoch": 0.1647546029436454, + "grad_norm": 0.9122349557623348, + "learning_rate": 1.9063622557267443e-05, + "loss": 0.8913, + "step": 1840 + }, + { + "epoch": 0.16484414348872348, + "grad_norm": 1.0200133268687577, + "learning_rate": 1.9062396799975667e-05, + "loss": 0.8579, + "step": 1841 + }, + { + "epoch": 0.16493368403380154, + "grad_norm": 1.0098398098752235, + "learning_rate": 1.9061170280384596e-05, + "loss": 0.9314, + "step": 1842 + }, + { + "epoch": 0.16502322457887963, + "grad_norm": 0.9749561796647002, + "learning_rate": 1.9059942998597413e-05, + "loss": 0.8652, + "step": 1843 + }, + { + "epoch": 0.1651127651239577, + "grad_norm": 0.9331007820092048, + "learning_rate": 1.9058714954717346e-05, + "loss": 0.8722, + "step": 1844 + }, + { + "epoch": 0.16520230566903576, + "grad_norm": 1.113777846520895, + "learning_rate": 1.90574861488477e-05, + "loss": 0.8882, + "step": 1845 + }, + { + "epoch": 0.16529184621411383, + "grad_norm": 1.184097028983729, + "learning_rate": 1.9056256581091834e-05, + "loss": 0.8463, + "step": 1846 + }, + { + "epoch": 0.1653813867591919, + "grad_norm": 1.0008001927521994, + "learning_rate": 1.9055026251553174e-05, + "loss": 0.9151, + "step": 1847 + }, + { + "epoch": 0.16547092730426996, + "grad_norm": 0.927853458445148, + "learning_rate": 1.9053795160335216e-05, + "loss": 0.8496, + "step": 1848 + }, + { + "epoch": 0.16556046784934803, + "grad_norm": 1.0154484889116662, + "learning_rate": 1.9052563307541512e-05, + "loss": 0.8845, + "step": 1849 + }, + { + "epoch": 0.1656500083944261, + "grad_norm": 1.058028333104348, + "learning_rate": 1.905133069327568e-05, + "loss": 0.9207, + "step": 1850 + }, + { + "epoch": 0.16573954893950416, + "grad_norm": 0.976645577135433, + "learning_rate": 1.905009731764141e-05, + "loss": 0.8764, + "step": 1851 + }, + { + "epoch": 0.16582908948458225, + "grad_norm": 1.0565341202946095, + "learning_rate": 1.904886318074244e-05, + "loss": 0.8988, + "step": 1852 + }, + { + "epoch": 0.1659186300296603, + "grad_norm": 1.3198924133718994, + "learning_rate": 1.904762828268259e-05, + "loss": 0.9048, + "step": 1853 + }, + { + "epoch": 0.16600817057473838, + "grad_norm": 0.9766860267319637, + "learning_rate": 1.904639262356573e-05, + "loss": 0.854, + "step": 1854 + }, + { + "epoch": 0.16609771111981644, + "grad_norm": 0.928804940651181, + "learning_rate": 1.9045156203495808e-05, + "loss": 0.8896, + "step": 1855 + }, + { + "epoch": 0.1661872516648945, + "grad_norm": 1.0057200060113751, + "learning_rate": 1.9043919022576817e-05, + "loss": 0.9238, + "step": 1856 + }, + { + "epoch": 0.16627679220997257, + "grad_norm": 0.9129435286379892, + "learning_rate": 1.9042681080912827e-05, + "loss": 0.8703, + "step": 1857 + }, + { + "epoch": 0.16636633275505064, + "grad_norm": 0.9658177919701865, + "learning_rate": 1.9041442378607975e-05, + "loss": 0.9285, + "step": 1858 + }, + { + "epoch": 0.1664558733001287, + "grad_norm": 1.1002497839677383, + "learning_rate": 1.9040202915766452e-05, + "loss": 0.8653, + "step": 1859 + }, + { + "epoch": 0.16654541384520677, + "grad_norm": 0.9560338476802797, + "learning_rate": 1.9038962692492522e-05, + "loss": 0.9056, + "step": 1860 + }, + { + "epoch": 0.16663495439028486, + "grad_norm": 0.911403953562522, + "learning_rate": 1.9037721708890503e-05, + "loss": 0.8939, + "step": 1861 + }, + { + "epoch": 0.16672449493536293, + "grad_norm": 1.0665333525466567, + "learning_rate": 1.903647996506479e-05, + "loss": 0.891, + "step": 1862 + }, + { + "epoch": 0.166814035480441, + "grad_norm": 0.9321967811423212, + "learning_rate": 1.9035237461119822e-05, + "loss": 0.8011, + "step": 1863 + }, + { + "epoch": 0.16690357602551906, + "grad_norm": 0.9997822119708683, + "learning_rate": 1.9033994197160127e-05, + "loss": 0.9351, + "step": 1864 + }, + { + "epoch": 0.16699311657059712, + "grad_norm": 1.1031609487340701, + "learning_rate": 1.9032750173290274e-05, + "loss": 0.9047, + "step": 1865 + }, + { + "epoch": 0.1670826571156752, + "grad_norm": 1.0442359335015263, + "learning_rate": 1.9031505389614918e-05, + "loss": 0.9414, + "step": 1866 + }, + { + "epoch": 0.16717219766075325, + "grad_norm": 1.0181507344969802, + "learning_rate": 1.9030259846238753e-05, + "loss": 0.902, + "step": 1867 + }, + { + "epoch": 0.16726173820583132, + "grad_norm": 0.9440914233838309, + "learning_rate": 1.9029013543266562e-05, + "loss": 0.9386, + "step": 1868 + }, + { + "epoch": 0.16735127875090938, + "grad_norm": 1.046613697917735, + "learning_rate": 1.9027766480803173e-05, + "loss": 0.953, + "step": 1869 + }, + { + "epoch": 0.16744081929598748, + "grad_norm": 1.092403235632166, + "learning_rate": 1.9026518658953487e-05, + "loss": 0.8567, + "step": 1870 + }, + { + "epoch": 0.16753035984106554, + "grad_norm": 0.9469343959822131, + "learning_rate": 1.9025270077822467e-05, + "loss": 0.8834, + "step": 1871 + }, + { + "epoch": 0.1676199003861436, + "grad_norm": 0.9201625504887306, + "learning_rate": 1.9024020737515135e-05, + "loss": 0.9375, + "step": 1872 + }, + { + "epoch": 0.16770944093122167, + "grad_norm": 0.9710181610723885, + "learning_rate": 1.902277063813659e-05, + "loss": 0.9332, + "step": 1873 + }, + { + "epoch": 0.16779898147629974, + "grad_norm": 1.0348670443098078, + "learning_rate": 1.9021519779791978e-05, + "loss": 0.8799, + "step": 1874 + }, + { + "epoch": 0.1678885220213778, + "grad_norm": 1.0588430587991342, + "learning_rate": 1.902026816258652e-05, + "loss": 0.873, + "step": 1875 + }, + { + "epoch": 0.16797806256645587, + "grad_norm": 0.9417594834625934, + "learning_rate": 1.90190157866255e-05, + "loss": 0.8742, + "step": 1876 + }, + { + "epoch": 0.16806760311153393, + "grad_norm": 0.8651762928670946, + "learning_rate": 1.9017762652014262e-05, + "loss": 0.8416, + "step": 1877 + }, + { + "epoch": 0.168157143656612, + "grad_norm": 1.0421629194921471, + "learning_rate": 1.901650875885822e-05, + "loss": 0.8654, + "step": 1878 + }, + { + "epoch": 0.1682466842016901, + "grad_norm": 0.8973432707429861, + "learning_rate": 1.9015254107262836e-05, + "loss": 0.882, + "step": 1879 + }, + { + "epoch": 0.16833622474676815, + "grad_norm": 1.0250087707742168, + "learning_rate": 1.901399869733366e-05, + "loss": 0.9123, + "step": 1880 + }, + { + "epoch": 0.16842576529184622, + "grad_norm": 0.9608320290386494, + "learning_rate": 1.901274252917629e-05, + "loss": 0.9088, + "step": 1881 + }, + { + "epoch": 0.16851530583692428, + "grad_norm": 5.517191370791696, + "learning_rate": 1.901148560289638e-05, + "loss": 0.8773, + "step": 1882 + }, + { + "epoch": 0.16860484638200235, + "grad_norm": 0.9464700512641965, + "learning_rate": 1.901022791859967e-05, + "loss": 0.8622, + "step": 1883 + }, + { + "epoch": 0.16869438692708041, + "grad_norm": 1.0715224470045512, + "learning_rate": 1.9008969476391952e-05, + "loss": 0.8893, + "step": 1884 + }, + { + "epoch": 0.16878392747215848, + "grad_norm": 0.8770921005961276, + "learning_rate": 1.9007710276379077e-05, + "loss": 0.879, + "step": 1885 + }, + { + "epoch": 0.16887346801723654, + "grad_norm": 0.9446411445367439, + "learning_rate": 1.9006450318666966e-05, + "loss": 0.8671, + "step": 1886 + }, + { + "epoch": 0.1689630085623146, + "grad_norm": 0.877136694507198, + "learning_rate": 1.9005189603361605e-05, + "loss": 0.9676, + "step": 1887 + }, + { + "epoch": 0.1690525491073927, + "grad_norm": 0.9341515732258432, + "learning_rate": 1.900392813056904e-05, + "loss": 0.8887, + "step": 1888 + }, + { + "epoch": 0.16914208965247077, + "grad_norm": 0.9627749431945741, + "learning_rate": 1.900266590039538e-05, + "loss": 0.872, + "step": 1889 + }, + { + "epoch": 0.16923163019754883, + "grad_norm": 1.0706570342788464, + "learning_rate": 1.9001402912946804e-05, + "loss": 0.9331, + "step": 1890 + }, + { + "epoch": 0.1693211707426269, + "grad_norm": 1.076337435271884, + "learning_rate": 1.9000139168329548e-05, + "loss": 0.8734, + "step": 1891 + }, + { + "epoch": 0.16941071128770496, + "grad_norm": 0.9481358249743946, + "learning_rate": 1.8998874666649913e-05, + "loss": 0.9072, + "step": 1892 + }, + { + "epoch": 0.16950025183278303, + "grad_norm": 1.236713736962692, + "learning_rate": 1.8997609408014263e-05, + "loss": 0.9773, + "step": 1893 + }, + { + "epoch": 0.1695897923778611, + "grad_norm": 1.0123854532286096, + "learning_rate": 1.8996343392529034e-05, + "loss": 0.9141, + "step": 1894 + }, + { + "epoch": 0.16967933292293916, + "grad_norm": 1.0006360089868338, + "learning_rate": 1.8995076620300714e-05, + "loss": 0.8859, + "step": 1895 + }, + { + "epoch": 0.16976887346801722, + "grad_norm": 0.9121666268264655, + "learning_rate": 1.899380909143586e-05, + "loss": 0.8843, + "step": 1896 + }, + { + "epoch": 0.16985841401309532, + "grad_norm": 0.9341349126299177, + "learning_rate": 1.8992540806041097e-05, + "loss": 0.932, + "step": 1897 + }, + { + "epoch": 0.16994795455817338, + "grad_norm": 0.9769853749130047, + "learning_rate": 1.89912717642231e-05, + "loss": 0.9209, + "step": 1898 + }, + { + "epoch": 0.17003749510325145, + "grad_norm": 1.0421573682821756, + "learning_rate": 1.8990001966088628e-05, + "loss": 0.928, + "step": 1899 + }, + { + "epoch": 0.1701270356483295, + "grad_norm": 0.9105995475918409, + "learning_rate": 1.8988731411744482e-05, + "loss": 0.9085, + "step": 1900 + }, + { + "epoch": 0.17021657619340758, + "grad_norm": 1.0099341283769252, + "learning_rate": 1.8987460101297542e-05, + "loss": 0.8693, + "step": 1901 + }, + { + "epoch": 0.17030611673848564, + "grad_norm": 0.9516414015811238, + "learning_rate": 1.8986188034854744e-05, + "loss": 0.8568, + "step": 1902 + }, + { + "epoch": 0.1703956572835637, + "grad_norm": 0.9041235781042996, + "learning_rate": 1.8984915212523093e-05, + "loss": 0.8967, + "step": 1903 + }, + { + "epoch": 0.17048519782864177, + "grad_norm": 0.9248095843562465, + "learning_rate": 1.8983641634409657e-05, + "loss": 0.8873, + "step": 1904 + }, + { + "epoch": 0.17057473837371984, + "grad_norm": 1.010821377772331, + "learning_rate": 1.898236730062156e-05, + "loss": 0.8491, + "step": 1905 + }, + { + "epoch": 0.17066427891879793, + "grad_norm": 0.9792816403181784, + "learning_rate": 1.8981092211265994e-05, + "loss": 0.8625, + "step": 1906 + }, + { + "epoch": 0.170753819463876, + "grad_norm": 0.8933261309732216, + "learning_rate": 1.897981636645022e-05, + "loss": 0.9004, + "step": 1907 + }, + { + "epoch": 0.17084336000895406, + "grad_norm": 1.0312355734756795, + "learning_rate": 1.8978539766281557e-05, + "loss": 0.8761, + "step": 1908 + }, + { + "epoch": 0.17093290055403212, + "grad_norm": 0.8857776422305738, + "learning_rate": 1.8977262410867383e-05, + "loss": 0.9252, + "step": 1909 + }, + { + "epoch": 0.1710224410991102, + "grad_norm": 0.9220160744778109, + "learning_rate": 1.8975984300315154e-05, + "loss": 0.8592, + "step": 1910 + }, + { + "epoch": 0.17111198164418825, + "grad_norm": 1.0660569245809242, + "learning_rate": 1.8974705434732376e-05, + "loss": 0.8756, + "step": 1911 + }, + { + "epoch": 0.17120152218926632, + "grad_norm": 1.2439466997590156, + "learning_rate": 1.8973425814226618e-05, + "loss": 0.8799, + "step": 1912 + }, + { + "epoch": 0.17129106273434438, + "grad_norm": 0.9680548658929549, + "learning_rate": 1.897214543890552e-05, + "loss": 0.8713, + "step": 1913 + }, + { + "epoch": 0.17138060327942245, + "grad_norm": 0.9218203896462943, + "learning_rate": 1.897086430887679e-05, + "loss": 0.8642, + "step": 1914 + }, + { + "epoch": 0.17147014382450054, + "grad_norm": 0.8664864799190866, + "learning_rate": 1.896958242424819e-05, + "loss": 0.8662, + "step": 1915 + }, + { + "epoch": 0.1715596843695786, + "grad_norm": 1.0732704995522417, + "learning_rate": 1.8968299785127544e-05, + "loss": 0.9084, + "step": 1916 + }, + { + "epoch": 0.17164922491465667, + "grad_norm": 1.0888010343701422, + "learning_rate": 1.8967016391622746e-05, + "loss": 0.8602, + "step": 1917 + }, + { + "epoch": 0.17173876545973474, + "grad_norm": 0.9788651414988516, + "learning_rate": 1.896573224384175e-05, + "loss": 0.9244, + "step": 1918 + }, + { + "epoch": 0.1718283060048128, + "grad_norm": 0.8998033529415681, + "learning_rate": 1.896444734189257e-05, + "loss": 0.9174, + "step": 1919 + }, + { + "epoch": 0.17191784654989087, + "grad_norm": 0.98450095096618, + "learning_rate": 1.8963161685883294e-05, + "loss": 0.8778, + "step": 1920 + }, + { + "epoch": 0.17200738709496893, + "grad_norm": 1.0300079714532986, + "learning_rate": 1.8961875275922067e-05, + "loss": 0.8764, + "step": 1921 + }, + { + "epoch": 0.172096927640047, + "grad_norm": 1.025865030401448, + "learning_rate": 1.8960588112117096e-05, + "loss": 0.8795, + "step": 1922 + }, + { + "epoch": 0.17218646818512506, + "grad_norm": 0.9176159898764925, + "learning_rate": 1.8959300194576654e-05, + "loss": 0.8309, + "step": 1923 + }, + { + "epoch": 0.17227600873020316, + "grad_norm": 0.9357280883796574, + "learning_rate": 1.895801152340907e-05, + "loss": 0.8989, + "step": 1924 + }, + { + "epoch": 0.17236554927528122, + "grad_norm": 0.9164941714889159, + "learning_rate": 1.895672209872275e-05, + "loss": 0.8966, + "step": 1925 + }, + { + "epoch": 0.1724550898203593, + "grad_norm": 1.0536675004756033, + "learning_rate": 1.8955431920626158e-05, + "loss": 0.8675, + "step": 1926 + }, + { + "epoch": 0.17254463036543735, + "grad_norm": 0.9925928295973078, + "learning_rate": 1.8954140989227815e-05, + "loss": 0.8649, + "step": 1927 + }, + { + "epoch": 0.17263417091051542, + "grad_norm": 1.0723251544668253, + "learning_rate": 1.895284930463631e-05, + "loss": 0.9037, + "step": 1928 + }, + { + "epoch": 0.17272371145559348, + "grad_norm": 0.9886715009610579, + "learning_rate": 1.8951556866960295e-05, + "loss": 0.935, + "step": 1929 + }, + { + "epoch": 0.17281325200067155, + "grad_norm": 1.1528987428472375, + "learning_rate": 1.8950263676308486e-05, + "loss": 0.9257, + "step": 1930 + }, + { + "epoch": 0.1729027925457496, + "grad_norm": 1.1746387736076054, + "learning_rate": 1.8948969732789666e-05, + "loss": 0.8688, + "step": 1931 + }, + { + "epoch": 0.17299233309082768, + "grad_norm": 0.959339659138055, + "learning_rate": 1.8947675036512673e-05, + "loss": 0.9206, + "step": 1932 + }, + { + "epoch": 0.17308187363590577, + "grad_norm": 0.9474846603977088, + "learning_rate": 1.894637958758641e-05, + "loss": 0.9444, + "step": 1933 + }, + { + "epoch": 0.17317141418098383, + "grad_norm": 0.9375627615846007, + "learning_rate": 1.8945083386119853e-05, + "loss": 0.9152, + "step": 1934 + }, + { + "epoch": 0.1732609547260619, + "grad_norm": 0.9296436663776422, + "learning_rate": 1.8943786432222032e-05, + "loss": 0.8914, + "step": 1935 + }, + { + "epoch": 0.17335049527113996, + "grad_norm": 1.2362422162629454, + "learning_rate": 1.894248872600204e-05, + "loss": 0.8218, + "step": 1936 + }, + { + "epoch": 0.17344003581621803, + "grad_norm": 1.0040378164547326, + "learning_rate": 1.8941190267569038e-05, + "loss": 0.8677, + "step": 1937 + }, + { + "epoch": 0.1735295763612961, + "grad_norm": 1.1729720800843382, + "learning_rate": 1.893989105703225e-05, + "loss": 0.8739, + "step": 1938 + }, + { + "epoch": 0.17361911690637416, + "grad_norm": 0.9567295614841844, + "learning_rate": 1.8938591094500953e-05, + "loss": 0.8262, + "step": 1939 + }, + { + "epoch": 0.17370865745145223, + "grad_norm": 0.8783872769783507, + "learning_rate": 1.8937290380084502e-05, + "loss": 0.9122, + "step": 1940 + }, + { + "epoch": 0.1737981979965303, + "grad_norm": 0.9887254332103576, + "learning_rate": 1.8935988913892314e-05, + "loss": 0.8431, + "step": 1941 + }, + { + "epoch": 0.17388773854160838, + "grad_norm": 0.946956199177709, + "learning_rate": 1.8934686696033853e-05, + "loss": 0.93, + "step": 1942 + }, + { + "epoch": 0.17397727908668645, + "grad_norm": 0.9526948957954328, + "learning_rate": 1.8933383726618663e-05, + "loss": 0.9021, + "step": 1943 + }, + { + "epoch": 0.1740668196317645, + "grad_norm": 0.9566142561413987, + "learning_rate": 1.8932080005756348e-05, + "loss": 0.8864, + "step": 1944 + }, + { + "epoch": 0.17415636017684258, + "grad_norm": 1.052273589932486, + "learning_rate": 1.893077553355657e-05, + "loss": 0.8982, + "step": 1945 + }, + { + "epoch": 0.17424590072192064, + "grad_norm": 1.1067352925842118, + "learning_rate": 1.8929470310129052e-05, + "loss": 0.8844, + "step": 1946 + }, + { + "epoch": 0.1743354412669987, + "grad_norm": 1.2879206912230712, + "learning_rate": 1.8928164335583596e-05, + "loss": 0.9149, + "step": 1947 + }, + { + "epoch": 0.17442498181207677, + "grad_norm": 0.9687815595795757, + "learning_rate": 1.8926857610030044e-05, + "loss": 0.8803, + "step": 1948 + }, + { + "epoch": 0.17451452235715484, + "grad_norm": 1.0532763762915853, + "learning_rate": 1.8925550133578326e-05, + "loss": 0.93, + "step": 1949 + }, + { + "epoch": 0.1746040629022329, + "grad_norm": 0.9989442239771669, + "learning_rate": 1.8924241906338413e-05, + "loss": 0.8685, + "step": 1950 + }, + { + "epoch": 0.174693603447311, + "grad_norm": 1.0186924745351928, + "learning_rate": 1.8922932928420354e-05, + "loss": 0.8627, + "step": 1951 + }, + { + "epoch": 0.17478314399238906, + "grad_norm": 0.9746583948679277, + "learning_rate": 1.8921623199934255e-05, + "loss": 0.8504, + "step": 1952 + }, + { + "epoch": 0.17487268453746713, + "grad_norm": 1.0184352792648206, + "learning_rate": 1.8920312720990283e-05, + "loss": 0.889, + "step": 1953 + }, + { + "epoch": 0.1749622250825452, + "grad_norm": 1.1372382777340262, + "learning_rate": 1.8919001491698674e-05, + "loss": 0.8855, + "step": 1954 + }, + { + "epoch": 0.17505176562762326, + "grad_norm": 1.0043620641668143, + "learning_rate": 1.8917689512169724e-05, + "loss": 0.875, + "step": 1955 + }, + { + "epoch": 0.17514130617270132, + "grad_norm": 0.8774619443162723, + "learning_rate": 1.8916376782513792e-05, + "loss": 0.8643, + "step": 1956 + }, + { + "epoch": 0.1752308467177794, + "grad_norm": 0.9234019514091268, + "learning_rate": 1.8915063302841302e-05, + "loss": 0.9038, + "step": 1957 + }, + { + "epoch": 0.17532038726285745, + "grad_norm": 1.02240273572741, + "learning_rate": 1.8913749073262738e-05, + "loss": 0.9436, + "step": 1958 + }, + { + "epoch": 0.17540992780793552, + "grad_norm": 0.9910022333390955, + "learning_rate": 1.891243409388865e-05, + "loss": 0.933, + "step": 1959 + }, + { + "epoch": 0.1754994683530136, + "grad_norm": 1.2008713326800773, + "learning_rate": 1.891111836482965e-05, + "loss": 0.9051, + "step": 1960 + }, + { + "epoch": 0.17558900889809168, + "grad_norm": 1.0097053014828616, + "learning_rate": 1.890980188619641e-05, + "loss": 0.838, + "step": 1961 + }, + { + "epoch": 0.17567854944316974, + "grad_norm": 0.8941981883511267, + "learning_rate": 1.890848465809967e-05, + "loss": 0.8881, + "step": 1962 + }, + { + "epoch": 0.1757680899882478, + "grad_norm": 0.9372976042199797, + "learning_rate": 1.890716668065023e-05, + "loss": 0.8245, + "step": 1963 + }, + { + "epoch": 0.17585763053332587, + "grad_norm": 1.1984549365445827, + "learning_rate": 1.8905847953958954e-05, + "loss": 0.9745, + "step": 1964 + }, + { + "epoch": 0.17594717107840394, + "grad_norm": 0.9615371902591314, + "learning_rate": 1.890452847813677e-05, + "loss": 0.9076, + "step": 1965 + }, + { + "epoch": 0.176036711623482, + "grad_norm": 1.0179971658018399, + "learning_rate": 1.8903208253294667e-05, + "loss": 0.9141, + "step": 1966 + }, + { + "epoch": 0.17612625216856007, + "grad_norm": 1.1467486860283234, + "learning_rate": 1.89018872795437e-05, + "loss": 0.8949, + "step": 1967 + }, + { + "epoch": 0.17621579271363813, + "grad_norm": 0.8495222638424595, + "learning_rate": 1.8900565556994986e-05, + "loss": 0.8654, + "step": 1968 + }, + { + "epoch": 0.17630533325871622, + "grad_norm": 1.0674984878548497, + "learning_rate": 1.88992430857597e-05, + "loss": 0.8856, + "step": 1969 + }, + { + "epoch": 0.1763948738037943, + "grad_norm": 1.0298993416395037, + "learning_rate": 1.8897919865949083e-05, + "loss": 0.8239, + "step": 1970 + }, + { + "epoch": 0.17648441434887235, + "grad_norm": 0.8821067762766143, + "learning_rate": 1.8896595897674446e-05, + "loss": 0.9071, + "step": 1971 + }, + { + "epoch": 0.17657395489395042, + "grad_norm": 0.9679190447891308, + "learning_rate": 1.8895271181047152e-05, + "loss": 0.9084, + "step": 1972 + }, + { + "epoch": 0.17666349543902848, + "grad_norm": 0.9875707276233355, + "learning_rate": 1.889394571617863e-05, + "loss": 0.8196, + "step": 1973 + }, + { + "epoch": 0.17675303598410655, + "grad_norm": 0.9531678573190864, + "learning_rate": 1.889261950318038e-05, + "loss": 0.8799, + "step": 1974 + }, + { + "epoch": 0.17684257652918461, + "grad_norm": 0.9211076513396957, + "learning_rate": 1.8891292542163958e-05, + "loss": 0.8719, + "step": 1975 + }, + { + "epoch": 0.17693211707426268, + "grad_norm": 1.0427539320226746, + "learning_rate": 1.8889964833240983e-05, + "loss": 0.8605, + "step": 1976 + }, + { + "epoch": 0.17702165761934074, + "grad_norm": 0.975239870947061, + "learning_rate": 1.8888636376523132e-05, + "loss": 0.8577, + "step": 1977 + }, + { + "epoch": 0.17711119816441884, + "grad_norm": 1.1353075959896342, + "learning_rate": 1.8887307172122154e-05, + "loss": 0.9429, + "step": 1978 + }, + { + "epoch": 0.1772007387094969, + "grad_norm": 0.9586216357570077, + "learning_rate": 1.888597722014986e-05, + "loss": 0.934, + "step": 1979 + }, + { + "epoch": 0.17729027925457497, + "grad_norm": 0.9955488744328173, + "learning_rate": 1.8884646520718117e-05, + "loss": 0.9025, + "step": 1980 + }, + { + "epoch": 0.17737981979965303, + "grad_norm": 0.9295597559787909, + "learning_rate": 1.888331507393886e-05, + "loss": 0.9435, + "step": 1981 + }, + { + "epoch": 0.1774693603447311, + "grad_norm": 1.080657280996886, + "learning_rate": 1.888198287992409e-05, + "loss": 0.877, + "step": 1982 + }, + { + "epoch": 0.17755890088980916, + "grad_norm": 0.9610678715193095, + "learning_rate": 1.888064993878586e-05, + "loss": 0.8843, + "step": 1983 + }, + { + "epoch": 0.17764844143488723, + "grad_norm": 0.9993026679773763, + "learning_rate": 1.8879316250636305e-05, + "loss": 0.899, + "step": 1984 + }, + { + "epoch": 0.1777379819799653, + "grad_norm": 1.044155063318996, + "learning_rate": 1.8877981815587594e-05, + "loss": 0.8823, + "step": 1985 + }, + { + "epoch": 0.17782752252504336, + "grad_norm": 0.9108182858953897, + "learning_rate": 1.8876646633751986e-05, + "loss": 0.8294, + "step": 1986 + }, + { + "epoch": 0.17791706307012145, + "grad_norm": 0.9715817475699078, + "learning_rate": 1.8875310705241793e-05, + "loss": 0.8981, + "step": 1987 + }, + { + "epoch": 0.17800660361519952, + "grad_norm": 0.9917234832365002, + "learning_rate": 1.887397403016938e-05, + "loss": 0.8882, + "step": 1988 + }, + { + "epoch": 0.17809614416027758, + "grad_norm": 1.1369931466621894, + "learning_rate": 1.887263660864719e-05, + "loss": 0.9686, + "step": 1989 + }, + { + "epoch": 0.17818568470535565, + "grad_norm": 0.9635371142542071, + "learning_rate": 1.8871298440787724e-05, + "loss": 0.9622, + "step": 1990 + }, + { + "epoch": 0.1782752252504337, + "grad_norm": 0.9791321740034132, + "learning_rate": 1.886995952670354e-05, + "loss": 0.9325, + "step": 1991 + }, + { + "epoch": 0.17836476579551178, + "grad_norm": 0.9597079835037503, + "learning_rate": 1.8868619866507268e-05, + "loss": 0.8883, + "step": 1992 + }, + { + "epoch": 0.17845430634058984, + "grad_norm": 1.0297552557669538, + "learning_rate": 1.886727946031159e-05, + "loss": 0.8132, + "step": 1993 + }, + { + "epoch": 0.1785438468856679, + "grad_norm": 0.9762845924503495, + "learning_rate": 1.886593830822926e-05, + "loss": 0.8892, + "step": 1994 + }, + { + "epoch": 0.17863338743074597, + "grad_norm": 1.131954070432886, + "learning_rate": 1.8864596410373092e-05, + "loss": 0.8654, + "step": 1995 + }, + { + "epoch": 0.17872292797582406, + "grad_norm": 1.0182147426726, + "learning_rate": 1.8863253766855964e-05, + "loss": 0.888, + "step": 1996 + }, + { + "epoch": 0.17881246852090213, + "grad_norm": 1.004129999434742, + "learning_rate": 1.8861910377790807e-05, + "loss": 0.8764, + "step": 1997 + }, + { + "epoch": 0.1789020090659802, + "grad_norm": 0.9796451968213635, + "learning_rate": 1.886056624329063e-05, + "loss": 0.8406, + "step": 1998 + }, + { + "epoch": 0.17899154961105826, + "grad_norm": 1.0282317316256078, + "learning_rate": 1.8859221363468493e-05, + "loss": 0.8934, + "step": 1999 + }, + { + "epoch": 0.17908109015613632, + "grad_norm": 0.942954338174738, + "learning_rate": 1.8857875738437526e-05, + "loss": 0.899, + "step": 2000 + }, + { + "epoch": 0.1791706307012144, + "grad_norm": 1.0203033012252298, + "learning_rate": 1.8856529368310916e-05, + "loss": 0.8698, + "step": 2001 + }, + { + "epoch": 0.17926017124629245, + "grad_norm": 0.9989036434597025, + "learning_rate": 1.885518225320192e-05, + "loss": 0.8436, + "step": 2002 + }, + { + "epoch": 0.17934971179137052, + "grad_norm": 1.0599084585580012, + "learning_rate": 1.8853834393223843e-05, + "loss": 0.8663, + "step": 2003 + }, + { + "epoch": 0.17943925233644858, + "grad_norm": 1.037842671893135, + "learning_rate": 1.885248578849007e-05, + "loss": 0.912, + "step": 2004 + }, + { + "epoch": 0.17952879288152668, + "grad_norm": 1.0863653806701572, + "learning_rate": 1.8851136439114045e-05, + "loss": 0.9749, + "step": 2005 + }, + { + "epoch": 0.17961833342660474, + "grad_norm": 0.9655098037867771, + "learning_rate": 1.884978634520926e-05, + "loss": 0.9255, + "step": 2006 + }, + { + "epoch": 0.1797078739716828, + "grad_norm": 1.2446128238837677, + "learning_rate": 1.884843550688929e-05, + "loss": 0.9274, + "step": 2007 + }, + { + "epoch": 0.17979741451676087, + "grad_norm": 6.753738439110338, + "learning_rate": 1.884708392426776e-05, + "loss": 0.9271, + "step": 2008 + }, + { + "epoch": 0.17988695506183894, + "grad_norm": 1.0231375711950297, + "learning_rate": 1.884573159745836e-05, + "loss": 0.8739, + "step": 2009 + }, + { + "epoch": 0.179976495606917, + "grad_norm": 0.9793432448990642, + "learning_rate": 1.884437852657484e-05, + "loss": 0.8788, + "step": 2010 + }, + { + "epoch": 0.18006603615199507, + "grad_norm": 1.200031794811684, + "learning_rate": 1.8843024711731023e-05, + "loss": 0.8713, + "step": 2011 + }, + { + "epoch": 0.18015557669707313, + "grad_norm": 1.1199835683931725, + "learning_rate": 1.8841670153040785e-05, + "loss": 0.9151, + "step": 2012 + }, + { + "epoch": 0.1802451172421512, + "grad_norm": 1.053122099573849, + "learning_rate": 1.8840314850618063e-05, + "loss": 0.8443, + "step": 2013 + }, + { + "epoch": 0.1803346577872293, + "grad_norm": 0.9759706156010873, + "learning_rate": 1.8838958804576866e-05, + "loss": 0.8576, + "step": 2014 + }, + { + "epoch": 0.18042419833230736, + "grad_norm": 0.9065741181637583, + "learning_rate": 1.8837602015031256e-05, + "loss": 0.8665, + "step": 2015 + }, + { + "epoch": 0.18051373887738542, + "grad_norm": 0.9680444180198995, + "learning_rate": 1.8836244482095366e-05, + "loss": 0.9128, + "step": 2016 + }, + { + "epoch": 0.1806032794224635, + "grad_norm": 0.9433064676561327, + "learning_rate": 1.8834886205883386e-05, + "loss": 0.8972, + "step": 2017 + }, + { + "epoch": 0.18069281996754155, + "grad_norm": 0.950258197124031, + "learning_rate": 1.8833527186509566e-05, + "loss": 0.9339, + "step": 2018 + }, + { + "epoch": 0.18078236051261962, + "grad_norm": 0.935048411436469, + "learning_rate": 1.8832167424088226e-05, + "loss": 0.8173, + "step": 2019 + }, + { + "epoch": 0.18087190105769768, + "grad_norm": 1.0262057360883636, + "learning_rate": 1.8830806918733743e-05, + "loss": 0.8968, + "step": 2020 + }, + { + "epoch": 0.18096144160277575, + "grad_norm": 0.9350930834619838, + "learning_rate": 1.8829445670560557e-05, + "loss": 0.8876, + "step": 2021 + }, + { + "epoch": 0.1810509821478538, + "grad_norm": 1.0589787654195535, + "learning_rate": 1.8828083679683174e-05, + "loss": 0.8945, + "step": 2022 + }, + { + "epoch": 0.1811405226929319, + "grad_norm": 0.8714957365065938, + "learning_rate": 1.8826720946216164e-05, + "loss": 0.8986, + "step": 2023 + }, + { + "epoch": 0.18123006323800997, + "grad_norm": 0.966588582425351, + "learning_rate": 1.882535747027415e-05, + "loss": 0.8878, + "step": 2024 + }, + { + "epoch": 0.18131960378308803, + "grad_norm": 1.0022062829519047, + "learning_rate": 1.8823993251971823e-05, + "loss": 0.8703, + "step": 2025 + }, + { + "epoch": 0.1814091443281661, + "grad_norm": 0.8364996371098609, + "learning_rate": 1.882262829142394e-05, + "loss": 0.8267, + "step": 2026 + }, + { + "epoch": 0.18149868487324416, + "grad_norm": 0.9858773258946832, + "learning_rate": 1.882126258874532e-05, + "loss": 0.9155, + "step": 2027 + }, + { + "epoch": 0.18158822541832223, + "grad_norm": 1.1291844532575677, + "learning_rate": 1.881989614405083e-05, + "loss": 0.9264, + "step": 2028 + }, + { + "epoch": 0.1816777659634003, + "grad_norm": 0.9480222985302227, + "learning_rate": 1.8818528957455418e-05, + "loss": 0.8741, + "step": 2029 + }, + { + "epoch": 0.18176730650847836, + "grad_norm": 1.0501255791222808, + "learning_rate": 1.881716102907409e-05, + "loss": 0.8373, + "step": 2030 + }, + { + "epoch": 0.18185684705355643, + "grad_norm": 1.0869242750927197, + "learning_rate": 1.8815792359021906e-05, + "loss": 0.9266, + "step": 2031 + }, + { + "epoch": 0.18194638759863452, + "grad_norm": 0.970630873189667, + "learning_rate": 1.8814422947414e-05, + "loss": 0.8465, + "step": 2032 + }, + { + "epoch": 0.18203592814371258, + "grad_norm": 0.9999269025769625, + "learning_rate": 1.8813052794365557e-05, + "loss": 0.9291, + "step": 2033 + }, + { + "epoch": 0.18212546868879065, + "grad_norm": 1.0064082224227495, + "learning_rate": 1.8811681899991835e-05, + "loss": 0.8799, + "step": 2034 + }, + { + "epoch": 0.1822150092338687, + "grad_norm": 0.94399842577035, + "learning_rate": 1.8810310264408144e-05, + "loss": 0.8844, + "step": 2035 + }, + { + "epoch": 0.18230454977894678, + "grad_norm": 1.1004251782488281, + "learning_rate": 1.880893788772986e-05, + "loss": 0.9008, + "step": 2036 + }, + { + "epoch": 0.18239409032402484, + "grad_norm": 1.069211403046441, + "learning_rate": 1.880756477007243e-05, + "loss": 0.9234, + "step": 2037 + }, + { + "epoch": 0.1824836308691029, + "grad_norm": 0.9273609457683307, + "learning_rate": 1.8806190911551354e-05, + "loss": 0.7874, + "step": 2038 + }, + { + "epoch": 0.18257317141418097, + "grad_norm": 0.9926060265694593, + "learning_rate": 1.8804816312282196e-05, + "loss": 0.8345, + "step": 2039 + }, + { + "epoch": 0.18266271195925904, + "grad_norm": 0.9889033596799334, + "learning_rate": 1.880344097238058e-05, + "loss": 0.9098, + "step": 2040 + }, + { + "epoch": 0.18275225250433713, + "grad_norm": 0.8992970800221503, + "learning_rate": 1.8802064891962196e-05, + "loss": 0.8625, + "step": 2041 + }, + { + "epoch": 0.1828417930494152, + "grad_norm": 1.1380749344208796, + "learning_rate": 1.88006880711428e-05, + "loss": 0.8794, + "step": 2042 + }, + { + "epoch": 0.18293133359449326, + "grad_norm": 1.1643531894166756, + "learning_rate": 1.87993105100382e-05, + "loss": 0.8687, + "step": 2043 + }, + { + "epoch": 0.18302087413957133, + "grad_norm": 1.0880932481635293, + "learning_rate": 1.8797932208764276e-05, + "loss": 0.9529, + "step": 2044 + }, + { + "epoch": 0.1831104146846494, + "grad_norm": 1.1193247354078457, + "learning_rate": 1.8796553167436964e-05, + "loss": 0.9103, + "step": 2045 + }, + { + "epoch": 0.18319995522972746, + "grad_norm": 1.0207537626468697, + "learning_rate": 1.8795173386172263e-05, + "loss": 0.894, + "step": 2046 + }, + { + "epoch": 0.18328949577480552, + "grad_norm": 1.084818714721135, + "learning_rate": 1.879379286508624e-05, + "loss": 0.8572, + "step": 2047 + }, + { + "epoch": 0.1833790363198836, + "grad_norm": 1.0572124454107197, + "learning_rate": 1.8792411604295016e-05, + "loss": 0.8582, + "step": 2048 + }, + { + "epoch": 0.18346857686496165, + "grad_norm": 0.9576980217347596, + "learning_rate": 1.8791029603914782e-05, + "loss": 0.8668, + "step": 2049 + }, + { + "epoch": 0.18355811741003975, + "grad_norm": 1.1093392048169, + "learning_rate": 1.8789646864061782e-05, + "loss": 0.8285, + "step": 2050 + }, + { + "epoch": 0.1836476579551178, + "grad_norm": 1.1694283818505133, + "learning_rate": 1.878826338485233e-05, + "loss": 0.901, + "step": 2051 + }, + { + "epoch": 0.18373719850019588, + "grad_norm": 1.0121608726717621, + "learning_rate": 1.8786879166402804e-05, + "loss": 0.9278, + "step": 2052 + }, + { + "epoch": 0.18382673904527394, + "grad_norm": 1.0120642871411525, + "learning_rate": 1.8785494208829632e-05, + "loss": 0.8472, + "step": 2053 + }, + { + "epoch": 0.183916279590352, + "grad_norm": 0.9770045902225385, + "learning_rate": 1.878410851224932e-05, + "loss": 0.8985, + "step": 2054 + }, + { + "epoch": 0.18400582013543007, + "grad_norm": 0.9866142002676872, + "learning_rate": 1.8782722076778426e-05, + "loss": 0.8796, + "step": 2055 + }, + { + "epoch": 0.18409536068050814, + "grad_norm": 0.9823511032845382, + "learning_rate": 1.8781334902533567e-05, + "loss": 0.8954, + "step": 2056 + }, + { + "epoch": 0.1841849012255862, + "grad_norm": 0.9719154255052916, + "learning_rate": 1.8779946989631437e-05, + "loss": 0.8636, + "step": 2057 + }, + { + "epoch": 0.18427444177066427, + "grad_norm": 0.935355186439493, + "learning_rate": 1.8778558338188775e-05, + "loss": 0.8678, + "step": 2058 + }, + { + "epoch": 0.18436398231574236, + "grad_norm": 0.9217521270310518, + "learning_rate": 1.877716894832239e-05, + "loss": 0.9128, + "step": 2059 + }, + { + "epoch": 0.18445352286082042, + "grad_norm": 1.0759196106492392, + "learning_rate": 1.8775778820149155e-05, + "loss": 0.9239, + "step": 2060 + }, + { + "epoch": 0.1845430634058985, + "grad_norm": 1.0217565670205238, + "learning_rate": 1.8774387953786006e-05, + "loss": 0.8621, + "step": 2061 + }, + { + "epoch": 0.18463260395097655, + "grad_norm": 0.9681408005270951, + "learning_rate": 1.8772996349349934e-05, + "loss": 0.8904, + "step": 2062 + }, + { + "epoch": 0.18472214449605462, + "grad_norm": 0.9839167295888791, + "learning_rate": 1.8771604006958e-05, + "loss": 0.8939, + "step": 2063 + }, + { + "epoch": 0.18481168504113268, + "grad_norm": 1.125242616450166, + "learning_rate": 1.877021092672732e-05, + "loss": 0.9073, + "step": 2064 + }, + { + "epoch": 0.18490122558621075, + "grad_norm": 1.0733566456704193, + "learning_rate": 1.8768817108775075e-05, + "loss": 0.9191, + "step": 2065 + }, + { + "epoch": 0.18499076613128881, + "grad_norm": 0.9051700593408406, + "learning_rate": 1.876742255321851e-05, + "loss": 0.8421, + "step": 2066 + }, + { + "epoch": 0.18508030667636688, + "grad_norm": 0.9897681071811837, + "learning_rate": 1.876602726017493e-05, + "loss": 0.9171, + "step": 2067 + }, + { + "epoch": 0.18516984722144497, + "grad_norm": 0.874721996556142, + "learning_rate": 1.8764631229761707e-05, + "loss": 0.8891, + "step": 2068 + }, + { + "epoch": 0.18525938776652304, + "grad_norm": 0.9174687560671284, + "learning_rate": 1.876323446209626e-05, + "loss": 0.8829, + "step": 2069 + }, + { + "epoch": 0.1853489283116011, + "grad_norm": 1.0669450954653164, + "learning_rate": 1.876183695729609e-05, + "loss": 0.9208, + "step": 2070 + }, + { + "epoch": 0.18543846885667917, + "grad_norm": 1.0018635800480915, + "learning_rate": 1.8760438715478747e-05, + "loss": 0.8795, + "step": 2071 + }, + { + "epoch": 0.18552800940175723, + "grad_norm": 0.9619539045919628, + "learning_rate": 1.875903973676185e-05, + "loss": 0.8464, + "step": 2072 + }, + { + "epoch": 0.1856175499468353, + "grad_norm": 0.9941366303740476, + "learning_rate": 1.875764002126307e-05, + "loss": 0.8883, + "step": 2073 + }, + { + "epoch": 0.18570709049191336, + "grad_norm": 0.9539166664959589, + "learning_rate": 1.875623956910015e-05, + "loss": 0.8937, + "step": 2074 + }, + { + "epoch": 0.18579663103699143, + "grad_norm": 0.9326793686742503, + "learning_rate": 1.8754838380390888e-05, + "loss": 0.8899, + "step": 2075 + }, + { + "epoch": 0.1858861715820695, + "grad_norm": 1.009732787098808, + "learning_rate": 1.875343645525316e-05, + "loss": 0.8378, + "step": 2076 + }, + { + "epoch": 0.18597571212714759, + "grad_norm": 1.0426230750652328, + "learning_rate": 1.8752033793804875e-05, + "loss": 0.9094, + "step": 2077 + }, + { + "epoch": 0.18606525267222565, + "grad_norm": 0.9304114399133168, + "learning_rate": 1.875063039616403e-05, + "loss": 0.8805, + "step": 2078 + }, + { + "epoch": 0.18615479321730372, + "grad_norm": 0.8776070187754171, + "learning_rate": 1.874922626244867e-05, + "loss": 0.8949, + "step": 2079 + }, + { + "epoch": 0.18624433376238178, + "grad_norm": 0.9009644197043234, + "learning_rate": 1.874782139277691e-05, + "loss": 0.8051, + "step": 2080 + }, + { + "epoch": 0.18633387430745985, + "grad_norm": 1.0413676214409295, + "learning_rate": 1.874641578726692e-05, + "loss": 0.9021, + "step": 2081 + }, + { + "epoch": 0.1864234148525379, + "grad_norm": 1.008199315049748, + "learning_rate": 1.8745009446036934e-05, + "loss": 0.8988, + "step": 2082 + }, + { + "epoch": 0.18651295539761598, + "grad_norm": 0.9359498387700267, + "learning_rate": 1.8743602369205253e-05, + "loss": 0.863, + "step": 2083 + }, + { + "epoch": 0.18660249594269404, + "grad_norm": 0.9488001418409905, + "learning_rate": 1.8742194556890236e-05, + "loss": 0.8817, + "step": 2084 + }, + { + "epoch": 0.1866920364877721, + "grad_norm": 1.037717733786703, + "learning_rate": 1.8740786009210298e-05, + "loss": 0.8619, + "step": 2085 + }, + { + "epoch": 0.1867815770328502, + "grad_norm": 1.0236975567061672, + "learning_rate": 1.8739376726283925e-05, + "loss": 0.9174, + "step": 2086 + }, + { + "epoch": 0.18687111757792826, + "grad_norm": 1.0253607069403057, + "learning_rate": 1.873796670822966e-05, + "loss": 0.9356, + "step": 2087 + }, + { + "epoch": 0.18696065812300633, + "grad_norm": 0.8855156958116601, + "learning_rate": 1.873655595516611e-05, + "loss": 0.8543, + "step": 2088 + }, + { + "epoch": 0.1870501986680844, + "grad_norm": 0.9174525994301415, + "learning_rate": 1.8735144467211945e-05, + "loss": 0.8716, + "step": 2089 + }, + { + "epoch": 0.18713973921316246, + "grad_norm": 0.9400546618503367, + "learning_rate": 1.8733732244485893e-05, + "loss": 0.8918, + "step": 2090 + }, + { + "epoch": 0.18722927975824052, + "grad_norm": 0.9045414611022441, + "learning_rate": 1.8732319287106743e-05, + "loss": 0.9017, + "step": 2091 + }, + { + "epoch": 0.1873188203033186, + "grad_norm": 1.0457875986672203, + "learning_rate": 1.8730905595193353e-05, + "loss": 0.9085, + "step": 2092 + }, + { + "epoch": 0.18740836084839665, + "grad_norm": 1.1389311523716208, + "learning_rate": 1.8729491168864634e-05, + "loss": 0.8342, + "step": 2093 + }, + { + "epoch": 0.18749790139347472, + "grad_norm": 0.9692127138714356, + "learning_rate": 1.8728076008239563e-05, + "loss": 0.8691, + "step": 2094 + }, + { + "epoch": 0.1875874419385528, + "grad_norm": 1.0015255977192068, + "learning_rate": 1.8726660113437182e-05, + "loss": 0.8136, + "step": 2095 + }, + { + "epoch": 0.18767698248363088, + "grad_norm": 0.8873289216654391, + "learning_rate": 1.872524348457659e-05, + "loss": 0.8381, + "step": 2096 + }, + { + "epoch": 0.18776652302870894, + "grad_norm": 1.0218470372251216, + "learning_rate": 1.872382612177695e-05, + "loss": 0.9126, + "step": 2097 + }, + { + "epoch": 0.187856063573787, + "grad_norm": 0.9329838498766835, + "learning_rate": 1.8722408025157482e-05, + "loss": 0.9278, + "step": 2098 + }, + { + "epoch": 0.18794560411886507, + "grad_norm": 0.9727209010822274, + "learning_rate": 1.872098919483748e-05, + "loss": 0.8233, + "step": 2099 + }, + { + "epoch": 0.18803514466394314, + "grad_norm": 0.9666381568045974, + "learning_rate": 1.8719569630936284e-05, + "loss": 0.882, + "step": 2100 + }, + { + "epoch": 0.1881246852090212, + "grad_norm": 0.9611971981078845, + "learning_rate": 1.8718149333573305e-05, + "loss": 0.9304, + "step": 2101 + }, + { + "epoch": 0.18821422575409927, + "grad_norm": 0.9399983640296502, + "learning_rate": 1.871672830286801e-05, + "loss": 0.836, + "step": 2102 + }, + { + "epoch": 0.18830376629917733, + "grad_norm": 1.0298884568875413, + "learning_rate": 1.871530653893994e-05, + "loss": 0.8355, + "step": 2103 + }, + { + "epoch": 0.18839330684425543, + "grad_norm": 1.0087656979303088, + "learning_rate": 1.871388404190868e-05, + "loss": 0.8535, + "step": 2104 + }, + { + "epoch": 0.1884828473893335, + "grad_norm": 1.002981890065292, + "learning_rate": 1.8712460811893892e-05, + "loss": 0.9125, + "step": 2105 + }, + { + "epoch": 0.18857238793441156, + "grad_norm": 0.8773538375393836, + "learning_rate": 1.8711036849015295e-05, + "loss": 0.8623, + "step": 2106 + }, + { + "epoch": 0.18866192847948962, + "grad_norm": 0.9869255903207411, + "learning_rate": 1.8709612153392663e-05, + "loss": 0.9029, + "step": 2107 + }, + { + "epoch": 0.1887514690245677, + "grad_norm": 0.9940119861790361, + "learning_rate": 1.870818672514584e-05, + "loss": 0.838, + "step": 2108 + }, + { + "epoch": 0.18884100956964575, + "grad_norm": 1.0067281970204898, + "learning_rate": 1.8706760564394725e-05, + "loss": 0.8872, + "step": 2109 + }, + { + "epoch": 0.18893055011472382, + "grad_norm": 0.947768659451969, + "learning_rate": 1.8705333671259285e-05, + "loss": 0.8742, + "step": 2110 + }, + { + "epoch": 0.18902009065980188, + "grad_norm": 0.9404184235473504, + "learning_rate": 1.8703906045859545e-05, + "loss": 0.89, + "step": 2111 + }, + { + "epoch": 0.18910963120487995, + "grad_norm": 0.9249328276985129, + "learning_rate": 1.870247768831559e-05, + "loss": 0.8998, + "step": 2112 + }, + { + "epoch": 0.18919917174995804, + "grad_norm": 0.9871538664690727, + "learning_rate": 1.8701048598747574e-05, + "loss": 0.9299, + "step": 2113 + }, + { + "epoch": 0.1892887122950361, + "grad_norm": 1.04691117593866, + "learning_rate": 1.8699618777275704e-05, + "loss": 0.9367, + "step": 2114 + }, + { + "epoch": 0.18937825284011417, + "grad_norm": 0.8601600353953, + "learning_rate": 1.869818822402025e-05, + "loss": 0.8674, + "step": 2115 + }, + { + "epoch": 0.18946779338519223, + "grad_norm": 1.044550566806482, + "learning_rate": 1.8696756939101546e-05, + "loss": 0.9302, + "step": 2116 + }, + { + "epoch": 0.1895573339302703, + "grad_norm": 0.9283696375885887, + "learning_rate": 1.8695324922639992e-05, + "loss": 0.8722, + "step": 2117 + }, + { + "epoch": 0.18964687447534836, + "grad_norm": 0.9217063591320144, + "learning_rate": 1.8693892174756035e-05, + "loss": 0.8277, + "step": 2118 + }, + { + "epoch": 0.18973641502042643, + "grad_norm": 0.9992054859811078, + "learning_rate": 1.8692458695570205e-05, + "loss": 0.878, + "step": 2119 + }, + { + "epoch": 0.1898259555655045, + "grad_norm": 0.9891229392484504, + "learning_rate": 1.8691024485203075e-05, + "loss": 0.9327, + "step": 2120 + }, + { + "epoch": 0.18991549611058256, + "grad_norm": 1.0443381360713542, + "learning_rate": 1.8689589543775285e-05, + "loss": 0.8624, + "step": 2121 + }, + { + "epoch": 0.19000503665566065, + "grad_norm": 0.9556460833741145, + "learning_rate": 1.868815387140754e-05, + "loss": 0.9356, + "step": 2122 + }, + { + "epoch": 0.19009457720073872, + "grad_norm": 1.0982853055984374, + "learning_rate": 1.86867174682206e-05, + "loss": 0.9365, + "step": 2123 + }, + { + "epoch": 0.19018411774581678, + "grad_norm": 1.0067646731769602, + "learning_rate": 1.86852803343353e-05, + "loss": 0.8566, + "step": 2124 + }, + { + "epoch": 0.19027365829089485, + "grad_norm": 1.2497559647129648, + "learning_rate": 1.8683842469872517e-05, + "loss": 0.8695, + "step": 2125 + }, + { + "epoch": 0.1903631988359729, + "grad_norm": 0.9356778576536655, + "learning_rate": 1.8682403874953207e-05, + "loss": 0.8578, + "step": 2126 + }, + { + "epoch": 0.19045273938105098, + "grad_norm": 1.0060481871224578, + "learning_rate": 1.8680964549698373e-05, + "loss": 0.9394, + "step": 2127 + }, + { + "epoch": 0.19054227992612904, + "grad_norm": 0.9329172447615051, + "learning_rate": 1.867952449422909e-05, + "loss": 0.8868, + "step": 2128 + }, + { + "epoch": 0.1906318204712071, + "grad_norm": 0.9828821791916115, + "learning_rate": 1.8678083708666494e-05, + "loss": 0.9244, + "step": 2129 + }, + { + "epoch": 0.19072136101628517, + "grad_norm": 0.9526600644982036, + "learning_rate": 1.867664219313177e-05, + "loss": 0.9117, + "step": 2130 + }, + { + "epoch": 0.19081090156136327, + "grad_norm": 0.9110446366269302, + "learning_rate": 1.8675199947746185e-05, + "loss": 0.8708, + "step": 2131 + }, + { + "epoch": 0.19090044210644133, + "grad_norm": 1.1928738394230822, + "learning_rate": 1.8673756972631047e-05, + "loss": 0.8943, + "step": 2132 + }, + { + "epoch": 0.1909899826515194, + "grad_norm": 1.0251645327029184, + "learning_rate": 1.867231326790774e-05, + "loss": 0.8731, + "step": 2133 + }, + { + "epoch": 0.19107952319659746, + "grad_norm": 0.9601199048308197, + "learning_rate": 1.86708688336977e-05, + "loss": 0.9122, + "step": 2134 + }, + { + "epoch": 0.19116906374167553, + "grad_norm": 0.9276325767140973, + "learning_rate": 1.866942367012243e-05, + "loss": 0.8649, + "step": 2135 + }, + { + "epoch": 0.1912586042867536, + "grad_norm": 1.0070167769698446, + "learning_rate": 1.866797777730349e-05, + "loss": 0.8273, + "step": 2136 + }, + { + "epoch": 0.19134814483183166, + "grad_norm": 0.9087537750063099, + "learning_rate": 1.8666531155362505e-05, + "loss": 0.8516, + "step": 2137 + }, + { + "epoch": 0.19143768537690972, + "grad_norm": 1.0700216002501721, + "learning_rate": 1.8665083804421165e-05, + "loss": 0.857, + "step": 2138 + }, + { + "epoch": 0.1915272259219878, + "grad_norm": 1.0675483274181667, + "learning_rate": 1.866363572460121e-05, + "loss": 0.9227, + "step": 2139 + }, + { + "epoch": 0.19161676646706588, + "grad_norm": 0.8782001475852552, + "learning_rate": 1.8662186916024452e-05, + "loss": 0.8594, + "step": 2140 + }, + { + "epoch": 0.19170630701214394, + "grad_norm": 0.9290959052055816, + "learning_rate": 1.8660737378812755e-05, + "loss": 0.9098, + "step": 2141 + }, + { + "epoch": 0.191795847557222, + "grad_norm": 1.2945708244779994, + "learning_rate": 1.8659287113088057e-05, + "loss": 0.8659, + "step": 2142 + }, + { + "epoch": 0.19188538810230008, + "grad_norm": 0.980169013224945, + "learning_rate": 1.8657836118972338e-05, + "loss": 0.8804, + "step": 2143 + }, + { + "epoch": 0.19197492864737814, + "grad_norm": 1.06328409685627, + "learning_rate": 1.8656384396587663e-05, + "loss": 0.8793, + "step": 2144 + }, + { + "epoch": 0.1920644691924562, + "grad_norm": 0.8789533764503326, + "learning_rate": 1.8654931946056142e-05, + "loss": 0.8152, + "step": 2145 + }, + { + "epoch": 0.19215400973753427, + "grad_norm": 0.9577200567831039, + "learning_rate": 1.865347876749995e-05, + "loss": 0.8348, + "step": 2146 + }, + { + "epoch": 0.19224355028261234, + "grad_norm": 0.8899274902843718, + "learning_rate": 1.8652024861041316e-05, + "loss": 0.862, + "step": 2147 + }, + { + "epoch": 0.1923330908276904, + "grad_norm": 1.0833933186932274, + "learning_rate": 1.8650570226802554e-05, + "loss": 0.8754, + "step": 2148 + }, + { + "epoch": 0.1924226313727685, + "grad_norm": 0.9122585189935996, + "learning_rate": 1.864911486490601e-05, + "loss": 0.8555, + "step": 2149 + }, + { + "epoch": 0.19251217191784656, + "grad_norm": 0.9636591277447347, + "learning_rate": 1.8647658775474106e-05, + "loss": 0.9523, + "step": 2150 + }, + { + "epoch": 0.19260171246292462, + "grad_norm": 1.022987097486522, + "learning_rate": 1.8646201958629332e-05, + "loss": 0.8915, + "step": 2151 + }, + { + "epoch": 0.1926912530080027, + "grad_norm": 0.9439380158619503, + "learning_rate": 1.864474441449422e-05, + "loss": 0.8983, + "step": 2152 + }, + { + "epoch": 0.19278079355308075, + "grad_norm": 1.0702329981538026, + "learning_rate": 1.864328614319138e-05, + "loss": 0.9003, + "step": 2153 + }, + { + "epoch": 0.19287033409815882, + "grad_norm": 0.970824733604063, + "learning_rate": 1.8641827144843473e-05, + "loss": 0.9012, + "step": 2154 + }, + { + "epoch": 0.19295987464323688, + "grad_norm": 0.9688317808543242, + "learning_rate": 1.8640367419573232e-05, + "loss": 0.8913, + "step": 2155 + }, + { + "epoch": 0.19304941518831495, + "grad_norm": 0.9730570976517954, + "learning_rate": 1.863890696750344e-05, + "loss": 0.9096, + "step": 2156 + }, + { + "epoch": 0.19313895573339301, + "grad_norm": 0.9568918068773145, + "learning_rate": 1.8637445788756944e-05, + "loss": 0.8465, + "step": 2157 + }, + { + "epoch": 0.1932284962784711, + "grad_norm": 0.9471598106525235, + "learning_rate": 1.863598388345665e-05, + "loss": 0.8659, + "step": 2158 + }, + { + "epoch": 0.19331803682354917, + "grad_norm": 0.9383234387970055, + "learning_rate": 1.863452125172554e-05, + "loss": 0.9164, + "step": 2159 + }, + { + "epoch": 0.19340757736862724, + "grad_norm": 1.0197662205805804, + "learning_rate": 1.863305789368664e-05, + "loss": 0.869, + "step": 2160 + }, + { + "epoch": 0.1934971179137053, + "grad_norm": 1.0193639294759718, + "learning_rate": 1.863159380946304e-05, + "loss": 0.8402, + "step": 2161 + }, + { + "epoch": 0.19358665845878337, + "grad_norm": 1.2553117291425584, + "learning_rate": 1.86301289991779e-05, + "loss": 0.8981, + "step": 2162 + }, + { + "epoch": 0.19367619900386143, + "grad_norm": 0.9613084303490637, + "learning_rate": 1.8628663462954428e-05, + "loss": 0.9202, + "step": 2163 + }, + { + "epoch": 0.1937657395489395, + "grad_norm": 0.9111142868178581, + "learning_rate": 1.8627197200915905e-05, + "loss": 0.8397, + "step": 2164 + }, + { + "epoch": 0.19385528009401756, + "grad_norm": 1.2208208677288694, + "learning_rate": 1.8625730213185666e-05, + "loss": 0.9081, + "step": 2165 + }, + { + "epoch": 0.19394482063909563, + "grad_norm": 0.9256580871261344, + "learning_rate": 1.8624262499887112e-05, + "loss": 0.9033, + "step": 2166 + }, + { + "epoch": 0.19403436118417372, + "grad_norm": 0.9540346114346476, + "learning_rate": 1.8622794061143698e-05, + "loss": 0.9022, + "step": 2167 + }, + { + "epoch": 0.19412390172925179, + "grad_norm": 0.9667623423930666, + "learning_rate": 1.862132489707895e-05, + "loss": 0.8871, + "step": 2168 + }, + { + "epoch": 0.19421344227432985, + "grad_norm": 0.9760936914727403, + "learning_rate": 1.8619855007816445e-05, + "loss": 0.8759, + "step": 2169 + }, + { + "epoch": 0.19430298281940792, + "grad_norm": 0.9434273649482908, + "learning_rate": 1.8618384393479822e-05, + "loss": 0.9374, + "step": 2170 + }, + { + "epoch": 0.19439252336448598, + "grad_norm": 0.9280745561017153, + "learning_rate": 1.8616913054192792e-05, + "loss": 0.8917, + "step": 2171 + }, + { + "epoch": 0.19448206390956405, + "grad_norm": 1.1196748115668116, + "learning_rate": 1.8615440990079117e-05, + "loss": 0.8364, + "step": 2172 + }, + { + "epoch": 0.1945716044546421, + "grad_norm": 0.986044807084855, + "learning_rate": 1.8613968201262622e-05, + "loss": 0.8703, + "step": 2173 + }, + { + "epoch": 0.19466114499972018, + "grad_norm": 1.0156667117110476, + "learning_rate": 1.8612494687867188e-05, + "loss": 0.8962, + "step": 2174 + }, + { + "epoch": 0.19475068554479824, + "grad_norm": 0.8859828076031111, + "learning_rate": 1.861102045001677e-05, + "loss": 0.8239, + "step": 2175 + }, + { + "epoch": 0.19484022608987633, + "grad_norm": 0.9348579479108126, + "learning_rate": 1.860954548783537e-05, + "loss": 0.768, + "step": 2176 + }, + { + "epoch": 0.1949297666349544, + "grad_norm": 0.8997383724537695, + "learning_rate": 1.860806980144706e-05, + "loss": 0.8946, + "step": 2177 + }, + { + "epoch": 0.19501930718003246, + "grad_norm": 0.8456604877544933, + "learning_rate": 1.8606593390975975e-05, + "loss": 0.8389, + "step": 2178 + }, + { + "epoch": 0.19510884772511053, + "grad_norm": 1.1110522330294677, + "learning_rate": 1.8605116256546293e-05, + "loss": 0.8427, + "step": 2179 + }, + { + "epoch": 0.1951983882701886, + "grad_norm": 1.0160263087814307, + "learning_rate": 1.8603638398282274e-05, + "loss": 0.8956, + "step": 2180 + }, + { + "epoch": 0.19528792881526666, + "grad_norm": 0.9683835489256681, + "learning_rate": 1.860215981630823e-05, + "loss": 0.922, + "step": 2181 + }, + { + "epoch": 0.19537746936034472, + "grad_norm": 0.967127428619307, + "learning_rate": 1.8600680510748536e-05, + "loss": 0.9135, + "step": 2182 + }, + { + "epoch": 0.1954670099054228, + "grad_norm": 0.9996503908880348, + "learning_rate": 1.8599200481727627e-05, + "loss": 0.828, + "step": 2183 + }, + { + "epoch": 0.19555655045050085, + "grad_norm": 1.100614693335705, + "learning_rate": 1.859771972936999e-05, + "loss": 0.8806, + "step": 2184 + }, + { + "epoch": 0.19564609099557895, + "grad_norm": 0.883532422650634, + "learning_rate": 1.859623825380019e-05, + "loss": 0.8702, + "step": 2185 + }, + { + "epoch": 0.195735631540657, + "grad_norm": 0.9691539210909547, + "learning_rate": 1.859475605514284e-05, + "loss": 0.8805, + "step": 2186 + }, + { + "epoch": 0.19582517208573508, + "grad_norm": 0.8727255611527925, + "learning_rate": 1.8593273133522618e-05, + "loss": 0.8671, + "step": 2187 + }, + { + "epoch": 0.19591471263081314, + "grad_norm": 0.9917768382521909, + "learning_rate": 1.8591789489064264e-05, + "loss": 0.8663, + "step": 2188 + }, + { + "epoch": 0.1960042531758912, + "grad_norm": 0.9535266940455634, + "learning_rate": 1.8590305121892575e-05, + "loss": 0.8771, + "step": 2189 + }, + { + "epoch": 0.19609379372096927, + "grad_norm": 1.298764404885573, + "learning_rate": 1.8588820032132414e-05, + "loss": 0.8326, + "step": 2190 + }, + { + "epoch": 0.19618333426604734, + "grad_norm": 0.9259134298605606, + "learning_rate": 1.85873342199087e-05, + "loss": 0.8543, + "step": 2191 + }, + { + "epoch": 0.1962728748111254, + "grad_norm": 1.17034996355197, + "learning_rate": 1.8585847685346415e-05, + "loss": 0.8671, + "step": 2192 + }, + { + "epoch": 0.19636241535620347, + "grad_norm": 0.9667252677373399, + "learning_rate": 1.85843604285706e-05, + "loss": 0.8538, + "step": 2193 + }, + { + "epoch": 0.19645195590128156, + "grad_norm": 1.0271637889961365, + "learning_rate": 1.8582872449706358e-05, + "loss": 0.8969, + "step": 2194 + }, + { + "epoch": 0.19654149644635963, + "grad_norm": 1.0031018376159087, + "learning_rate": 1.8581383748878856e-05, + "loss": 0.9053, + "step": 2195 + }, + { + "epoch": 0.1966310369914377, + "grad_norm": 1.201736235266263, + "learning_rate": 1.857989432621332e-05, + "loss": 0.8759, + "step": 2196 + }, + { + "epoch": 0.19672057753651576, + "grad_norm": 1.2075952692267113, + "learning_rate": 1.8578404181835032e-05, + "loss": 0.8789, + "step": 2197 + }, + { + "epoch": 0.19681011808159382, + "grad_norm": 0.9279715908865723, + "learning_rate": 1.8576913315869337e-05, + "loss": 0.9152, + "step": 2198 + }, + { + "epoch": 0.1968996586266719, + "grad_norm": 0.8970766735911032, + "learning_rate": 1.8575421728441646e-05, + "loss": 0.887, + "step": 2199 + }, + { + "epoch": 0.19698919917174995, + "grad_norm": 0.9757095356538632, + "learning_rate": 1.857392941967742e-05, + "loss": 0.8501, + "step": 2200 + }, + { + "epoch": 0.19707873971682802, + "grad_norm": 0.9982619304779129, + "learning_rate": 1.857243638970219e-05, + "loss": 0.8337, + "step": 2201 + }, + { + "epoch": 0.19716828026190608, + "grad_norm": 0.9433956420204105, + "learning_rate": 1.857094263864155e-05, + "loss": 0.8544, + "step": 2202 + }, + { + "epoch": 0.19725782080698417, + "grad_norm": 0.934352084405641, + "learning_rate": 1.8569448166621145e-05, + "loss": 0.9233, + "step": 2203 + }, + { + "epoch": 0.19734736135206224, + "grad_norm": 1.031436327987299, + "learning_rate": 1.856795297376669e-05, + "loss": 0.8744, + "step": 2204 + }, + { + "epoch": 0.1974369018971403, + "grad_norm": 1.0240623105697386, + "learning_rate": 1.8566457060203942e-05, + "loss": 0.8735, + "step": 2205 + }, + { + "epoch": 0.19752644244221837, + "grad_norm": 1.0906919291585435, + "learning_rate": 1.8564960426058745e-05, + "loss": 0.8653, + "step": 2206 + }, + { + "epoch": 0.19761598298729643, + "grad_norm": 0.9910406985137401, + "learning_rate": 1.8563463071456992e-05, + "loss": 0.8733, + "step": 2207 + }, + { + "epoch": 0.1977055235323745, + "grad_norm": 0.9453247271459769, + "learning_rate": 1.8561964996524628e-05, + "loss": 0.8732, + "step": 2208 + }, + { + "epoch": 0.19779506407745256, + "grad_norm": 1.1468704408192922, + "learning_rate": 1.8560466201387667e-05, + "loss": 0.8389, + "step": 2209 + }, + { + "epoch": 0.19788460462253063, + "grad_norm": 1.0361611345917605, + "learning_rate": 1.8558966686172185e-05, + "loss": 0.931, + "step": 2210 + }, + { + "epoch": 0.1979741451676087, + "grad_norm": 0.8996302960858265, + "learning_rate": 1.8557466451004323e-05, + "loss": 0.8797, + "step": 2211 + }, + { + "epoch": 0.1980636857126868, + "grad_norm": 0.9052330818463086, + "learning_rate": 1.8555965496010264e-05, + "loss": 0.8755, + "step": 2212 + }, + { + "epoch": 0.19815322625776485, + "grad_norm": 1.0078760944568, + "learning_rate": 1.855446382131627e-05, + "loss": 0.9506, + "step": 2213 + }, + { + "epoch": 0.19824276680284292, + "grad_norm": 1.1178863670983918, + "learning_rate": 1.8552961427048655e-05, + "loss": 0.9527, + "step": 2214 + }, + { + "epoch": 0.19833230734792098, + "grad_norm": 1.0001230530025589, + "learning_rate": 1.8551458313333796e-05, + "loss": 0.8492, + "step": 2215 + }, + { + "epoch": 0.19842184789299905, + "grad_norm": 0.9956672912856674, + "learning_rate": 1.854995448029813e-05, + "loss": 0.9267, + "step": 2216 + }, + { + "epoch": 0.1985113884380771, + "grad_norm": 1.0595658528483614, + "learning_rate": 1.854844992806816e-05, + "loss": 0.902, + "step": 2217 + }, + { + "epoch": 0.19860092898315518, + "grad_norm": 1.1899805839581479, + "learning_rate": 1.8546944656770432e-05, + "loss": 0.8977, + "step": 2218 + }, + { + "epoch": 0.19869046952823324, + "grad_norm": 0.9447784563291665, + "learning_rate": 1.8545438666531576e-05, + "loss": 0.8224, + "step": 2219 + }, + { + "epoch": 0.1987800100733113, + "grad_norm": 1.0220566961267354, + "learning_rate": 1.8543931957478266e-05, + "loss": 0.8891, + "step": 2220 + }, + { + "epoch": 0.1988695506183894, + "grad_norm": 1.1364571594323145, + "learning_rate": 1.854242452973724e-05, + "loss": 0.8934, + "step": 2221 + }, + { + "epoch": 0.19895909116346747, + "grad_norm": 1.0942620924441164, + "learning_rate": 1.8540916383435303e-05, + "loss": 0.8898, + "step": 2222 + }, + { + "epoch": 0.19904863170854553, + "grad_norm": 1.043209974011806, + "learning_rate": 1.8539407518699307e-05, + "loss": 0.9096, + "step": 2223 + }, + { + "epoch": 0.1991381722536236, + "grad_norm": 1.2707230369313236, + "learning_rate": 1.853789793565618e-05, + "loss": 0.8767, + "step": 2224 + }, + { + "epoch": 0.19922771279870166, + "grad_norm": 0.9546219047171328, + "learning_rate": 1.8536387634432904e-05, + "loss": 0.8807, + "step": 2225 + }, + { + "epoch": 0.19931725334377973, + "grad_norm": 1.0673545874512418, + "learning_rate": 1.8534876615156518e-05, + "loss": 0.8653, + "step": 2226 + }, + { + "epoch": 0.1994067938888578, + "grad_norm": 1.2109923883941378, + "learning_rate": 1.8533364877954118e-05, + "loss": 0.9511, + "step": 2227 + }, + { + "epoch": 0.19949633443393586, + "grad_norm": 0.993671669735077, + "learning_rate": 1.8531852422952878e-05, + "loss": 0.8557, + "step": 2228 + }, + { + "epoch": 0.19958587497901392, + "grad_norm": 1.1845301101479957, + "learning_rate": 1.8530339250280012e-05, + "loss": 0.8443, + "step": 2229 + }, + { + "epoch": 0.19967541552409201, + "grad_norm": 0.9201463712025468, + "learning_rate": 1.852882536006281e-05, + "loss": 0.8686, + "step": 2230 + }, + { + "epoch": 0.19976495606917008, + "grad_norm": 0.9738653800117629, + "learning_rate": 1.8527310752428605e-05, + "loss": 0.8987, + "step": 2231 + }, + { + "epoch": 0.19985449661424814, + "grad_norm": 0.951423719642921, + "learning_rate": 1.852579542750481e-05, + "loss": 0.8699, + "step": 2232 + }, + { + "epoch": 0.1999440371593262, + "grad_norm": 1.016604686236065, + "learning_rate": 1.8524279385418887e-05, + "loss": 0.852, + "step": 2233 + }, + { + "epoch": 0.20003357770440428, + "grad_norm": 0.8505285054144482, + "learning_rate": 1.8522762626298364e-05, + "loss": 0.8345, + "step": 2234 + }, + { + "epoch": 0.20012311824948234, + "grad_norm": 1.0960041259666753, + "learning_rate": 1.852124515027082e-05, + "loss": 0.9099, + "step": 2235 + }, + { + "epoch": 0.2002126587945604, + "grad_norm": 0.9785559619870202, + "learning_rate": 1.8519726957463898e-05, + "loss": 0.9079, + "step": 2236 + }, + { + "epoch": 0.20030219933963847, + "grad_norm": 1.0060972409437032, + "learning_rate": 1.851820804800531e-05, + "loss": 1.0094, + "step": 2237 + }, + { + "epoch": 0.20039173988471654, + "grad_norm": 0.8874165284918272, + "learning_rate": 1.851668842202282e-05, + "loss": 0.9034, + "step": 2238 + }, + { + "epoch": 0.20048128042979463, + "grad_norm": 0.9824025367951479, + "learning_rate": 1.8515168079644256e-05, + "loss": 0.9035, + "step": 2239 + }, + { + "epoch": 0.2005708209748727, + "grad_norm": 0.9215040562482527, + "learning_rate": 1.85136470209975e-05, + "loss": 0.8632, + "step": 2240 + }, + { + "epoch": 0.20066036151995076, + "grad_norm": 1.0157440400619355, + "learning_rate": 1.8512125246210496e-05, + "loss": 0.8759, + "step": 2241 + }, + { + "epoch": 0.20074990206502882, + "grad_norm": 0.8780438891401056, + "learning_rate": 1.8510602755411258e-05, + "loss": 0.8428, + "step": 2242 + }, + { + "epoch": 0.2008394426101069, + "grad_norm": 0.8641754553926261, + "learning_rate": 1.850907954872785e-05, + "loss": 0.844, + "step": 2243 + }, + { + "epoch": 0.20092898315518495, + "grad_norm": 1.0074301323388741, + "learning_rate": 1.8507555626288398e-05, + "loss": 0.8817, + "step": 2244 + }, + { + "epoch": 0.20101852370026302, + "grad_norm": 1.062915978659435, + "learning_rate": 1.850603098822109e-05, + "loss": 0.9504, + "step": 2245 + }, + { + "epoch": 0.20110806424534108, + "grad_norm": 0.9086226602272129, + "learning_rate": 1.8504505634654177e-05, + "loss": 0.9166, + "step": 2246 + }, + { + "epoch": 0.20119760479041915, + "grad_norm": 1.194891926642487, + "learning_rate": 1.850297956571596e-05, + "loss": 0.8712, + "step": 2247 + }, + { + "epoch": 0.20128714533549724, + "grad_norm": 1.0784646103371456, + "learning_rate": 1.850145278153481e-05, + "loss": 0.8859, + "step": 2248 + }, + { + "epoch": 0.2013766858805753, + "grad_norm": 0.990326061063382, + "learning_rate": 1.8499925282239158e-05, + "loss": 0.8448, + "step": 2249 + }, + { + "epoch": 0.20146622642565337, + "grad_norm": 1.002340504473485, + "learning_rate": 1.849839706795749e-05, + "loss": 0.9413, + "step": 2250 + }, + { + "epoch": 0.20155576697073144, + "grad_norm": 1.0297860229452893, + "learning_rate": 1.8496868138818354e-05, + "loss": 0.8943, + "step": 2251 + }, + { + "epoch": 0.2016453075158095, + "grad_norm": 1.1690679545261213, + "learning_rate": 1.849533849495036e-05, + "loss": 0.8732, + "step": 2252 + }, + { + "epoch": 0.20173484806088757, + "grad_norm": 0.9404967904005352, + "learning_rate": 1.8493808136482176e-05, + "loss": 0.8638, + "step": 2253 + }, + { + "epoch": 0.20182438860596563, + "grad_norm": 0.9162247683723409, + "learning_rate": 1.8492277063542524e-05, + "loss": 0.8645, + "step": 2254 + }, + { + "epoch": 0.2019139291510437, + "grad_norm": 0.9996871440155509, + "learning_rate": 1.8490745276260208e-05, + "loss": 0.9186, + "step": 2255 + }, + { + "epoch": 0.20200346969612176, + "grad_norm": 0.9952018287608507, + "learning_rate": 1.8489212774764064e-05, + "loss": 0.8692, + "step": 2256 + }, + { + "epoch": 0.20209301024119986, + "grad_norm": 0.9717356685883268, + "learning_rate": 1.8487679559183e-05, + "loss": 0.8843, + "step": 2257 + }, + { + "epoch": 0.20218255078627792, + "grad_norm": 0.9332154506932737, + "learning_rate": 1.8486145629646e-05, + "loss": 0.892, + "step": 2258 + }, + { + "epoch": 0.20227209133135599, + "grad_norm": 1.1144490522914088, + "learning_rate": 1.848461098628208e-05, + "loss": 0.9278, + "step": 2259 + }, + { + "epoch": 0.20236163187643405, + "grad_norm": 1.7003814728035742, + "learning_rate": 1.8483075629220333e-05, + "loss": 0.9214, + "step": 2260 + }, + { + "epoch": 0.20245117242151212, + "grad_norm": 0.9801119058428106, + "learning_rate": 1.8481539558589906e-05, + "loss": 0.8527, + "step": 2261 + }, + { + "epoch": 0.20254071296659018, + "grad_norm": 1.008014406838476, + "learning_rate": 1.848000277452001e-05, + "loss": 0.8528, + "step": 2262 + }, + { + "epoch": 0.20263025351166825, + "grad_norm": 0.9126280839115792, + "learning_rate": 1.8478465277139914e-05, + "loss": 0.877, + "step": 2263 + }, + { + "epoch": 0.2027197940567463, + "grad_norm": 0.967325954184627, + "learning_rate": 1.8476927066578948e-05, + "loss": 0.9016, + "step": 2264 + }, + { + "epoch": 0.20280933460182438, + "grad_norm": 0.929545593222842, + "learning_rate": 1.8475388142966503e-05, + "loss": 0.8877, + "step": 2265 + }, + { + "epoch": 0.20289887514690247, + "grad_norm": 1.1397034070437517, + "learning_rate": 1.8473848506432025e-05, + "loss": 0.8955, + "step": 2266 + }, + { + "epoch": 0.20298841569198053, + "grad_norm": 1.0627198764167012, + "learning_rate": 1.8472308157105026e-05, + "loss": 0.8469, + "step": 2267 + }, + { + "epoch": 0.2030779562370586, + "grad_norm": 0.9521235323210383, + "learning_rate": 1.8470767095115074e-05, + "loss": 0.8906, + "step": 2268 + }, + { + "epoch": 0.20316749678213666, + "grad_norm": 1.169231267601412, + "learning_rate": 1.8469225320591794e-05, + "loss": 0.8857, + "step": 2269 + }, + { + "epoch": 0.20325703732721473, + "grad_norm": 0.9071337225375996, + "learning_rate": 1.846768283366488e-05, + "loss": 0.8882, + "step": 2270 + }, + { + "epoch": 0.2033465778722928, + "grad_norm": 0.9876077221974757, + "learning_rate": 1.8466139634464082e-05, + "loss": 0.9231, + "step": 2271 + }, + { + "epoch": 0.20343611841737086, + "grad_norm": 1.154352599620688, + "learning_rate": 1.8464595723119206e-05, + "loss": 0.8787, + "step": 2272 + }, + { + "epoch": 0.20352565896244892, + "grad_norm": 0.9010408888430375, + "learning_rate": 1.846305109976012e-05, + "loss": 0.8744, + "step": 2273 + }, + { + "epoch": 0.203615199507527, + "grad_norm": 1.1119423771290902, + "learning_rate": 1.8461505764516752e-05, + "loss": 0.9113, + "step": 2274 + }, + { + "epoch": 0.20370474005260508, + "grad_norm": 1.1117116621873602, + "learning_rate": 1.8459959717519096e-05, + "loss": 0.7942, + "step": 2275 + }, + { + "epoch": 0.20379428059768315, + "grad_norm": 0.9782284100915064, + "learning_rate": 1.8458412958897196e-05, + "loss": 0.846, + "step": 2276 + }, + { + "epoch": 0.2038838211427612, + "grad_norm": 0.9534606652957766, + "learning_rate": 1.8456865488781162e-05, + "loss": 0.9166, + "step": 2277 + }, + { + "epoch": 0.20397336168783928, + "grad_norm": 0.9209304511029442, + "learning_rate": 1.845531730730116e-05, + "loss": 0.9099, + "step": 2278 + }, + { + "epoch": 0.20406290223291734, + "grad_norm": 1.0346689149350008, + "learning_rate": 1.8453768414587424e-05, + "loss": 0.9293, + "step": 2279 + }, + { + "epoch": 0.2041524427779954, + "grad_norm": 0.9657162413976449, + "learning_rate": 1.8452218810770232e-05, + "loss": 0.927, + "step": 2280 + }, + { + "epoch": 0.20424198332307347, + "grad_norm": 0.9533802716136274, + "learning_rate": 1.8450668495979937e-05, + "loss": 0.8645, + "step": 2281 + }, + { + "epoch": 0.20433152386815154, + "grad_norm": 1.0006368922078988, + "learning_rate": 1.844911747034695e-05, + "loss": 0.8591, + "step": 2282 + }, + { + "epoch": 0.2044210644132296, + "grad_norm": 0.9706237429879425, + "learning_rate": 1.844756573400173e-05, + "loss": 0.8721, + "step": 2283 + }, + { + "epoch": 0.2045106049583077, + "grad_norm": 0.9752254327001012, + "learning_rate": 1.8446013287074812e-05, + "loss": 0.8422, + "step": 2284 + }, + { + "epoch": 0.20460014550338576, + "grad_norm": 0.9044730858750591, + "learning_rate": 1.844446012969678e-05, + "loss": 0.8817, + "step": 2285 + }, + { + "epoch": 0.20468968604846383, + "grad_norm": 0.9321495665441216, + "learning_rate": 1.8442906261998277e-05, + "loss": 0.8777, + "step": 2286 + }, + { + "epoch": 0.2047792265935419, + "grad_norm": 1.0967912583911346, + "learning_rate": 1.8441351684110014e-05, + "loss": 0.9745, + "step": 2287 + }, + { + "epoch": 0.20486876713861996, + "grad_norm": 0.892517396538192, + "learning_rate": 1.8439796396162756e-05, + "loss": 0.8608, + "step": 2288 + }, + { + "epoch": 0.20495830768369802, + "grad_norm": 1.102513827990313, + "learning_rate": 1.8438240398287325e-05, + "loss": 0.8773, + "step": 2289 + }, + { + "epoch": 0.2050478482287761, + "grad_norm": 1.0334482534892258, + "learning_rate": 1.843668369061461e-05, + "loss": 0.8989, + "step": 2290 + }, + { + "epoch": 0.20513738877385415, + "grad_norm": 0.9556946031206666, + "learning_rate": 1.843512627327556e-05, + "loss": 0.9172, + "step": 2291 + }, + { + "epoch": 0.20522692931893222, + "grad_norm": 1.020493288569179, + "learning_rate": 1.843356814640117e-05, + "loss": 0.9067, + "step": 2292 + }, + { + "epoch": 0.2053164698640103, + "grad_norm": 0.9529903207270544, + "learning_rate": 1.8432009310122513e-05, + "loss": 0.9397, + "step": 2293 + }, + { + "epoch": 0.20540601040908837, + "grad_norm": 0.9661606044885973, + "learning_rate": 1.8430449764570708e-05, + "loss": 0.8634, + "step": 2294 + }, + { + "epoch": 0.20549555095416644, + "grad_norm": 0.9645320086110252, + "learning_rate": 1.8428889509876943e-05, + "loss": 0.9056, + "step": 2295 + }, + { + "epoch": 0.2055850914992445, + "grad_norm": 0.898271645970045, + "learning_rate": 1.842732854617246e-05, + "loss": 0.8977, + "step": 2296 + }, + { + "epoch": 0.20567463204432257, + "grad_norm": 0.9715530618711378, + "learning_rate": 1.842576687358856e-05, + "loss": 0.9202, + "step": 2297 + }, + { + "epoch": 0.20576417258940063, + "grad_norm": 1.0776860530106205, + "learning_rate": 1.842420449225661e-05, + "loss": 0.8519, + "step": 2298 + }, + { + "epoch": 0.2058537131344787, + "grad_norm": 0.999185911264621, + "learning_rate": 1.8422641402308027e-05, + "loss": 0.8701, + "step": 2299 + }, + { + "epoch": 0.20594325367955676, + "grad_norm": 1.0671519059548256, + "learning_rate": 1.84210776038743e-05, + "loss": 0.918, + "step": 2300 + }, + { + "epoch": 0.20603279422463483, + "grad_norm": 0.9568544913626, + "learning_rate": 1.8419513097086965e-05, + "loss": 0.8333, + "step": 2301 + }, + { + "epoch": 0.20612233476971292, + "grad_norm": 0.9879354458395455, + "learning_rate": 1.8417947882077625e-05, + "loss": 0.8645, + "step": 2302 + }, + { + "epoch": 0.206211875314791, + "grad_norm": 0.8836017727055884, + "learning_rate": 1.841638195897794e-05, + "loss": 0.8397, + "step": 2303 + }, + { + "epoch": 0.20630141585986905, + "grad_norm": 0.9626370393798671, + "learning_rate": 1.8414815327919633e-05, + "loss": 0.9311, + "step": 2304 + }, + { + "epoch": 0.20639095640494712, + "grad_norm": 0.9674128224778638, + "learning_rate": 1.841324798903448e-05, + "loss": 0.8801, + "step": 2305 + }, + { + "epoch": 0.20648049695002518, + "grad_norm": 1.0844014321482562, + "learning_rate": 1.8411679942454324e-05, + "loss": 0.871, + "step": 2306 + }, + { + "epoch": 0.20657003749510325, + "grad_norm": 0.9681295636253464, + "learning_rate": 1.841011118831106e-05, + "loss": 0.8777, + "step": 2307 + }, + { + "epoch": 0.2066595780401813, + "grad_norm": 1.013305173332575, + "learning_rate": 1.840854172673665e-05, + "loss": 0.9095, + "step": 2308 + }, + { + "epoch": 0.20674911858525938, + "grad_norm": 0.9009463850456422, + "learning_rate": 1.840697155786311e-05, + "loss": 0.8796, + "step": 2309 + }, + { + "epoch": 0.20683865913033744, + "grad_norm": 0.9758458671539242, + "learning_rate": 1.8405400681822523e-05, + "loss": 0.9225, + "step": 2310 + }, + { + "epoch": 0.20692819967541554, + "grad_norm": 1.0661411544736863, + "learning_rate": 1.8403829098747017e-05, + "loss": 0.8499, + "step": 2311 + }, + { + "epoch": 0.2070177402204936, + "grad_norm": 1.1632544058505203, + "learning_rate": 1.840225680876879e-05, + "loss": 0.9372, + "step": 2312 + }, + { + "epoch": 0.20710728076557167, + "grad_norm": 0.8744858126977464, + "learning_rate": 1.8400683812020107e-05, + "loss": 0.8443, + "step": 2313 + }, + { + "epoch": 0.20719682131064973, + "grad_norm": 0.9239166169008859, + "learning_rate": 1.8399110108633275e-05, + "loss": 0.8266, + "step": 2314 + }, + { + "epoch": 0.2072863618557278, + "grad_norm": 1.3286468410130272, + "learning_rate": 1.839753569874067e-05, + "loss": 0.8958, + "step": 2315 + }, + { + "epoch": 0.20737590240080586, + "grad_norm": 0.9340196406553349, + "learning_rate": 1.839596058247473e-05, + "loss": 0.9065, + "step": 2316 + }, + { + "epoch": 0.20746544294588393, + "grad_norm": 1.0134212296588005, + "learning_rate": 1.8394384759967943e-05, + "loss": 0.8473, + "step": 2317 + }, + { + "epoch": 0.207554983490962, + "grad_norm": 0.9350759401341093, + "learning_rate": 1.8392808231352867e-05, + "loss": 0.9388, + "step": 2318 + }, + { + "epoch": 0.20764452403604006, + "grad_norm": 1.0223254248819673, + "learning_rate": 1.8391230996762107e-05, + "loss": 0.8575, + "step": 2319 + }, + { + "epoch": 0.20773406458111815, + "grad_norm": 0.9908714217445399, + "learning_rate": 1.8389653056328344e-05, + "loss": 0.8585, + "step": 2320 + }, + { + "epoch": 0.20782360512619621, + "grad_norm": 0.9657244175770199, + "learning_rate": 1.8388074410184304e-05, + "loss": 0.838, + "step": 2321 + }, + { + "epoch": 0.20791314567127428, + "grad_norm": 0.8700578346757099, + "learning_rate": 1.838649505846278e-05, + "loss": 0.815, + "step": 2322 + }, + { + "epoch": 0.20800268621635234, + "grad_norm": 0.8691703628662262, + "learning_rate": 1.8384915001296623e-05, + "loss": 0.8868, + "step": 2323 + }, + { + "epoch": 0.2080922267614304, + "grad_norm": 0.9799360287605824, + "learning_rate": 1.8383334238818738e-05, + "loss": 0.882, + "step": 2324 + }, + { + "epoch": 0.20818176730650848, + "grad_norm": 1.1916782650823785, + "learning_rate": 1.8381752771162095e-05, + "loss": 0.8824, + "step": 2325 + }, + { + "epoch": 0.20827130785158654, + "grad_norm": 0.9590769507726428, + "learning_rate": 1.838017059845972e-05, + "loss": 0.8517, + "step": 2326 + }, + { + "epoch": 0.2083608483966646, + "grad_norm": 0.903858830451462, + "learning_rate": 1.8378587720844708e-05, + "loss": 0.9012, + "step": 2327 + }, + { + "epoch": 0.20845038894174267, + "grad_norm": 0.9416101144004887, + "learning_rate": 1.8377004138450196e-05, + "loss": 0.8305, + "step": 2328 + }, + { + "epoch": 0.20853992948682076, + "grad_norm": 0.9675763383619337, + "learning_rate": 1.8375419851409396e-05, + "loss": 0.8669, + "step": 2329 + }, + { + "epoch": 0.20862947003189883, + "grad_norm": 1.1956420278260163, + "learning_rate": 1.8373834859855572e-05, + "loss": 0.8705, + "step": 2330 + }, + { + "epoch": 0.2087190105769769, + "grad_norm": 0.9254323946556332, + "learning_rate": 1.8372249163922045e-05, + "loss": 0.8704, + "step": 2331 + }, + { + "epoch": 0.20880855112205496, + "grad_norm": 1.0849889563041322, + "learning_rate": 1.83706627637422e-05, + "loss": 0.8618, + "step": 2332 + }, + { + "epoch": 0.20889809166713302, + "grad_norm": 0.9479872523530047, + "learning_rate": 1.8369075659449486e-05, + "loss": 0.8492, + "step": 2333 + }, + { + "epoch": 0.2089876322122111, + "grad_norm": 1.2130042495505715, + "learning_rate": 1.83674878511774e-05, + "loss": 0.9536, + "step": 2334 + }, + { + "epoch": 0.20907717275728915, + "grad_norm": 1.0511298363043613, + "learning_rate": 1.8365899339059496e-05, + "loss": 0.8939, + "step": 2335 + }, + { + "epoch": 0.20916671330236722, + "grad_norm": 0.9150730778417326, + "learning_rate": 1.8364310123229406e-05, + "loss": 0.9726, + "step": 2336 + }, + { + "epoch": 0.20925625384744528, + "grad_norm": 0.9914732870978461, + "learning_rate": 1.8362720203820807e-05, + "loss": 0.8335, + "step": 2337 + }, + { + "epoch": 0.20934579439252338, + "grad_norm": 0.9492069698840945, + "learning_rate": 1.8361129580967432e-05, + "loss": 0.863, + "step": 2338 + }, + { + "epoch": 0.20943533493760144, + "grad_norm": 0.9500460835425355, + "learning_rate": 1.8359538254803086e-05, + "loss": 0.915, + "step": 2339 + }, + { + "epoch": 0.2095248754826795, + "grad_norm": 1.0338876708733444, + "learning_rate": 1.8357946225461622e-05, + "loss": 0.9589, + "step": 2340 + }, + { + "epoch": 0.20961441602775757, + "grad_norm": 0.932578747668577, + "learning_rate": 1.8356353493076958e-05, + "loss": 0.9089, + "step": 2341 + }, + { + "epoch": 0.20970395657283564, + "grad_norm": 0.9495835200375395, + "learning_rate": 1.835476005778307e-05, + "loss": 0.8113, + "step": 2342 + }, + { + "epoch": 0.2097934971179137, + "grad_norm": 0.929083138985875, + "learning_rate": 1.8353165919713988e-05, + "loss": 0.8614, + "step": 2343 + }, + { + "epoch": 0.20988303766299177, + "grad_norm": 0.9816988023833834, + "learning_rate": 1.8351571079003813e-05, + "loss": 0.8872, + "step": 2344 + }, + { + "epoch": 0.20997257820806983, + "grad_norm": 0.9031129362987765, + "learning_rate": 1.8349975535786693e-05, + "loss": 0.8456, + "step": 2345 + }, + { + "epoch": 0.2100621187531479, + "grad_norm": 0.9932823622276261, + "learning_rate": 1.8348379290196843e-05, + "loss": 0.8864, + "step": 2346 + }, + { + "epoch": 0.210151659298226, + "grad_norm": 0.8910276168675275, + "learning_rate": 1.834678234236853e-05, + "loss": 0.8729, + "step": 2347 + }, + { + "epoch": 0.21024119984330406, + "grad_norm": 0.9666084257721075, + "learning_rate": 1.8345184692436087e-05, + "loss": 0.9274, + "step": 2348 + }, + { + "epoch": 0.21033074038838212, + "grad_norm": 0.8908680022270415, + "learning_rate": 1.83435863405339e-05, + "loss": 0.8732, + "step": 2349 + }, + { + "epoch": 0.21042028093346019, + "grad_norm": 0.8803649263566433, + "learning_rate": 1.834198728679642e-05, + "loss": 0.8832, + "step": 2350 + }, + { + "epoch": 0.21050982147853825, + "grad_norm": 0.9377616078307532, + "learning_rate": 1.8340387531358156e-05, + "loss": 0.8635, + "step": 2351 + }, + { + "epoch": 0.21059936202361632, + "grad_norm": 0.8635539452490355, + "learning_rate": 1.833878707435367e-05, + "loss": 0.8356, + "step": 2352 + }, + { + "epoch": 0.21068890256869438, + "grad_norm": 1.001493615160847, + "learning_rate": 1.8337185915917587e-05, + "loss": 0.8926, + "step": 2353 + }, + { + "epoch": 0.21077844311377245, + "grad_norm": 0.9801629498571586, + "learning_rate": 1.8335584056184597e-05, + "loss": 0.9211, + "step": 2354 + }, + { + "epoch": 0.2108679836588505, + "grad_norm": 0.959325240539797, + "learning_rate": 1.8333981495289437e-05, + "loss": 0.8779, + "step": 2355 + }, + { + "epoch": 0.2109575242039286, + "grad_norm": 0.9093656483913796, + "learning_rate": 1.8332378233366912e-05, + "loss": 0.8038, + "step": 2356 + }, + { + "epoch": 0.21104706474900667, + "grad_norm": 1.010983225526202, + "learning_rate": 1.8330774270551884e-05, + "loss": 0.9086, + "step": 2357 + }, + { + "epoch": 0.21113660529408473, + "grad_norm": 1.1201327384173354, + "learning_rate": 1.832916960697927e-05, + "loss": 0.8897, + "step": 2358 + }, + { + "epoch": 0.2112261458391628, + "grad_norm": 0.8354700243392361, + "learning_rate": 1.832756424278405e-05, + "loss": 0.8484, + "step": 2359 + }, + { + "epoch": 0.21131568638424086, + "grad_norm": 0.9371706155650414, + "learning_rate": 1.8325958178101266e-05, + "loss": 0.8264, + "step": 2360 + }, + { + "epoch": 0.21140522692931893, + "grad_norm": 1.1543065998751798, + "learning_rate": 1.832435141306601e-05, + "loss": 0.8042, + "step": 2361 + }, + { + "epoch": 0.211494767474397, + "grad_norm": 1.1672765163503769, + "learning_rate": 1.832274394781344e-05, + "loss": 0.9222, + "step": 2362 + }, + { + "epoch": 0.21158430801947506, + "grad_norm": 0.8967948503815383, + "learning_rate": 1.8321135782478773e-05, + "loss": 0.81, + "step": 2363 + }, + { + "epoch": 0.21167384856455312, + "grad_norm": 0.9276379971238726, + "learning_rate": 1.8319526917197278e-05, + "loss": 0.8702, + "step": 2364 + }, + { + "epoch": 0.21176338910963122, + "grad_norm": 1.0034197014559743, + "learning_rate": 1.8317917352104287e-05, + "loss": 0.8772, + "step": 2365 + }, + { + "epoch": 0.21185292965470928, + "grad_norm": 0.9963851383438483, + "learning_rate": 1.8316307087335197e-05, + "loss": 0.9241, + "step": 2366 + }, + { + "epoch": 0.21194247019978735, + "grad_norm": 1.034402821663142, + "learning_rate": 1.8314696123025456e-05, + "loss": 0.8914, + "step": 2367 + }, + { + "epoch": 0.2120320107448654, + "grad_norm": 0.9219135549089859, + "learning_rate": 1.8313084459310567e-05, + "loss": 0.8905, + "step": 2368 + }, + { + "epoch": 0.21212155128994348, + "grad_norm": 0.972516040517733, + "learning_rate": 1.8311472096326107e-05, + "loss": 0.854, + "step": 2369 + }, + { + "epoch": 0.21221109183502154, + "grad_norm": 0.9782277892644399, + "learning_rate": 1.83098590342077e-05, + "loss": 0.9286, + "step": 2370 + }, + { + "epoch": 0.2123006323800996, + "grad_norm": 0.9659890813862299, + "learning_rate": 1.830824527309103e-05, + "loss": 0.8964, + "step": 2371 + }, + { + "epoch": 0.21239017292517767, + "grad_norm": 1.0012652565914089, + "learning_rate": 1.830663081311184e-05, + "loss": 0.8075, + "step": 2372 + }, + { + "epoch": 0.21247971347025574, + "grad_norm": 1.119722591134955, + "learning_rate": 1.8305015654405935e-05, + "loss": 0.8757, + "step": 2373 + }, + { + "epoch": 0.21256925401533383, + "grad_norm": 1.0607785324143888, + "learning_rate": 1.8303399797109177e-05, + "loss": 0.8634, + "step": 2374 + }, + { + "epoch": 0.2126587945604119, + "grad_norm": 1.060619050660391, + "learning_rate": 1.830178324135749e-05, + "loss": 0.865, + "step": 2375 + }, + { + "epoch": 0.21274833510548996, + "grad_norm": 1.0206851872511882, + "learning_rate": 1.8300165987286847e-05, + "loss": 0.8723, + "step": 2376 + }, + { + "epoch": 0.21283787565056803, + "grad_norm": 1.089646829848144, + "learning_rate": 1.829854803503329e-05, + "loss": 0.8418, + "step": 2377 + }, + { + "epoch": 0.2129274161956461, + "grad_norm": 0.9354182514621092, + "learning_rate": 1.8296929384732912e-05, + "loss": 0.827, + "step": 2378 + }, + { + "epoch": 0.21301695674072416, + "grad_norm": 1.0359599840938436, + "learning_rate": 1.8295310036521873e-05, + "loss": 0.8735, + "step": 2379 + }, + { + "epoch": 0.21310649728580222, + "grad_norm": 0.9694553494925326, + "learning_rate": 1.8293689990536385e-05, + "loss": 0.8843, + "step": 2380 + }, + { + "epoch": 0.2131960378308803, + "grad_norm": 0.8926400234972416, + "learning_rate": 1.8292069246912722e-05, + "loss": 0.887, + "step": 2381 + }, + { + "epoch": 0.21328557837595835, + "grad_norm": 0.9938703325044396, + "learning_rate": 1.8290447805787215e-05, + "loss": 0.919, + "step": 2382 + }, + { + "epoch": 0.21337511892103644, + "grad_norm": 1.0778689495775973, + "learning_rate": 1.8288825667296258e-05, + "loss": 0.9056, + "step": 2383 + }, + { + "epoch": 0.2134646594661145, + "grad_norm": 0.991945507752043, + "learning_rate": 1.8287202831576292e-05, + "loss": 0.8863, + "step": 2384 + }, + { + "epoch": 0.21355420001119257, + "grad_norm": 1.1842987904262394, + "learning_rate": 1.828557929876383e-05, + "loss": 0.9336, + "step": 2385 + }, + { + "epoch": 0.21364374055627064, + "grad_norm": 0.9559436610716089, + "learning_rate": 1.828395506899544e-05, + "loss": 0.8603, + "step": 2386 + }, + { + "epoch": 0.2137332811013487, + "grad_norm": 1.02937528151375, + "learning_rate": 1.8282330142407744e-05, + "loss": 0.8659, + "step": 2387 + }, + { + "epoch": 0.21382282164642677, + "grad_norm": 1.0355878641550564, + "learning_rate": 1.8280704519137424e-05, + "loss": 0.9109, + "step": 2388 + }, + { + "epoch": 0.21391236219150483, + "grad_norm": 0.9117788276341109, + "learning_rate": 1.8279078199321227e-05, + "loss": 0.8406, + "step": 2389 + }, + { + "epoch": 0.2140019027365829, + "grad_norm": 1.1824253091763357, + "learning_rate": 1.8277451183095948e-05, + "loss": 0.9205, + "step": 2390 + }, + { + "epoch": 0.21409144328166096, + "grad_norm": 0.9267728934433077, + "learning_rate": 1.8275823470598453e-05, + "loss": 0.8937, + "step": 2391 + }, + { + "epoch": 0.21418098382673906, + "grad_norm": 0.8973344687815957, + "learning_rate": 1.8274195061965652e-05, + "loss": 0.8954, + "step": 2392 + }, + { + "epoch": 0.21427052437181712, + "grad_norm": 1.0108183443673422, + "learning_rate": 1.8272565957334533e-05, + "loss": 0.8828, + "step": 2393 + }, + { + "epoch": 0.2143600649168952, + "grad_norm": 1.0290833780973254, + "learning_rate": 1.8270936156842113e-05, + "loss": 0.9551, + "step": 2394 + }, + { + "epoch": 0.21444960546197325, + "grad_norm": 0.9823910298875254, + "learning_rate": 1.8269305660625504e-05, + "loss": 0.8813, + "step": 2395 + }, + { + "epoch": 0.21453914600705132, + "grad_norm": 0.9138915602531238, + "learning_rate": 1.8267674468821847e-05, + "loss": 0.8636, + "step": 2396 + }, + { + "epoch": 0.21462868655212938, + "grad_norm": 1.013238122058016, + "learning_rate": 1.8266042581568355e-05, + "loss": 0.8841, + "step": 2397 + }, + { + "epoch": 0.21471822709720745, + "grad_norm": 0.9314746653929642, + "learning_rate": 1.82644099990023e-05, + "loss": 0.8543, + "step": 2398 + }, + { + "epoch": 0.2148077676422855, + "grad_norm": 0.9615886037125216, + "learning_rate": 1.8262776721261004e-05, + "loss": 0.8606, + "step": 2399 + }, + { + "epoch": 0.21489730818736358, + "grad_norm": 0.9795353347989464, + "learning_rate": 1.826114274848186e-05, + "loss": 0.8525, + "step": 2400 + }, + { + "epoch": 0.21498684873244167, + "grad_norm": 1.0731244977395105, + "learning_rate": 1.8259508080802304e-05, + "loss": 0.902, + "step": 2401 + }, + { + "epoch": 0.21507638927751974, + "grad_norm": 0.9160601494799316, + "learning_rate": 1.8257872718359847e-05, + "loss": 0.8584, + "step": 2402 + }, + { + "epoch": 0.2151659298225978, + "grad_norm": 0.9227231094400433, + "learning_rate": 1.8256236661292047e-05, + "loss": 0.8822, + "step": 2403 + }, + { + "epoch": 0.21525547036767587, + "grad_norm": 0.9434025511349725, + "learning_rate": 1.825459990973652e-05, + "loss": 0.8652, + "step": 2404 + }, + { + "epoch": 0.21534501091275393, + "grad_norm": 0.91101944361123, + "learning_rate": 1.825296246383095e-05, + "loss": 0.8749, + "step": 2405 + }, + { + "epoch": 0.215434551457832, + "grad_norm": 0.9038147704623257, + "learning_rate": 1.8251324323713073e-05, + "loss": 0.8905, + "step": 2406 + }, + { + "epoch": 0.21552409200291006, + "grad_norm": 1.0522085217364545, + "learning_rate": 1.824968548952068e-05, + "loss": 0.9143, + "step": 2407 + }, + { + "epoch": 0.21561363254798813, + "grad_norm": 0.940877365545532, + "learning_rate": 1.824804596139163e-05, + "loss": 0.8757, + "step": 2408 + }, + { + "epoch": 0.2157031730930662, + "grad_norm": 0.9306804031553232, + "learning_rate": 1.824640573946383e-05, + "loss": 0.8752, + "step": 2409 + }, + { + "epoch": 0.21579271363814428, + "grad_norm": 0.9429717658862485, + "learning_rate": 1.824476482387525e-05, + "loss": 0.9239, + "step": 2410 + }, + { + "epoch": 0.21588225418322235, + "grad_norm": 0.9433277125967082, + "learning_rate": 1.8243123214763924e-05, + "loss": 0.9011, + "step": 2411 + }, + { + "epoch": 0.21597179472830041, + "grad_norm": 0.9062348798505817, + "learning_rate": 1.8241480912267932e-05, + "loss": 0.9271, + "step": 2412 + }, + { + "epoch": 0.21606133527337848, + "grad_norm": 1.2752312630537277, + "learning_rate": 1.8239837916525423e-05, + "loss": 0.8966, + "step": 2413 + }, + { + "epoch": 0.21615087581845654, + "grad_norm": 0.8969866084944477, + "learning_rate": 1.82381942276746e-05, + "loss": 0.9156, + "step": 2414 + }, + { + "epoch": 0.2162404163635346, + "grad_norm": 1.004994647556404, + "learning_rate": 1.8236549845853723e-05, + "loss": 0.8822, + "step": 2415 + }, + { + "epoch": 0.21632995690861268, + "grad_norm": 1.107616954536359, + "learning_rate": 1.8234904771201115e-05, + "loss": 0.9268, + "step": 2416 + }, + { + "epoch": 0.21641949745369074, + "grad_norm": 0.8615234920114818, + "learning_rate": 1.8233259003855153e-05, + "loss": 0.8407, + "step": 2417 + }, + { + "epoch": 0.2165090379987688, + "grad_norm": 1.0041899789411581, + "learning_rate": 1.8231612543954272e-05, + "loss": 0.8439, + "step": 2418 + }, + { + "epoch": 0.2165985785438469, + "grad_norm": 0.9616912177434204, + "learning_rate": 1.822996539163697e-05, + "loss": 0.9266, + "step": 2419 + }, + { + "epoch": 0.21668811908892496, + "grad_norm": 0.974390662288401, + "learning_rate": 1.82283175470418e-05, + "loss": 0.8753, + "step": 2420 + }, + { + "epoch": 0.21677765963400303, + "grad_norm": 0.931638048833105, + "learning_rate": 1.8226669010307366e-05, + "loss": 0.9048, + "step": 2421 + }, + { + "epoch": 0.2168672001790811, + "grad_norm": 0.922031028650458, + "learning_rate": 1.8225019781572348e-05, + "loss": 0.8848, + "step": 2422 + }, + { + "epoch": 0.21695674072415916, + "grad_norm": 1.0329411783563305, + "learning_rate": 1.8223369860975466e-05, + "loss": 0.8732, + "step": 2423 + }, + { + "epoch": 0.21704628126923722, + "grad_norm": 0.9676490035827793, + "learning_rate": 1.822171924865551e-05, + "loss": 0.9131, + "step": 2424 + }, + { + "epoch": 0.2171358218143153, + "grad_norm": 0.8814572021818587, + "learning_rate": 1.822006794475132e-05, + "loss": 0.8895, + "step": 2425 + }, + { + "epoch": 0.21722536235939335, + "grad_norm": 0.9400735607711662, + "learning_rate": 1.8218415949401808e-05, + "loss": 0.9035, + "step": 2426 + }, + { + "epoch": 0.21731490290447142, + "grad_norm": 0.8950728216513003, + "learning_rate": 1.821676326274592e-05, + "loss": 0.8957, + "step": 2427 + }, + { + "epoch": 0.2174044434495495, + "grad_norm": 0.935220097707214, + "learning_rate": 1.821510988492269e-05, + "loss": 0.8545, + "step": 2428 + }, + { + "epoch": 0.21749398399462758, + "grad_norm": 1.1479663454499143, + "learning_rate": 1.821345581607118e-05, + "loss": 0.9415, + "step": 2429 + }, + { + "epoch": 0.21758352453970564, + "grad_norm": 1.0230933831638547, + "learning_rate": 1.8211801056330537e-05, + "loss": 0.8363, + "step": 2430 + }, + { + "epoch": 0.2176730650847837, + "grad_norm": 1.0025394868693154, + "learning_rate": 1.8210145605839946e-05, + "loss": 0.8652, + "step": 2431 + }, + { + "epoch": 0.21776260562986177, + "grad_norm": 1.2016130975252066, + "learning_rate": 1.8208489464738664e-05, + "loss": 0.8907, + "step": 2432 + }, + { + "epoch": 0.21785214617493984, + "grad_norm": 1.000661700842076, + "learning_rate": 1.8206832633165996e-05, + "loss": 0.8826, + "step": 2433 + }, + { + "epoch": 0.2179416867200179, + "grad_norm": 0.8823379144012643, + "learning_rate": 1.820517511126131e-05, + "loss": 0.8819, + "step": 2434 + }, + { + "epoch": 0.21803122726509597, + "grad_norm": 1.0012576349800977, + "learning_rate": 1.820351689916403e-05, + "loss": 0.8218, + "step": 2435 + }, + { + "epoch": 0.21812076781017403, + "grad_norm": 0.9264567782586764, + "learning_rate": 1.8201857997013644e-05, + "loss": 0.8521, + "step": 2436 + }, + { + "epoch": 0.21821030835525212, + "grad_norm": 1.005346150299651, + "learning_rate": 1.8200198404949688e-05, + "loss": 0.859, + "step": 2437 + }, + { + "epoch": 0.2182998489003302, + "grad_norm": 0.9123350117823129, + "learning_rate": 1.819853812311177e-05, + "loss": 0.8495, + "step": 2438 + }, + { + "epoch": 0.21838938944540826, + "grad_norm": 1.027033039433404, + "learning_rate": 1.8196877151639537e-05, + "loss": 0.9043, + "step": 2439 + }, + { + "epoch": 0.21847892999048632, + "grad_norm": 0.972354150722636, + "learning_rate": 1.8195215490672708e-05, + "loss": 0.9621, + "step": 2440 + }, + { + "epoch": 0.21856847053556439, + "grad_norm": 0.927727867401141, + "learning_rate": 1.819355314035106e-05, + "loss": 0.8606, + "step": 2441 + }, + { + "epoch": 0.21865801108064245, + "grad_norm": 1.0856583066609942, + "learning_rate": 1.819189010081442e-05, + "loss": 0.8233, + "step": 2442 + }, + { + "epoch": 0.21874755162572052, + "grad_norm": 1.0679478390735815, + "learning_rate": 1.819022637220268e-05, + "loss": 0.8729, + "step": 2443 + }, + { + "epoch": 0.21883709217079858, + "grad_norm": 0.9618063368678332, + "learning_rate": 1.8188561954655792e-05, + "loss": 0.9243, + "step": 2444 + }, + { + "epoch": 0.21892663271587665, + "grad_norm": 0.9398162238441737, + "learning_rate": 1.8186896848313752e-05, + "loss": 0.8522, + "step": 2445 + }, + { + "epoch": 0.21901617326095474, + "grad_norm": 1.0485128452469143, + "learning_rate": 1.818523105331663e-05, + "loss": 0.8806, + "step": 2446 + }, + { + "epoch": 0.2191057138060328, + "grad_norm": 0.876430435557789, + "learning_rate": 1.818356456980454e-05, + "loss": 0.8728, + "step": 2447 + }, + { + "epoch": 0.21919525435111087, + "grad_norm": 1.0042534113970187, + "learning_rate": 1.8181897397917672e-05, + "loss": 0.8558, + "step": 2448 + }, + { + "epoch": 0.21928479489618893, + "grad_norm": 1.0157550710124708, + "learning_rate": 1.8180229537796257e-05, + "loss": 0.9105, + "step": 2449 + }, + { + "epoch": 0.219374335441267, + "grad_norm": 0.9741772651910044, + "learning_rate": 1.8178560989580586e-05, + "loss": 0.8689, + "step": 2450 + }, + { + "epoch": 0.21946387598634506, + "grad_norm": 0.9312969441118285, + "learning_rate": 1.817689175341102e-05, + "loss": 0.9185, + "step": 2451 + }, + { + "epoch": 0.21955341653142313, + "grad_norm": 1.1572547846458558, + "learning_rate": 1.8175221829427966e-05, + "loss": 0.9016, + "step": 2452 + }, + { + "epoch": 0.2196429570765012, + "grad_norm": 1.0217207796068877, + "learning_rate": 1.817355121777189e-05, + "loss": 0.9161, + "step": 2453 + }, + { + "epoch": 0.21973249762157926, + "grad_norm": 0.9287415250858831, + "learning_rate": 1.8171879918583322e-05, + "loss": 0.9167, + "step": 2454 + }, + { + "epoch": 0.21982203816665735, + "grad_norm": 0.9328585528642417, + "learning_rate": 1.8170207932002844e-05, + "loss": 0.8416, + "step": 2455 + }, + { + "epoch": 0.21991157871173542, + "grad_norm": 0.9184961769454396, + "learning_rate": 1.8168535258171102e-05, + "loss": 0.8781, + "step": 2456 + }, + { + "epoch": 0.22000111925681348, + "grad_norm": 0.9715845873701263, + "learning_rate": 1.8166861897228788e-05, + "loss": 0.8624, + "step": 2457 + }, + { + "epoch": 0.22009065980189155, + "grad_norm": 0.9862747398022517, + "learning_rate": 1.8165187849316668e-05, + "loss": 0.8596, + "step": 2458 + }, + { + "epoch": 0.2201802003469696, + "grad_norm": 0.8993864243402101, + "learning_rate": 1.816351311457555e-05, + "loss": 0.891, + "step": 2459 + }, + { + "epoch": 0.22026974089204768, + "grad_norm": 1.062569435992692, + "learning_rate": 1.8161837693146316e-05, + "loss": 0.8735, + "step": 2460 + }, + { + "epoch": 0.22035928143712574, + "grad_norm": 0.9205036651208217, + "learning_rate": 1.816016158516989e-05, + "loss": 0.8045, + "step": 2461 + }, + { + "epoch": 0.2204488219822038, + "grad_norm": 1.1680790181822271, + "learning_rate": 1.8158484790787265e-05, + "loss": 0.8345, + "step": 2462 + }, + { + "epoch": 0.22053836252728187, + "grad_norm": 0.9703330349505758, + "learning_rate": 1.8156807310139482e-05, + "loss": 0.8716, + "step": 2463 + }, + { + "epoch": 0.22062790307235997, + "grad_norm": 1.010707673203592, + "learning_rate": 1.8155129143367653e-05, + "loss": 0.864, + "step": 2464 + }, + { + "epoch": 0.22071744361743803, + "grad_norm": 0.8897449856767962, + "learning_rate": 1.8153450290612933e-05, + "loss": 0.8504, + "step": 2465 + }, + { + "epoch": 0.2208069841625161, + "grad_norm": 0.8877515188492499, + "learning_rate": 1.8151770752016544e-05, + "loss": 0.8579, + "step": 2466 + }, + { + "epoch": 0.22089652470759416, + "grad_norm": 0.9435996370183599, + "learning_rate": 1.8150090527719765e-05, + "loss": 0.8604, + "step": 2467 + }, + { + "epoch": 0.22098606525267223, + "grad_norm": 0.8918097750761799, + "learning_rate": 1.8148409617863926e-05, + "loss": 0.8707, + "step": 2468 + }, + { + "epoch": 0.2210756057977503, + "grad_norm": 1.1948767801438525, + "learning_rate": 1.8146728022590426e-05, + "loss": 0.8861, + "step": 2469 + }, + { + "epoch": 0.22116514634282836, + "grad_norm": 1.285702211040259, + "learning_rate": 1.8145045742040716e-05, + "loss": 0.8666, + "step": 2470 + }, + { + "epoch": 0.22125468688790642, + "grad_norm": 0.9614767806921428, + "learning_rate": 1.8143362776356294e-05, + "loss": 0.8984, + "step": 2471 + }, + { + "epoch": 0.22134422743298449, + "grad_norm": 1.1699012842176681, + "learning_rate": 1.8141679125678736e-05, + "loss": 0.9143, + "step": 2472 + }, + { + "epoch": 0.22143376797806258, + "grad_norm": 0.9472735651683517, + "learning_rate": 1.813999479014966e-05, + "loss": 0.8561, + "step": 2473 + }, + { + "epoch": 0.22152330852314064, + "grad_norm": 0.9579782491725819, + "learning_rate": 1.8138309769910747e-05, + "loss": 0.8876, + "step": 2474 + }, + { + "epoch": 0.2216128490682187, + "grad_norm": 1.1913490035421463, + "learning_rate": 1.813662406510374e-05, + "loss": 0.8718, + "step": 2475 + }, + { + "epoch": 0.22170238961329677, + "grad_norm": 0.8864942915515203, + "learning_rate": 1.8134937675870427e-05, + "loss": 0.7986, + "step": 2476 + }, + { + "epoch": 0.22179193015837484, + "grad_norm": 0.9465771328442915, + "learning_rate": 1.813325060235267e-05, + "loss": 0.9006, + "step": 2477 + }, + { + "epoch": 0.2218814707034529, + "grad_norm": 0.9343366745027019, + "learning_rate": 1.8131562844692375e-05, + "loss": 0.8496, + "step": 2478 + }, + { + "epoch": 0.22197101124853097, + "grad_norm": 0.8754879707723164, + "learning_rate": 1.812987440303151e-05, + "loss": 0.8571, + "step": 2479 + }, + { + "epoch": 0.22206055179360903, + "grad_norm": 0.9822651029684982, + "learning_rate": 1.8128185277512106e-05, + "loss": 0.8728, + "step": 2480 + }, + { + "epoch": 0.2221500923386871, + "grad_norm": 0.9125410538711639, + "learning_rate": 1.8126495468276242e-05, + "loss": 0.8659, + "step": 2481 + }, + { + "epoch": 0.2222396328837652, + "grad_norm": 0.9934659712844545, + "learning_rate": 1.812480497546606e-05, + "loss": 0.923, + "step": 2482 + }, + { + "epoch": 0.22232917342884326, + "grad_norm": 0.9818721535560684, + "learning_rate": 1.8123113799223763e-05, + "loss": 0.9276, + "step": 2483 + }, + { + "epoch": 0.22241871397392132, + "grad_norm": 0.9329367212816099, + "learning_rate": 1.8121421939691602e-05, + "loss": 0.8995, + "step": 2484 + }, + { + "epoch": 0.2225082545189994, + "grad_norm": 0.9631879446163104, + "learning_rate": 1.8119729397011892e-05, + "loss": 0.8651, + "step": 2485 + }, + { + "epoch": 0.22259779506407745, + "grad_norm": 1.0095514931491958, + "learning_rate": 1.8118036171327006e-05, + "loss": 0.8314, + "step": 2486 + }, + { + "epoch": 0.22268733560915552, + "grad_norm": 0.9431351183531096, + "learning_rate": 1.811634226277937e-05, + "loss": 0.904, + "step": 2487 + }, + { + "epoch": 0.22277687615423358, + "grad_norm": 1.0513438756757167, + "learning_rate": 1.8114647671511474e-05, + "loss": 0.8897, + "step": 2488 + }, + { + "epoch": 0.22286641669931165, + "grad_norm": 0.9002681160903409, + "learning_rate": 1.8112952397665858e-05, + "loss": 0.8495, + "step": 2489 + }, + { + "epoch": 0.2229559572443897, + "grad_norm": 0.8906035776740626, + "learning_rate": 1.8111256441385125e-05, + "loss": 0.9004, + "step": 2490 + }, + { + "epoch": 0.2230454977894678, + "grad_norm": 0.9453921528207156, + "learning_rate": 1.810955980281193e-05, + "loss": 0.9041, + "step": 2491 + }, + { + "epoch": 0.22313503833454587, + "grad_norm": 0.9175716939079239, + "learning_rate": 1.8107862482088994e-05, + "loss": 0.8167, + "step": 2492 + }, + { + "epoch": 0.22322457887962394, + "grad_norm": 0.9147878762136227, + "learning_rate": 1.8106164479359083e-05, + "loss": 0.8602, + "step": 2493 + }, + { + "epoch": 0.223314119424702, + "grad_norm": 0.9892504733612675, + "learning_rate": 1.8104465794765034e-05, + "loss": 0.8904, + "step": 2494 + }, + { + "epoch": 0.22340365996978007, + "grad_norm": 0.9451410722728956, + "learning_rate": 1.8102766428449735e-05, + "loss": 0.9189, + "step": 2495 + }, + { + "epoch": 0.22349320051485813, + "grad_norm": 0.9489445999870919, + "learning_rate": 1.8101066380556127e-05, + "loss": 0.8843, + "step": 2496 + }, + { + "epoch": 0.2235827410599362, + "grad_norm": 0.8835652795143871, + "learning_rate": 1.8099365651227213e-05, + "loss": 0.8384, + "step": 2497 + }, + { + "epoch": 0.22367228160501426, + "grad_norm": 1.0201550048896366, + "learning_rate": 1.809766424060605e-05, + "loss": 0.9434, + "step": 2498 + }, + { + "epoch": 0.22376182215009233, + "grad_norm": 1.0618140225731325, + "learning_rate": 1.8095962148835768e-05, + "loss": 0.909, + "step": 2499 + }, + { + "epoch": 0.22385136269517042, + "grad_norm": 0.9767501354402025, + "learning_rate": 1.8094259376059527e-05, + "loss": 0.8983, + "step": 2500 + }, + { + "epoch": 0.22394090324024848, + "grad_norm": 0.898521627981632, + "learning_rate": 1.8092555922420564e-05, + "loss": 0.8936, + "step": 2501 + }, + { + "epoch": 0.22403044378532655, + "grad_norm": 1.0039108021537608, + "learning_rate": 1.8090851788062167e-05, + "loss": 0.8683, + "step": 2502 + }, + { + "epoch": 0.22411998433040461, + "grad_norm": 0.9528426183103165, + "learning_rate": 1.8089146973127688e-05, + "loss": 0.8829, + "step": 2503 + }, + { + "epoch": 0.22420952487548268, + "grad_norm": 0.9658704081880096, + "learning_rate": 1.808744147776052e-05, + "loss": 0.8321, + "step": 2504 + }, + { + "epoch": 0.22429906542056074, + "grad_norm": 0.9479741464234925, + "learning_rate": 1.808573530210413e-05, + "loss": 0.8399, + "step": 2505 + }, + { + "epoch": 0.2243886059656388, + "grad_norm": 1.000469194174804, + "learning_rate": 1.808402844630204e-05, + "loss": 0.8924, + "step": 2506 + }, + { + "epoch": 0.22447814651071687, + "grad_norm": 0.9263997781239804, + "learning_rate": 1.808232091049782e-05, + "loss": 0.8764, + "step": 2507 + }, + { + "epoch": 0.22456768705579494, + "grad_norm": 0.8966692868755989, + "learning_rate": 1.8080612694835096e-05, + "loss": 0.8927, + "step": 2508 + }, + { + "epoch": 0.22465722760087303, + "grad_norm": 1.0767165332844624, + "learning_rate": 1.8078903799457572e-05, + "loss": 0.9091, + "step": 2509 + }, + { + "epoch": 0.2247467681459511, + "grad_norm": 1.0488003354563713, + "learning_rate": 1.8077194224508983e-05, + "loss": 0.8488, + "step": 2510 + }, + { + "epoch": 0.22483630869102916, + "grad_norm": 1.0244703484057969, + "learning_rate": 1.807548397013314e-05, + "loss": 0.848, + "step": 2511 + }, + { + "epoch": 0.22492584923610723, + "grad_norm": 0.9580782040359516, + "learning_rate": 1.80737730364739e-05, + "loss": 0.8626, + "step": 2512 + }, + { + "epoch": 0.2250153897811853, + "grad_norm": 0.9119457192277778, + "learning_rate": 1.8072061423675183e-05, + "loss": 0.8546, + "step": 2513 + }, + { + "epoch": 0.22510493032626336, + "grad_norm": 1.207608081541003, + "learning_rate": 1.807034913188096e-05, + "loss": 0.9042, + "step": 2514 + }, + { + "epoch": 0.22519447087134142, + "grad_norm": 0.9662483204068355, + "learning_rate": 1.806863616123527e-05, + "loss": 0.9431, + "step": 2515 + }, + { + "epoch": 0.2252840114164195, + "grad_norm": 0.8922635174027994, + "learning_rate": 1.8066922511882198e-05, + "loss": 0.8136, + "step": 2516 + }, + { + "epoch": 0.22537355196149755, + "grad_norm": 0.9582239887819564, + "learning_rate": 1.8065208183965893e-05, + "loss": 0.8781, + "step": 2517 + }, + { + "epoch": 0.22546309250657565, + "grad_norm": 1.0434420539541909, + "learning_rate": 1.8063493177630556e-05, + "loss": 0.947, + "step": 2518 + }, + { + "epoch": 0.2255526330516537, + "grad_norm": 0.9276314397686056, + "learning_rate": 1.806177749302045e-05, + "loss": 0.8937, + "step": 2519 + }, + { + "epoch": 0.22564217359673178, + "grad_norm": 0.9631735141876852, + "learning_rate": 1.8060061130279895e-05, + "loss": 0.8675, + "step": 2520 + }, + { + "epoch": 0.22573171414180984, + "grad_norm": 0.9808146663870502, + "learning_rate": 1.8058344089553263e-05, + "loss": 0.854, + "step": 2521 + }, + { + "epoch": 0.2258212546868879, + "grad_norm": 1.1222796833599575, + "learning_rate": 1.805662637098498e-05, + "loss": 0.9385, + "step": 2522 + }, + { + "epoch": 0.22591079523196597, + "grad_norm": 0.9275537332540574, + "learning_rate": 1.8054907974719547e-05, + "loss": 0.8658, + "step": 2523 + }, + { + "epoch": 0.22600033577704404, + "grad_norm": 1.0645121579922552, + "learning_rate": 1.80531889009015e-05, + "loss": 0.8641, + "step": 2524 + }, + { + "epoch": 0.2260898763221221, + "grad_norm": 0.9355536910913024, + "learning_rate": 1.8051469149675448e-05, + "loss": 0.8622, + "step": 2525 + }, + { + "epoch": 0.22617941686720017, + "grad_norm": 0.9252707911114164, + "learning_rate": 1.8049748721186046e-05, + "loss": 0.8895, + "step": 2526 + }, + { + "epoch": 0.22626895741227826, + "grad_norm": 1.0058931450989164, + "learning_rate": 1.8048027615578018e-05, + "loss": 0.8288, + "step": 2527 + }, + { + "epoch": 0.22635849795735632, + "grad_norm": 1.0202690460620532, + "learning_rate": 1.8046305832996128e-05, + "loss": 0.8803, + "step": 2528 + }, + { + "epoch": 0.2264480385024344, + "grad_norm": 1.0709501224161226, + "learning_rate": 1.8044583373585213e-05, + "loss": 0.8407, + "step": 2529 + }, + { + "epoch": 0.22653757904751246, + "grad_norm": 0.8958129508180114, + "learning_rate": 1.804286023749016e-05, + "loss": 0.8152, + "step": 2530 + }, + { + "epoch": 0.22662711959259052, + "grad_norm": 0.9467621134233632, + "learning_rate": 1.8041136424855915e-05, + "loss": 0.8865, + "step": 2531 + }, + { + "epoch": 0.22671666013766859, + "grad_norm": 1.0505031675590963, + "learning_rate": 1.8039411935827474e-05, + "loss": 0.915, + "step": 2532 + }, + { + "epoch": 0.22680620068274665, + "grad_norm": 0.933142619778036, + "learning_rate": 1.8037686770549904e-05, + "loss": 0.9037, + "step": 2533 + }, + { + "epoch": 0.22689574122782472, + "grad_norm": 0.8432244177180609, + "learning_rate": 1.803596092916831e-05, + "loss": 0.8659, + "step": 2534 + }, + { + "epoch": 0.22698528177290278, + "grad_norm": 1.0677966355782909, + "learning_rate": 1.8034234411827874e-05, + "loss": 0.8628, + "step": 2535 + }, + { + "epoch": 0.22707482231798087, + "grad_norm": 1.0191266204932303, + "learning_rate": 1.8032507218673817e-05, + "loss": 0.9117, + "step": 2536 + }, + { + "epoch": 0.22716436286305894, + "grad_norm": 1.0446812903638734, + "learning_rate": 1.803077934985143e-05, + "loss": 0.9206, + "step": 2537 + }, + { + "epoch": 0.227253903408137, + "grad_norm": 1.0669702997515123, + "learning_rate": 1.8029050805506056e-05, + "loss": 0.8787, + "step": 2538 + }, + { + "epoch": 0.22734344395321507, + "grad_norm": 0.9555762543954538, + "learning_rate": 1.8027321585783087e-05, + "loss": 0.866, + "step": 2539 + }, + { + "epoch": 0.22743298449829313, + "grad_norm": 1.0120429950640326, + "learning_rate": 1.802559169082799e-05, + "loss": 0.8081, + "step": 2540 + }, + { + "epoch": 0.2275225250433712, + "grad_norm": 0.9086390378975789, + "learning_rate": 1.802386112078627e-05, + "loss": 0.8899, + "step": 2541 + }, + { + "epoch": 0.22761206558844926, + "grad_norm": 0.956931408650241, + "learning_rate": 1.8022129875803503e-05, + "loss": 0.8861, + "step": 2542 + }, + { + "epoch": 0.22770160613352733, + "grad_norm": 1.0290655917010858, + "learning_rate": 1.8020397956025308e-05, + "loss": 0.874, + "step": 2543 + }, + { + "epoch": 0.2277911466786054, + "grad_norm": 0.9992495510535807, + "learning_rate": 1.8018665361597378e-05, + "loss": 0.9552, + "step": 2544 + }, + { + "epoch": 0.2278806872236835, + "grad_norm": 0.9033937158354753, + "learning_rate": 1.8016932092665443e-05, + "loss": 0.9056, + "step": 2545 + }, + { + "epoch": 0.22797022776876155, + "grad_norm": 1.0437158567645224, + "learning_rate": 1.801519814937531e-05, + "loss": 0.8871, + "step": 2546 + }, + { + "epoch": 0.22805976831383962, + "grad_norm": 0.8873756681422895, + "learning_rate": 1.8013463531872826e-05, + "loss": 0.9109, + "step": 2547 + }, + { + "epoch": 0.22814930885891768, + "grad_norm": 1.0581781924497864, + "learning_rate": 1.8011728240303907e-05, + "loss": 0.9178, + "step": 2548 + }, + { + "epoch": 0.22823884940399575, + "grad_norm": 1.079651431634101, + "learning_rate": 1.8009992274814507e-05, + "loss": 0.8827, + "step": 2549 + }, + { + "epoch": 0.2283283899490738, + "grad_norm": 1.032263821563887, + "learning_rate": 1.8008255635550666e-05, + "loss": 0.8941, + "step": 2550 + }, + { + "epoch": 0.22841793049415188, + "grad_norm": 0.9220953600277201, + "learning_rate": 1.800651832265846e-05, + "loss": 0.8434, + "step": 2551 + }, + { + "epoch": 0.22850747103922994, + "grad_norm": 1.054601456870059, + "learning_rate": 1.8004780336284016e-05, + "loss": 0.9479, + "step": 2552 + }, + { + "epoch": 0.228597011584308, + "grad_norm": 1.0085492112600614, + "learning_rate": 1.800304167657354e-05, + "loss": 0.8401, + "step": 2553 + }, + { + "epoch": 0.2286865521293861, + "grad_norm": 0.9676772516323091, + "learning_rate": 1.8001302343673276e-05, + "loss": 0.9005, + "step": 2554 + }, + { + "epoch": 0.22877609267446417, + "grad_norm": 0.8678914177267638, + "learning_rate": 1.799956233772953e-05, + "loss": 0.8824, + "step": 2555 + }, + { + "epoch": 0.22886563321954223, + "grad_norm": 1.0702126246287937, + "learning_rate": 1.799782165888867e-05, + "loss": 0.8676, + "step": 2556 + }, + { + "epoch": 0.2289551737646203, + "grad_norm": 1.3121248411028528, + "learning_rate": 1.799608030729712e-05, + "loss": 0.8896, + "step": 2557 + }, + { + "epoch": 0.22904471430969836, + "grad_norm": 1.0131661199832729, + "learning_rate": 1.799433828310135e-05, + "loss": 0.893, + "step": 2558 + }, + { + "epoch": 0.22913425485477643, + "grad_norm": 0.9043152855485418, + "learning_rate": 1.799259558644789e-05, + "loss": 0.8607, + "step": 2559 + }, + { + "epoch": 0.2292237953998545, + "grad_norm": 1.1801178679964865, + "learning_rate": 1.799085221748334e-05, + "loss": 0.9057, + "step": 2560 + }, + { + "epoch": 0.22931333594493256, + "grad_norm": 0.9315033449661035, + "learning_rate": 1.7989108176354335e-05, + "loss": 0.8864, + "step": 2561 + }, + { + "epoch": 0.22940287649001062, + "grad_norm": 1.1104694345334944, + "learning_rate": 1.798736346320759e-05, + "loss": 0.9229, + "step": 2562 + }, + { + "epoch": 0.2294924170350887, + "grad_norm": 0.9902123081478843, + "learning_rate": 1.7985618078189854e-05, + "loss": 0.8994, + "step": 2563 + }, + { + "epoch": 0.22958195758016678, + "grad_norm": 0.8337760711564342, + "learning_rate": 1.798387202144795e-05, + "loss": 0.9, + "step": 2564 + }, + { + "epoch": 0.22967149812524484, + "grad_norm": 0.9593759546794962, + "learning_rate": 1.7982125293128752e-05, + "loss": 0.8324, + "step": 2565 + }, + { + "epoch": 0.2297610386703229, + "grad_norm": 1.2005911662238826, + "learning_rate": 1.798037789337918e-05, + "loss": 0.9079, + "step": 2566 + }, + { + "epoch": 0.22985057921540097, + "grad_norm": 0.9265124694783007, + "learning_rate": 1.7978629822346233e-05, + "loss": 0.8878, + "step": 2567 + }, + { + "epoch": 0.22994011976047904, + "grad_norm": 0.8541826945204339, + "learning_rate": 1.797688108017694e-05, + "loss": 0.8667, + "step": 2568 + }, + { + "epoch": 0.2300296603055571, + "grad_norm": 0.9058874652277398, + "learning_rate": 1.7975131667018403e-05, + "loss": 0.8833, + "step": 2569 + }, + { + "epoch": 0.23011920085063517, + "grad_norm": 0.9039226307305662, + "learning_rate": 1.7973381583017783e-05, + "loss": 0.9017, + "step": 2570 + }, + { + "epoch": 0.23020874139571323, + "grad_norm": 0.9137581852621146, + "learning_rate": 1.7971630828322285e-05, + "loss": 0.8998, + "step": 2571 + }, + { + "epoch": 0.23029828194079133, + "grad_norm": 0.9713535632572307, + "learning_rate": 1.796987940307918e-05, + "loss": 0.9105, + "step": 2572 + }, + { + "epoch": 0.2303878224858694, + "grad_norm": 0.9935165515419422, + "learning_rate": 1.796812730743579e-05, + "loss": 0.8464, + "step": 2573 + }, + { + "epoch": 0.23047736303094746, + "grad_norm": 0.9919506810302618, + "learning_rate": 1.7966374541539497e-05, + "loss": 0.9083, + "step": 2574 + }, + { + "epoch": 0.23056690357602552, + "grad_norm": 1.005897362272084, + "learning_rate": 1.796462110553774e-05, + "loss": 0.9058, + "step": 2575 + }, + { + "epoch": 0.2306564441211036, + "grad_norm": 0.9616937545104918, + "learning_rate": 1.7962866999578005e-05, + "loss": 0.8934, + "step": 2576 + }, + { + "epoch": 0.23074598466618165, + "grad_norm": 0.9765589070992285, + "learning_rate": 1.796111222380785e-05, + "loss": 0.8947, + "step": 2577 + }, + { + "epoch": 0.23083552521125972, + "grad_norm": 1.0531262840183424, + "learning_rate": 1.7959356778374878e-05, + "loss": 0.8806, + "step": 2578 + }, + { + "epoch": 0.23092506575633778, + "grad_norm": 0.9276498025173632, + "learning_rate": 1.7957600663426747e-05, + "loss": 0.8567, + "step": 2579 + }, + { + "epoch": 0.23101460630141585, + "grad_norm": 1.1162326068192843, + "learning_rate": 1.7955843879111182e-05, + "loss": 0.8748, + "step": 2580 + }, + { + "epoch": 0.23110414684649394, + "grad_norm": 0.9172631756008399, + "learning_rate": 1.795408642557596e-05, + "loss": 0.8775, + "step": 2581 + }, + { + "epoch": 0.231193687391572, + "grad_norm": 1.0451464888650999, + "learning_rate": 1.7952328302968904e-05, + "loss": 0.8192, + "step": 2582 + }, + { + "epoch": 0.23128322793665007, + "grad_norm": 0.9125392466065658, + "learning_rate": 1.7950569511437903e-05, + "loss": 0.8945, + "step": 2583 + }, + { + "epoch": 0.23137276848172814, + "grad_norm": 0.969917390519741, + "learning_rate": 1.7948810051130907e-05, + "loss": 0.9172, + "step": 2584 + }, + { + "epoch": 0.2314623090268062, + "grad_norm": 0.9859667102899877, + "learning_rate": 1.794704992219591e-05, + "loss": 0.9144, + "step": 2585 + }, + { + "epoch": 0.23155184957188427, + "grad_norm": 0.8949310569260401, + "learning_rate": 1.7945289124780973e-05, + "loss": 0.8174, + "step": 2586 + }, + { + "epoch": 0.23164139011696233, + "grad_norm": 0.935230584064052, + "learning_rate": 1.7943527659034204e-05, + "loss": 0.8717, + "step": 2587 + }, + { + "epoch": 0.2317309306620404, + "grad_norm": 0.9503475459266788, + "learning_rate": 1.7941765525103777e-05, + "loss": 0.8336, + "step": 2588 + }, + { + "epoch": 0.23182047120711846, + "grad_norm": 0.9609321883625781, + "learning_rate": 1.794000272313791e-05, + "loss": 0.8623, + "step": 2589 + }, + { + "epoch": 0.23191001175219655, + "grad_norm": 0.9345102490435835, + "learning_rate": 1.793823925328489e-05, + "loss": 0.89, + "step": 2590 + }, + { + "epoch": 0.23199955229727462, + "grad_norm": 0.9438304667160562, + "learning_rate": 1.7936475115693054e-05, + "loss": 0.8851, + "step": 2591 + }, + { + "epoch": 0.23208909284235268, + "grad_norm": 0.9828322677280299, + "learning_rate": 1.793471031051079e-05, + "loss": 0.85, + "step": 2592 + }, + { + "epoch": 0.23217863338743075, + "grad_norm": 1.0343131063016096, + "learning_rate": 1.7932944837886556e-05, + "loss": 0.921, + "step": 2593 + }, + { + "epoch": 0.23226817393250881, + "grad_norm": 1.0114673934588416, + "learning_rate": 1.793117869796885e-05, + "loss": 0.8872, + "step": 2594 + }, + { + "epoch": 0.23235771447758688, + "grad_norm": 0.9868974783342381, + "learning_rate": 1.7929411890906237e-05, + "loss": 0.9114, + "step": 2595 + }, + { + "epoch": 0.23244725502266494, + "grad_norm": 0.9016025942968532, + "learning_rate": 1.7927644416847337e-05, + "loss": 0.8787, + "step": 2596 + }, + { + "epoch": 0.232536795567743, + "grad_norm": 0.9567110155335192, + "learning_rate": 1.7925876275940822e-05, + "loss": 0.8878, + "step": 2597 + }, + { + "epoch": 0.23262633611282107, + "grad_norm": 0.952703649408506, + "learning_rate": 1.7924107468335422e-05, + "loss": 0.8732, + "step": 2598 + }, + { + "epoch": 0.23271587665789917, + "grad_norm": 1.035802017035399, + "learning_rate": 1.7922337994179925e-05, + "loss": 0.8149, + "step": 2599 + }, + { + "epoch": 0.23280541720297723, + "grad_norm": 0.95004596292956, + "learning_rate": 1.792056785362317e-05, + "loss": 0.8232, + "step": 2600 + }, + { + "epoch": 0.2328949577480553, + "grad_norm": 0.9581760059483662, + "learning_rate": 1.7918797046814065e-05, + "loss": 0.9145, + "step": 2601 + }, + { + "epoch": 0.23298449829313336, + "grad_norm": 1.0471642009871134, + "learning_rate": 1.7917025573901552e-05, + "loss": 0.8696, + "step": 2602 + }, + { + "epoch": 0.23307403883821143, + "grad_norm": 0.9364149465864768, + "learning_rate": 1.7915253435034647e-05, + "loss": 0.8139, + "step": 2603 + }, + { + "epoch": 0.2331635793832895, + "grad_norm": 0.9521297694837739, + "learning_rate": 1.791348063036242e-05, + "loss": 0.8289, + "step": 2604 + }, + { + "epoch": 0.23325311992836756, + "grad_norm": 0.9412998392569706, + "learning_rate": 1.7911707160033986e-05, + "loss": 0.9158, + "step": 2605 + }, + { + "epoch": 0.23334266047344562, + "grad_norm": 0.9716043680940335, + "learning_rate": 1.7909933024198528e-05, + "loss": 0.8187, + "step": 2606 + }, + { + "epoch": 0.2334322010185237, + "grad_norm": 0.9245215907332207, + "learning_rate": 1.790815822300528e-05, + "loss": 0.8452, + "step": 2607 + }, + { + "epoch": 0.23352174156360178, + "grad_norm": 1.0169525429323707, + "learning_rate": 1.7906382756603536e-05, + "loss": 0.8704, + "step": 2608 + }, + { + "epoch": 0.23361128210867985, + "grad_norm": 0.9486720265347628, + "learning_rate": 1.7904606625142636e-05, + "loss": 0.8845, + "step": 2609 + }, + { + "epoch": 0.2337008226537579, + "grad_norm": 0.9985718616356085, + "learning_rate": 1.7902829828771984e-05, + "loss": 0.8662, + "step": 2610 + }, + { + "epoch": 0.23379036319883598, + "grad_norm": 1.0079681307614403, + "learning_rate": 1.7901052367641047e-05, + "loss": 0.877, + "step": 2611 + }, + { + "epoch": 0.23387990374391404, + "grad_norm": 1.2877814644958372, + "learning_rate": 1.7899274241899324e-05, + "loss": 0.8652, + "step": 2612 + }, + { + "epoch": 0.2339694442889921, + "grad_norm": 1.1685013204505492, + "learning_rate": 1.7897495451696395e-05, + "loss": 0.8939, + "step": 2613 + }, + { + "epoch": 0.23405898483407017, + "grad_norm": 0.9271524495405291, + "learning_rate": 1.7895715997181887e-05, + "loss": 0.9014, + "step": 2614 + }, + { + "epoch": 0.23414852537914824, + "grad_norm": 0.9605270410006715, + "learning_rate": 1.7893935878505477e-05, + "loss": 0.9317, + "step": 2615 + }, + { + "epoch": 0.2342380659242263, + "grad_norm": 1.0457142015273801, + "learning_rate": 1.7892155095816904e-05, + "loss": 0.8972, + "step": 2616 + }, + { + "epoch": 0.2343276064693044, + "grad_norm": 0.8897417700216302, + "learning_rate": 1.7890373649265967e-05, + "loss": 0.8684, + "step": 2617 + }, + { + "epoch": 0.23441714701438246, + "grad_norm": 0.9863290835446341, + "learning_rate": 1.7888591539002506e-05, + "loss": 0.8635, + "step": 2618 + }, + { + "epoch": 0.23450668755946052, + "grad_norm": 0.8763130093836499, + "learning_rate": 1.7886808765176433e-05, + "loss": 0.8602, + "step": 2619 + }, + { + "epoch": 0.2345962281045386, + "grad_norm": 1.0029768902041363, + "learning_rate": 1.7885025327937707e-05, + "loss": 0.8474, + "step": 2620 + }, + { + "epoch": 0.23468576864961666, + "grad_norm": 0.9938746099417956, + "learning_rate": 1.7883241227436346e-05, + "loss": 0.8751, + "step": 2621 + }, + { + "epoch": 0.23477530919469472, + "grad_norm": 1.0819811831139574, + "learning_rate": 1.7881456463822426e-05, + "loss": 0.8039, + "step": 2622 + }, + { + "epoch": 0.23486484973977279, + "grad_norm": 1.075059917708264, + "learning_rate": 1.7879671037246063e-05, + "loss": 0.904, + "step": 2623 + }, + { + "epoch": 0.23495439028485085, + "grad_norm": 0.952609111176791, + "learning_rate": 1.7877884947857457e-05, + "loss": 0.8575, + "step": 2624 + }, + { + "epoch": 0.23504393082992892, + "grad_norm": 0.981070468885405, + "learning_rate": 1.787609819580684e-05, + "loss": 0.8534, + "step": 2625 + }, + { + "epoch": 0.235133471375007, + "grad_norm": 0.8934496249456562, + "learning_rate": 1.7874310781244505e-05, + "loss": 0.8485, + "step": 2626 + }, + { + "epoch": 0.23522301192008507, + "grad_norm": 0.8662848566055952, + "learning_rate": 1.787252270432081e-05, + "loss": 0.8984, + "step": 2627 + }, + { + "epoch": 0.23531255246516314, + "grad_norm": 0.9178788506593065, + "learning_rate": 1.7870733965186158e-05, + "loss": 0.8762, + "step": 2628 + }, + { + "epoch": 0.2354020930102412, + "grad_norm": 0.9626225811255891, + "learning_rate": 1.7868944563991014e-05, + "loss": 0.8785, + "step": 2629 + }, + { + "epoch": 0.23549163355531927, + "grad_norm": 0.8852751535574673, + "learning_rate": 1.7867154500885898e-05, + "loss": 0.8586, + "step": 2630 + }, + { + "epoch": 0.23558117410039733, + "grad_norm": 0.9183662546585113, + "learning_rate": 1.786536377602138e-05, + "loss": 0.8655, + "step": 2631 + }, + { + "epoch": 0.2356707146454754, + "grad_norm": 1.007747485845422, + "learning_rate": 1.786357238954809e-05, + "loss": 0.858, + "step": 2632 + }, + { + "epoch": 0.23576025519055346, + "grad_norm": 1.0393029191828451, + "learning_rate": 1.786178034161672e-05, + "loss": 0.8772, + "step": 2633 + }, + { + "epoch": 0.23584979573563153, + "grad_norm": 0.9257576439738907, + "learning_rate": 1.7859987632378003e-05, + "loss": 0.881, + "step": 2634 + }, + { + "epoch": 0.23593933628070962, + "grad_norm": 0.9438131390493132, + "learning_rate": 1.7858194261982742e-05, + "loss": 0.9049, + "step": 2635 + }, + { + "epoch": 0.2360288768257877, + "grad_norm": 0.9254056064527866, + "learning_rate": 1.7856400230581786e-05, + "loss": 0.8646, + "step": 2636 + }, + { + "epoch": 0.23611841737086575, + "grad_norm": 1.023092547018399, + "learning_rate": 1.7854605538326044e-05, + "loss": 0.8676, + "step": 2637 + }, + { + "epoch": 0.23620795791594382, + "grad_norm": 0.944292291619518, + "learning_rate": 1.7852810185366483e-05, + "loss": 0.8562, + "step": 2638 + }, + { + "epoch": 0.23629749846102188, + "grad_norm": 1.0546311228616252, + "learning_rate": 1.7851014171854112e-05, + "loss": 0.9121, + "step": 2639 + }, + { + "epoch": 0.23638703900609995, + "grad_norm": 0.9230496647553422, + "learning_rate": 1.784921749794002e-05, + "loss": 0.8929, + "step": 2640 + }, + { + "epoch": 0.236476579551178, + "grad_norm": 0.8436094813949143, + "learning_rate": 1.7847420163775327e-05, + "loss": 0.8146, + "step": 2641 + }, + { + "epoch": 0.23656612009625608, + "grad_norm": 0.9683885604145878, + "learning_rate": 1.7845622169511223e-05, + "loss": 0.8781, + "step": 2642 + }, + { + "epoch": 0.23665566064133414, + "grad_norm": 1.0521803476722145, + "learning_rate": 1.784382351529895e-05, + "loss": 0.8454, + "step": 2643 + }, + { + "epoch": 0.23674520118641224, + "grad_norm": 0.9170253910131152, + "learning_rate": 1.7842024201289803e-05, + "loss": 0.8689, + "step": 2644 + }, + { + "epoch": 0.2368347417314903, + "grad_norm": 0.9729363223624565, + "learning_rate": 1.7840224227635136e-05, + "loss": 0.9019, + "step": 2645 + }, + { + "epoch": 0.23692428227656837, + "grad_norm": 0.9304258924835851, + "learning_rate": 1.7838423594486355e-05, + "loss": 0.9293, + "step": 2646 + }, + { + "epoch": 0.23701382282164643, + "grad_norm": 1.0137938753598892, + "learning_rate": 1.783662230199492e-05, + "loss": 0.9052, + "step": 2647 + }, + { + "epoch": 0.2371033633667245, + "grad_norm": 0.9234728892236547, + "learning_rate": 1.783482035031236e-05, + "loss": 0.8904, + "step": 2648 + }, + { + "epoch": 0.23719290391180256, + "grad_norm": 1.0609154343320197, + "learning_rate": 1.7833017739590243e-05, + "loss": 0.8809, + "step": 2649 + }, + { + "epoch": 0.23728244445688063, + "grad_norm": 0.9869192441106394, + "learning_rate": 1.7831214469980196e-05, + "loss": 0.9141, + "step": 2650 + }, + { + "epoch": 0.2373719850019587, + "grad_norm": 0.9238068631519115, + "learning_rate": 1.782941054163391e-05, + "loss": 0.8793, + "step": 2651 + }, + { + "epoch": 0.23746152554703676, + "grad_norm": 1.0022334996559363, + "learning_rate": 1.7827605954703126e-05, + "loss": 0.9115, + "step": 2652 + }, + { + "epoch": 0.23755106609211485, + "grad_norm": 0.8891432097363757, + "learning_rate": 1.7825800709339632e-05, + "loss": 0.8781, + "step": 2653 + }, + { + "epoch": 0.2376406066371929, + "grad_norm": 0.8989902803091024, + "learning_rate": 1.782399480569528e-05, + "loss": 0.8425, + "step": 2654 + }, + { + "epoch": 0.23773014718227098, + "grad_norm": 0.9912972011753028, + "learning_rate": 1.782218824392199e-05, + "loss": 0.9158, + "step": 2655 + }, + { + "epoch": 0.23781968772734904, + "grad_norm": 0.983719020031523, + "learning_rate": 1.7820381024171713e-05, + "loss": 0.8112, + "step": 2656 + }, + { + "epoch": 0.2379092282724271, + "grad_norm": 0.8918817781164265, + "learning_rate": 1.7818573146596465e-05, + "loss": 0.8408, + "step": 2657 + }, + { + "epoch": 0.23799876881750517, + "grad_norm": 1.1084179488449928, + "learning_rate": 1.7816764611348324e-05, + "loss": 0.9429, + "step": 2658 + }, + { + "epoch": 0.23808830936258324, + "grad_norm": 0.9568337603666967, + "learning_rate": 1.781495541857942e-05, + "loss": 0.9176, + "step": 2659 + }, + { + "epoch": 0.2381778499076613, + "grad_norm": 0.9094113930117377, + "learning_rate": 1.7813145568441927e-05, + "loss": 0.8074, + "step": 2660 + }, + { + "epoch": 0.23826739045273937, + "grad_norm": 0.9734006635669809, + "learning_rate": 1.7811335061088093e-05, + "loss": 0.7893, + "step": 2661 + }, + { + "epoch": 0.23835693099781746, + "grad_norm": 0.8898647116120292, + "learning_rate": 1.7809523896670205e-05, + "loss": 0.8337, + "step": 2662 + }, + { + "epoch": 0.23844647154289553, + "grad_norm": 0.9668526906350915, + "learning_rate": 1.780771207534062e-05, + "loss": 0.8143, + "step": 2663 + }, + { + "epoch": 0.2385360120879736, + "grad_norm": 1.155557046212242, + "learning_rate": 1.7805899597251736e-05, + "loss": 0.8202, + "step": 2664 + }, + { + "epoch": 0.23862555263305166, + "grad_norm": 1.0978460663297456, + "learning_rate": 1.7804086462556015e-05, + "loss": 0.872, + "step": 2665 + }, + { + "epoch": 0.23871509317812972, + "grad_norm": 0.9788033916710924, + "learning_rate": 1.7802272671405972e-05, + "loss": 0.8301, + "step": 2666 + }, + { + "epoch": 0.2388046337232078, + "grad_norm": 0.9976434859425, + "learning_rate": 1.780045822395418e-05, + "loss": 0.8621, + "step": 2667 + }, + { + "epoch": 0.23889417426828585, + "grad_norm": 0.9656441610717202, + "learning_rate": 1.7798643120353262e-05, + "loss": 0.8737, + "step": 2668 + }, + { + "epoch": 0.23898371481336392, + "grad_norm": 0.982047421264553, + "learning_rate": 1.7796827360755892e-05, + "loss": 0.8233, + "step": 2669 + }, + { + "epoch": 0.23907325535844198, + "grad_norm": 1.0838198515924433, + "learning_rate": 1.7795010945314816e-05, + "loss": 0.9123, + "step": 2670 + }, + { + "epoch": 0.23916279590352008, + "grad_norm": 1.0451740752492333, + "learning_rate": 1.779319387418282e-05, + "loss": 0.8826, + "step": 2671 + }, + { + "epoch": 0.23925233644859814, + "grad_norm": 1.003395524090343, + "learning_rate": 1.7791376147512754e-05, + "loss": 0.8879, + "step": 2672 + }, + { + "epoch": 0.2393418769936762, + "grad_norm": 0.9953550986807853, + "learning_rate": 1.7789557765457514e-05, + "loss": 0.8861, + "step": 2673 + }, + { + "epoch": 0.23943141753875427, + "grad_norm": 1.1030472874146318, + "learning_rate": 1.7787738728170057e-05, + "loss": 0.8329, + "step": 2674 + }, + { + "epoch": 0.23952095808383234, + "grad_norm": 0.9052115998066025, + "learning_rate": 1.77859190358034e-05, + "loss": 0.8419, + "step": 2675 + }, + { + "epoch": 0.2396104986289104, + "grad_norm": 1.2851847215676462, + "learning_rate": 1.77840986885106e-05, + "loss": 0.9421, + "step": 2676 + }, + { + "epoch": 0.23970003917398847, + "grad_norm": 0.8976328324702899, + "learning_rate": 1.778227768644479e-05, + "loss": 0.9233, + "step": 2677 + }, + { + "epoch": 0.23978957971906653, + "grad_norm": 0.9928390911819834, + "learning_rate": 1.778045602975914e-05, + "loss": 0.8793, + "step": 2678 + }, + { + "epoch": 0.2398791202641446, + "grad_norm": 1.1219352403064662, + "learning_rate": 1.7778633718606882e-05, + "loss": 0.8689, + "step": 2679 + }, + { + "epoch": 0.2399686608092227, + "grad_norm": 1.0006621662579105, + "learning_rate": 1.77768107531413e-05, + "loss": 0.8128, + "step": 2680 + }, + { + "epoch": 0.24005820135430075, + "grad_norm": 0.9885008535400198, + "learning_rate": 1.7774987133515743e-05, + "loss": 0.881, + "step": 2681 + }, + { + "epoch": 0.24014774189937882, + "grad_norm": 0.9434443960493979, + "learning_rate": 1.7773162859883607e-05, + "loss": 0.9008, + "step": 2682 + }, + { + "epoch": 0.24023728244445688, + "grad_norm": 0.9530156413917824, + "learning_rate": 1.777133793239834e-05, + "loss": 0.9299, + "step": 2683 + }, + { + "epoch": 0.24032682298953495, + "grad_norm": 1.0222522045827696, + "learning_rate": 1.776951235121345e-05, + "loss": 0.8827, + "step": 2684 + }, + { + "epoch": 0.24041636353461301, + "grad_norm": 0.9755682089948413, + "learning_rate": 1.77676861164825e-05, + "loss": 0.8843, + "step": 2685 + }, + { + "epoch": 0.24050590407969108, + "grad_norm": 1.0368372394799665, + "learning_rate": 1.7765859228359107e-05, + "loss": 0.8657, + "step": 2686 + }, + { + "epoch": 0.24059544462476914, + "grad_norm": 0.935599898442727, + "learning_rate": 1.776403168699694e-05, + "loss": 0.8892, + "step": 2687 + }, + { + "epoch": 0.2406849851698472, + "grad_norm": 1.0852113247658912, + "learning_rate": 1.776220349254973e-05, + "loss": 0.9044, + "step": 2688 + }, + { + "epoch": 0.2407745257149253, + "grad_norm": 0.8611597478426928, + "learning_rate": 1.776037464517126e-05, + "loss": 0.8814, + "step": 2689 + }, + { + "epoch": 0.24086406626000337, + "grad_norm": 0.8960616729913411, + "learning_rate": 1.7758545145015357e-05, + "loss": 0.8411, + "step": 2690 + }, + { + "epoch": 0.24095360680508143, + "grad_norm": 0.982020686778685, + "learning_rate": 1.7756714992235923e-05, + "loss": 0.8811, + "step": 2691 + }, + { + "epoch": 0.2410431473501595, + "grad_norm": 1.0211076463363102, + "learning_rate": 1.7754884186986902e-05, + "loss": 0.8903, + "step": 2692 + }, + { + "epoch": 0.24113268789523756, + "grad_norm": 0.9107275047766401, + "learning_rate": 1.775305272942229e-05, + "loss": 0.8918, + "step": 2693 + }, + { + "epoch": 0.24122222844031563, + "grad_norm": 0.9017106495487175, + "learning_rate": 1.775122061969615e-05, + "loss": 0.8736, + "step": 2694 + }, + { + "epoch": 0.2413117689853937, + "grad_norm": 1.05237763746774, + "learning_rate": 1.774938785796259e-05, + "loss": 0.895, + "step": 2695 + }, + { + "epoch": 0.24140130953047176, + "grad_norm": 0.9921704153549351, + "learning_rate": 1.7747554444375778e-05, + "loss": 0.9303, + "step": 2696 + }, + { + "epoch": 0.24149085007554982, + "grad_norm": 1.0619069229384261, + "learning_rate": 1.774572037908993e-05, + "loss": 0.8861, + "step": 2697 + }, + { + "epoch": 0.24158039062062792, + "grad_norm": 0.9163750106196041, + "learning_rate": 1.7743885662259327e-05, + "loss": 0.8824, + "step": 2698 + }, + { + "epoch": 0.24166993116570598, + "grad_norm": 1.0451213070568686, + "learning_rate": 1.7742050294038296e-05, + "loss": 0.8694, + "step": 2699 + }, + { + "epoch": 0.24175947171078405, + "grad_norm": 1.1228707866301095, + "learning_rate": 1.7740214274581225e-05, + "loss": 0.8818, + "step": 2700 + }, + { + "epoch": 0.2418490122558621, + "grad_norm": 0.8219860263683608, + "learning_rate": 1.7738377604042552e-05, + "loss": 0.8437, + "step": 2701 + }, + { + "epoch": 0.24193855280094018, + "grad_norm": 0.9130427729516896, + "learning_rate": 1.773654028257677e-05, + "loss": 0.8817, + "step": 2702 + }, + { + "epoch": 0.24202809334601824, + "grad_norm": 0.9578896782605372, + "learning_rate": 1.7734702310338432e-05, + "loss": 0.9219, + "step": 2703 + }, + { + "epoch": 0.2421176338910963, + "grad_norm": 0.8716933894015255, + "learning_rate": 1.773286368748214e-05, + "loss": 0.9295, + "step": 2704 + }, + { + "epoch": 0.24220717443617437, + "grad_norm": 1.0252457086825695, + "learning_rate": 1.7731024414162556e-05, + "loss": 0.8979, + "step": 2705 + }, + { + "epoch": 0.24229671498125244, + "grad_norm": 0.9247889599034405, + "learning_rate": 1.7729184490534387e-05, + "loss": 0.8642, + "step": 2706 + }, + { + "epoch": 0.24238625552633053, + "grad_norm": 0.9275643236004367, + "learning_rate": 1.772734391675241e-05, + "loss": 0.8276, + "step": 2707 + }, + { + "epoch": 0.2424757960714086, + "grad_norm": 0.8467931196907335, + "learning_rate": 1.772550269297144e-05, + "loss": 0.8379, + "step": 2708 + }, + { + "epoch": 0.24256533661648666, + "grad_norm": 1.0013710701177705, + "learning_rate": 1.7723660819346362e-05, + "loss": 0.9381, + "step": 2709 + }, + { + "epoch": 0.24265487716156472, + "grad_norm": 0.9187642130023972, + "learning_rate": 1.7721818296032102e-05, + "loss": 0.8503, + "step": 2710 + }, + { + "epoch": 0.2427444177066428, + "grad_norm": 1.2330183344577654, + "learning_rate": 1.7719975123183654e-05, + "loss": 0.8964, + "step": 2711 + }, + { + "epoch": 0.24283395825172086, + "grad_norm": 0.9827652701156832, + "learning_rate": 1.7718131300956055e-05, + "loss": 0.8825, + "step": 2712 + }, + { + "epoch": 0.24292349879679892, + "grad_norm": 1.0645073916860257, + "learning_rate": 1.7716286829504397e-05, + "loss": 0.8761, + "step": 2713 + }, + { + "epoch": 0.24301303934187699, + "grad_norm": 0.9559215040123434, + "learning_rate": 1.771444170898384e-05, + "loss": 0.8963, + "step": 2714 + }, + { + "epoch": 0.24310257988695505, + "grad_norm": 0.8934086109799099, + "learning_rate": 1.7712595939549582e-05, + "loss": 0.894, + "step": 2715 + }, + { + "epoch": 0.24319212043203314, + "grad_norm": 0.9557143202988652, + "learning_rate": 1.7710749521356894e-05, + "loss": 0.8777, + "step": 2716 + }, + { + "epoch": 0.2432816609771112, + "grad_norm": 0.9951329789554673, + "learning_rate": 1.7708902454561076e-05, + "loss": 0.9169, + "step": 2717 + }, + { + "epoch": 0.24337120152218927, + "grad_norm": 0.9131655089319715, + "learning_rate": 1.7707054739317508e-05, + "loss": 0.8481, + "step": 2718 + }, + { + "epoch": 0.24346074206726734, + "grad_norm": 1.0259273191981082, + "learning_rate": 1.770520637578161e-05, + "loss": 0.8317, + "step": 2719 + }, + { + "epoch": 0.2435502826123454, + "grad_norm": 0.8934711674176932, + "learning_rate": 1.7703357364108862e-05, + "loss": 0.9181, + "step": 2720 + }, + { + "epoch": 0.24363982315742347, + "grad_norm": 0.9518098452068476, + "learning_rate": 1.7701507704454794e-05, + "loss": 0.9235, + "step": 2721 + }, + { + "epoch": 0.24372936370250153, + "grad_norm": 0.9615663055458201, + "learning_rate": 1.7699657396974993e-05, + "loss": 0.8781, + "step": 2722 + }, + { + "epoch": 0.2438189042475796, + "grad_norm": 0.9672350339557478, + "learning_rate": 1.7697806441825106e-05, + "loss": 0.9083, + "step": 2723 + }, + { + "epoch": 0.24390844479265766, + "grad_norm": 1.2235643908573797, + "learning_rate": 1.769595483916083e-05, + "loss": 0.8948, + "step": 2724 + }, + { + "epoch": 0.24399798533773576, + "grad_norm": 0.9724308246464767, + "learning_rate": 1.7694102589137903e-05, + "loss": 0.8558, + "step": 2725 + }, + { + "epoch": 0.24408752588281382, + "grad_norm": 0.9839020135226488, + "learning_rate": 1.769224969191214e-05, + "loss": 0.8888, + "step": 2726 + }, + { + "epoch": 0.2441770664278919, + "grad_norm": 1.0542576330945779, + "learning_rate": 1.7690396147639403e-05, + "loss": 0.9123, + "step": 2727 + }, + { + "epoch": 0.24426660697296995, + "grad_norm": 0.9647643797132811, + "learning_rate": 1.76885419564756e-05, + "loss": 0.8185, + "step": 2728 + }, + { + "epoch": 0.24435614751804802, + "grad_norm": 1.0668523302626827, + "learning_rate": 1.7686687118576707e-05, + "loss": 0.9345, + "step": 2729 + }, + { + "epoch": 0.24444568806312608, + "grad_norm": 0.9731682213180951, + "learning_rate": 1.768483163409874e-05, + "loss": 0.9307, + "step": 2730 + }, + { + "epoch": 0.24453522860820415, + "grad_norm": 0.9926343776486147, + "learning_rate": 1.7682975503197776e-05, + "loss": 0.9298, + "step": 2731 + }, + { + "epoch": 0.2446247691532822, + "grad_norm": 1.0835089625505936, + "learning_rate": 1.7681118726029952e-05, + "loss": 0.8636, + "step": 2732 + }, + { + "epoch": 0.24471430969836028, + "grad_norm": 0.9527805436959033, + "learning_rate": 1.7679261302751448e-05, + "loss": 0.8977, + "step": 2733 + }, + { + "epoch": 0.24480385024343837, + "grad_norm": 0.9390805341550253, + "learning_rate": 1.767740323351851e-05, + "loss": 0.8305, + "step": 2734 + }, + { + "epoch": 0.24489339078851644, + "grad_norm": 0.9872127560617658, + "learning_rate": 1.767554451848743e-05, + "loss": 0.8969, + "step": 2735 + }, + { + "epoch": 0.2449829313335945, + "grad_norm": 0.9465664465372386, + "learning_rate": 1.7673685157814556e-05, + "loss": 0.844, + "step": 2736 + }, + { + "epoch": 0.24507247187867257, + "grad_norm": 1.0302506448451823, + "learning_rate": 1.76718251516563e-05, + "loss": 0.8496, + "step": 2737 + }, + { + "epoch": 0.24516201242375063, + "grad_norm": 1.0238860822398237, + "learning_rate": 1.7669964500169103e-05, + "loss": 0.8523, + "step": 2738 + }, + { + "epoch": 0.2452515529688287, + "grad_norm": 1.0750848462952611, + "learning_rate": 1.7668103203509494e-05, + "loss": 0.8817, + "step": 2739 + }, + { + "epoch": 0.24534109351390676, + "grad_norm": 0.8955590253859774, + "learning_rate": 1.7666241261834028e-05, + "loss": 0.9062, + "step": 2740 + }, + { + "epoch": 0.24543063405898483, + "grad_norm": 0.8707931441652753, + "learning_rate": 1.7664378675299328e-05, + "loss": 0.8611, + "step": 2741 + }, + { + "epoch": 0.2455201746040629, + "grad_norm": 1.0799676357731698, + "learning_rate": 1.766251544406207e-05, + "loss": 0.9025, + "step": 2742 + }, + { + "epoch": 0.24560971514914098, + "grad_norm": 0.9687187951683363, + "learning_rate": 1.7660651568278983e-05, + "loss": 0.8924, + "step": 2743 + }, + { + "epoch": 0.24569925569421905, + "grad_norm": 0.9243104535331628, + "learning_rate": 1.765878704810685e-05, + "loss": 0.8382, + "step": 2744 + }, + { + "epoch": 0.2457887962392971, + "grad_norm": 1.0523232525281316, + "learning_rate": 1.7656921883702512e-05, + "loss": 0.8809, + "step": 2745 + }, + { + "epoch": 0.24587833678437518, + "grad_norm": 0.8443677969596001, + "learning_rate": 1.765505607522285e-05, + "loss": 0.8486, + "step": 2746 + }, + { + "epoch": 0.24596787732945324, + "grad_norm": 0.926803234417444, + "learning_rate": 1.765318962282482e-05, + "loss": 0.8838, + "step": 2747 + }, + { + "epoch": 0.2460574178745313, + "grad_norm": 0.9300929304339939, + "learning_rate": 1.765132252666542e-05, + "loss": 0.8935, + "step": 2748 + }, + { + "epoch": 0.24614695841960937, + "grad_norm": 1.0523953372204147, + "learning_rate": 1.7649454786901697e-05, + "loss": 0.8673, + "step": 2749 + }, + { + "epoch": 0.24623649896468744, + "grad_norm": 0.9683403739448853, + "learning_rate": 1.764758640369077e-05, + "loss": 0.8622, + "step": 2750 + }, + { + "epoch": 0.2463260395097655, + "grad_norm": 0.9175951408387996, + "learning_rate": 1.7645717377189795e-05, + "loss": 0.9167, + "step": 2751 + }, + { + "epoch": 0.2464155800548436, + "grad_norm": 0.9670774194552706, + "learning_rate": 1.764384770755599e-05, + "loss": 0.8792, + "step": 2752 + }, + { + "epoch": 0.24650512059992166, + "grad_norm": 1.0342858962744663, + "learning_rate": 1.7641977394946623e-05, + "loss": 0.9173, + "step": 2753 + }, + { + "epoch": 0.24659466114499973, + "grad_norm": 0.8829273388062568, + "learning_rate": 1.7640106439519024e-05, + "loss": 0.9118, + "step": 2754 + }, + { + "epoch": 0.2466842016900778, + "grad_norm": 0.9602603377760228, + "learning_rate": 1.7638234841430563e-05, + "loss": 0.8875, + "step": 2755 + }, + { + "epoch": 0.24677374223515586, + "grad_norm": 1.0239336237311405, + "learning_rate": 1.763636260083868e-05, + "loss": 0.8827, + "step": 2756 + }, + { + "epoch": 0.24686328278023392, + "grad_norm": 0.9562132243310533, + "learning_rate": 1.763448971790086e-05, + "loss": 0.8791, + "step": 2757 + }, + { + "epoch": 0.246952823325312, + "grad_norm": 0.9606704192471304, + "learning_rate": 1.763261619277464e-05, + "loss": 0.9082, + "step": 2758 + }, + { + "epoch": 0.24704236387039005, + "grad_norm": 1.0006112315852194, + "learning_rate": 1.7630742025617626e-05, + "loss": 0.8467, + "step": 2759 + }, + { + "epoch": 0.24713190441546812, + "grad_norm": 0.9373879963582208, + "learning_rate": 1.7628867216587452e-05, + "loss": 0.8991, + "step": 2760 + }, + { + "epoch": 0.2472214449605462, + "grad_norm": 0.8571657260390055, + "learning_rate": 1.7626991765841832e-05, + "loss": 0.9024, + "step": 2761 + }, + { + "epoch": 0.24731098550562428, + "grad_norm": 0.8855173483650962, + "learning_rate": 1.762511567353852e-05, + "loss": 0.8526, + "step": 2762 + }, + { + "epoch": 0.24740052605070234, + "grad_norm": 0.9525417658088339, + "learning_rate": 1.7623238939835322e-05, + "loss": 0.8183, + "step": 2763 + }, + { + "epoch": 0.2474900665957804, + "grad_norm": 0.8264905716337613, + "learning_rate": 1.7621361564890108e-05, + "loss": 0.8002, + "step": 2764 + }, + { + "epoch": 0.24757960714085847, + "grad_norm": 0.9611381182640658, + "learning_rate": 1.7619483548860792e-05, + "loss": 0.8724, + "step": 2765 + }, + { + "epoch": 0.24766914768593654, + "grad_norm": 1.0909350991237563, + "learning_rate": 1.761760489190535e-05, + "loss": 0.8594, + "step": 2766 + }, + { + "epoch": 0.2477586882310146, + "grad_norm": 1.0508531917172441, + "learning_rate": 1.7615725594181808e-05, + "loss": 0.8874, + "step": 2767 + }, + { + "epoch": 0.24784822877609267, + "grad_norm": 0.9134953625375521, + "learning_rate": 1.761384565584825e-05, + "loss": 0.8931, + "step": 2768 + }, + { + "epoch": 0.24793776932117073, + "grad_norm": 0.9114919325780945, + "learning_rate": 1.7611965077062808e-05, + "loss": 0.8779, + "step": 2769 + }, + { + "epoch": 0.24802730986624882, + "grad_norm": 0.9681423120707378, + "learning_rate": 1.7610083857983663e-05, + "loss": 0.8259, + "step": 2770 + }, + { + "epoch": 0.2481168504113269, + "grad_norm": 1.0607695766166856, + "learning_rate": 1.7608201998769065e-05, + "loss": 0.8886, + "step": 2771 + }, + { + "epoch": 0.24820639095640495, + "grad_norm": 0.9274279877402068, + "learning_rate": 1.7606319499577308e-05, + "loss": 0.8285, + "step": 2772 + }, + { + "epoch": 0.24829593150148302, + "grad_norm": 0.9901015756754248, + "learning_rate": 1.7604436360566742e-05, + "loss": 0.8709, + "step": 2773 + }, + { + "epoch": 0.24838547204656108, + "grad_norm": 1.0168318332719135, + "learning_rate": 1.760255258189577e-05, + "loss": 0.8394, + "step": 2774 + }, + { + "epoch": 0.24847501259163915, + "grad_norm": 0.9561944657924711, + "learning_rate": 1.760066816372285e-05, + "loss": 0.8442, + "step": 2775 + }, + { + "epoch": 0.24856455313671721, + "grad_norm": 0.8889753117868241, + "learning_rate": 1.7598783106206488e-05, + "loss": 0.8368, + "step": 2776 + }, + { + "epoch": 0.24865409368179528, + "grad_norm": 0.9128333726713597, + "learning_rate": 1.7596897409505257e-05, + "loss": 0.8396, + "step": 2777 + }, + { + "epoch": 0.24874363422687334, + "grad_norm": 0.905698393292759, + "learning_rate": 1.7595011073777773e-05, + "loss": 0.897, + "step": 2778 + }, + { + "epoch": 0.24883317477195144, + "grad_norm": 0.9205434875374836, + "learning_rate": 1.7593124099182705e-05, + "loss": 0.835, + "step": 2779 + }, + { + "epoch": 0.2489227153170295, + "grad_norm": 0.9069947674139621, + "learning_rate": 1.7591236485878783e-05, + "loss": 0.9214, + "step": 2780 + }, + { + "epoch": 0.24901225586210757, + "grad_norm": 0.9607755672372462, + "learning_rate": 1.7589348234024787e-05, + "loss": 0.9125, + "step": 2781 + }, + { + "epoch": 0.24910179640718563, + "grad_norm": 1.0495989272277562, + "learning_rate": 1.7587459343779545e-05, + "loss": 0.8987, + "step": 2782 + }, + { + "epoch": 0.2491913369522637, + "grad_norm": 0.9867383154208691, + "learning_rate": 1.758556981530195e-05, + "loss": 0.8427, + "step": 2783 + }, + { + "epoch": 0.24928087749734176, + "grad_norm": 0.9097319160504008, + "learning_rate": 1.7583679648750945e-05, + "loss": 0.8443, + "step": 2784 + }, + { + "epoch": 0.24937041804241983, + "grad_norm": 0.9317617865863824, + "learning_rate": 1.7581788844285513e-05, + "loss": 0.8513, + "step": 2785 + }, + { + "epoch": 0.2494599585874979, + "grad_norm": 1.0166778739233655, + "learning_rate": 1.7579897402064716e-05, + "loss": 0.8926, + "step": 2786 + }, + { + "epoch": 0.24954949913257596, + "grad_norm": 0.9516827087404582, + "learning_rate": 1.7578005322247648e-05, + "loss": 0.9082, + "step": 2787 + }, + { + "epoch": 0.24963903967765405, + "grad_norm": 0.9289996303495486, + "learning_rate": 1.7576112604993468e-05, + "loss": 0.8394, + "step": 2788 + }, + { + "epoch": 0.24972858022273212, + "grad_norm": 0.9027645565735546, + "learning_rate": 1.7574219250461385e-05, + "loss": 0.8481, + "step": 2789 + }, + { + "epoch": 0.24981812076781018, + "grad_norm": 0.9544300252910155, + "learning_rate": 1.757232525881066e-05, + "loss": 0.8086, + "step": 2790 + }, + { + "epoch": 0.24990766131288825, + "grad_norm": 0.9722804704566914, + "learning_rate": 1.757043063020061e-05, + "loss": 0.8849, + "step": 2791 + }, + { + "epoch": 0.2499972018579663, + "grad_norm": 0.9760416399715646, + "learning_rate": 1.75685353647906e-05, + "loss": 0.8818, + "step": 2792 + }, + { + "epoch": 0.2500867424030444, + "grad_norm": 0.9172019223324674, + "learning_rate": 1.7566639462740064e-05, + "loss": 0.8777, + "step": 2793 + }, + { + "epoch": 0.25017628294812244, + "grad_norm": 1.1990262362097253, + "learning_rate": 1.7564742924208477e-05, + "loss": 0.8797, + "step": 2794 + }, + { + "epoch": 0.25026582349320053, + "grad_norm": 1.0423280661491978, + "learning_rate": 1.756284574935536e-05, + "loss": 0.9221, + "step": 2795 + }, + { + "epoch": 0.25035536403827857, + "grad_norm": 0.9970916842384036, + "learning_rate": 1.7560947938340306e-05, + "loss": 0.8825, + "step": 2796 + }, + { + "epoch": 0.25044490458335666, + "grad_norm": 1.0147323709176705, + "learning_rate": 1.755904949132295e-05, + "loss": 0.9022, + "step": 2797 + }, + { + "epoch": 0.2505344451284347, + "grad_norm": 1.056225729992979, + "learning_rate": 1.7557150408462986e-05, + "loss": 0.8786, + "step": 2798 + }, + { + "epoch": 0.2506239856735128, + "grad_norm": 0.9591230350067063, + "learning_rate": 1.7555250689920154e-05, + "loss": 0.8994, + "step": 2799 + }, + { + "epoch": 0.25071352621859083, + "grad_norm": 1.0658895295115187, + "learning_rate": 1.7553350335854253e-05, + "loss": 0.8461, + "step": 2800 + }, + { + "epoch": 0.2508030667636689, + "grad_norm": 0.9305997578989742, + "learning_rate": 1.755144934642514e-05, + "loss": 0.878, + "step": 2801 + }, + { + "epoch": 0.250892607308747, + "grad_norm": 0.9473578769190715, + "learning_rate": 1.7549547721792713e-05, + "loss": 0.9143, + "step": 2802 + }, + { + "epoch": 0.25098214785382505, + "grad_norm": 0.9713128629177371, + "learning_rate": 1.754764546211693e-05, + "loss": 0.8201, + "step": 2803 + }, + { + "epoch": 0.25107168839890315, + "grad_norm": 0.9508628325420606, + "learning_rate": 1.7545742567557813e-05, + "loss": 0.9219, + "step": 2804 + }, + { + "epoch": 0.2511612289439812, + "grad_norm": 0.9014703463077044, + "learning_rate": 1.7543839038275416e-05, + "loss": 0.8355, + "step": 2805 + }, + { + "epoch": 0.2512507694890593, + "grad_norm": 0.8254199968080466, + "learning_rate": 1.7541934874429864e-05, + "loss": 0.8581, + "step": 2806 + }, + { + "epoch": 0.2513403100341373, + "grad_norm": 1.050064023527621, + "learning_rate": 1.754003007618133e-05, + "loss": 0.8637, + "step": 2807 + }, + { + "epoch": 0.2514298505792154, + "grad_norm": 1.0225103566909177, + "learning_rate": 1.7538124643690033e-05, + "loss": 0.832, + "step": 2808 + }, + { + "epoch": 0.25151939112429345, + "grad_norm": 1.200794491385842, + "learning_rate": 1.7536218577116255e-05, + "loss": 0.8707, + "step": 2809 + }, + { + "epoch": 0.25160893166937154, + "grad_norm": 0.9338264801135122, + "learning_rate": 1.7534311876620332e-05, + "loss": 0.8918, + "step": 2810 + }, + { + "epoch": 0.25169847221444963, + "grad_norm": 0.9477966491362365, + "learning_rate": 1.7532404542362643e-05, + "loss": 0.8287, + "step": 2811 + }, + { + "epoch": 0.25178801275952767, + "grad_norm": 0.9372558632118163, + "learning_rate": 1.753049657450363e-05, + "loss": 0.8872, + "step": 2812 + }, + { + "epoch": 0.25187755330460576, + "grad_norm": 0.9314781001030886, + "learning_rate": 1.7528587973203785e-05, + "loss": 0.9026, + "step": 2813 + }, + { + "epoch": 0.2519670938496838, + "grad_norm": 0.9408565072625145, + "learning_rate": 1.7526678738623656e-05, + "loss": 0.8771, + "step": 2814 + }, + { + "epoch": 0.2520566343947619, + "grad_norm": 0.9750786292172663, + "learning_rate": 1.7524768870923835e-05, + "loss": 0.8439, + "step": 2815 + }, + { + "epoch": 0.25214617493983993, + "grad_norm": 1.05985362590735, + "learning_rate": 1.7522858370264976e-05, + "loss": 0.8099, + "step": 2816 + }, + { + "epoch": 0.252235715484918, + "grad_norm": 0.8846640969877093, + "learning_rate": 1.752094723680779e-05, + "loss": 0.8839, + "step": 2817 + }, + { + "epoch": 0.25232525602999606, + "grad_norm": 0.9664230725840194, + "learning_rate": 1.751903547071303e-05, + "loss": 0.8209, + "step": 2818 + }, + { + "epoch": 0.25241479657507415, + "grad_norm": 0.922721426488302, + "learning_rate": 1.751712307214151e-05, + "loss": 0.8952, + "step": 2819 + }, + { + "epoch": 0.25250433712015224, + "grad_norm": 1.1563436484504441, + "learning_rate": 1.7515210041254088e-05, + "loss": 0.9158, + "step": 2820 + }, + { + "epoch": 0.2525938776652303, + "grad_norm": 0.9492504085298364, + "learning_rate": 1.751329637821169e-05, + "loss": 0.9369, + "step": 2821 + }, + { + "epoch": 0.2526834182103084, + "grad_norm": 0.8701165687089394, + "learning_rate": 1.751138208317529e-05, + "loss": 0.8711, + "step": 2822 + }, + { + "epoch": 0.2527729587553864, + "grad_norm": 0.8358804813242242, + "learning_rate": 1.75094671563059e-05, + "loss": 0.9106, + "step": 2823 + }, + { + "epoch": 0.2528624993004645, + "grad_norm": 1.0338531132979683, + "learning_rate": 1.7507551597764603e-05, + "loss": 0.8406, + "step": 2824 + }, + { + "epoch": 0.25295203984554254, + "grad_norm": 0.8965129315233688, + "learning_rate": 1.7505635407712533e-05, + "loss": 0.8768, + "step": 2825 + }, + { + "epoch": 0.25304158039062064, + "grad_norm": 0.9175218369263208, + "learning_rate": 1.7503718586310872e-05, + "loss": 0.8085, + "step": 2826 + }, + { + "epoch": 0.2531311209356987, + "grad_norm": 0.9682162629606315, + "learning_rate": 1.7501801133720856e-05, + "loss": 0.8715, + "step": 2827 + }, + { + "epoch": 0.25322066148077677, + "grad_norm": 0.9453568389751502, + "learning_rate": 1.7499883050103773e-05, + "loss": 0.8435, + "step": 2828 + }, + { + "epoch": 0.25331020202585486, + "grad_norm": 0.8904804787042726, + "learning_rate": 1.7497964335620965e-05, + "loss": 0.8932, + "step": 2829 + }, + { + "epoch": 0.2533997425709329, + "grad_norm": 0.9339773370954416, + "learning_rate": 1.7496044990433833e-05, + "loss": 0.8836, + "step": 2830 + }, + { + "epoch": 0.253489283116011, + "grad_norm": 0.8950829887510492, + "learning_rate": 1.7494125014703825e-05, + "loss": 0.8429, + "step": 2831 + }, + { + "epoch": 0.253578823661089, + "grad_norm": 0.9642177884708231, + "learning_rate": 1.7492204408592447e-05, + "loss": 0.8316, + "step": 2832 + }, + { + "epoch": 0.2536683642061671, + "grad_norm": 1.1670573716889592, + "learning_rate": 1.749028317226124e-05, + "loss": 0.8622, + "step": 2833 + }, + { + "epoch": 0.25375790475124516, + "grad_norm": 0.974798871965889, + "learning_rate": 1.7488361305871827e-05, + "loss": 0.9001, + "step": 2834 + }, + { + "epoch": 0.25384744529632325, + "grad_norm": 0.9133881135448743, + "learning_rate": 1.748643880958586e-05, + "loss": 0.8976, + "step": 2835 + }, + { + "epoch": 0.2539369858414013, + "grad_norm": 0.9726097684469386, + "learning_rate": 1.7484515683565058e-05, + "loss": 0.8545, + "step": 2836 + }, + { + "epoch": 0.2540265263864794, + "grad_norm": 0.9786331045239071, + "learning_rate": 1.7482591927971184e-05, + "loss": 0.8382, + "step": 2837 + }, + { + "epoch": 0.25411606693155747, + "grad_norm": 0.9159840509517129, + "learning_rate": 1.7480667542966063e-05, + "loss": 0.81, + "step": 2838 + }, + { + "epoch": 0.2542056074766355, + "grad_norm": 1.0820499580325034, + "learning_rate": 1.7478742528711566e-05, + "loss": 0.931, + "step": 2839 + }, + { + "epoch": 0.2542951480217136, + "grad_norm": 0.9686829698345041, + "learning_rate": 1.747681688536962e-05, + "loss": 0.88, + "step": 2840 + }, + { + "epoch": 0.25438468856679164, + "grad_norm": 0.8706647913154442, + "learning_rate": 1.74748906131022e-05, + "loss": 0.8974, + "step": 2841 + }, + { + "epoch": 0.25447422911186973, + "grad_norm": 0.9435140380959134, + "learning_rate": 1.747296371207134e-05, + "loss": 0.8526, + "step": 2842 + }, + { + "epoch": 0.25456376965694777, + "grad_norm": 0.9422761827617258, + "learning_rate": 1.7471036182439124e-05, + "loss": 0.875, + "step": 2843 + }, + { + "epoch": 0.25465331020202586, + "grad_norm": 0.9301740124329331, + "learning_rate": 1.7469108024367688e-05, + "loss": 0.8221, + "step": 2844 + }, + { + "epoch": 0.2547428507471039, + "grad_norm": 0.9920298900665119, + "learning_rate": 1.746717923801923e-05, + "loss": 0.8856, + "step": 2845 + }, + { + "epoch": 0.254832391292182, + "grad_norm": 0.9596495363831525, + "learning_rate": 1.7465249823555987e-05, + "loss": 0.8556, + "step": 2846 + }, + { + "epoch": 0.2549219318372601, + "grad_norm": 1.0747696499442136, + "learning_rate": 1.7463319781140257e-05, + "loss": 0.8332, + "step": 2847 + }, + { + "epoch": 0.2550114723823381, + "grad_norm": 0.9088360802474033, + "learning_rate": 1.7461389110934382e-05, + "loss": 0.8548, + "step": 2848 + }, + { + "epoch": 0.2551010129274162, + "grad_norm": 0.983857389929394, + "learning_rate": 1.7459457813100774e-05, + "loss": 0.8216, + "step": 2849 + }, + { + "epoch": 0.25519055347249425, + "grad_norm": 0.9563966487761592, + "learning_rate": 1.745752588780188e-05, + "loss": 0.8428, + "step": 2850 + }, + { + "epoch": 0.25528009401757235, + "grad_norm": 1.1235664826006715, + "learning_rate": 1.745559333520021e-05, + "loss": 0.885, + "step": 2851 + }, + { + "epoch": 0.2553696345626504, + "grad_norm": 1.0144690281417854, + "learning_rate": 1.745366015545833e-05, + "loss": 0.8542, + "step": 2852 + }, + { + "epoch": 0.2554591751077285, + "grad_norm": 1.0757820002498766, + "learning_rate": 1.745172634873884e-05, + "loss": 0.9457, + "step": 2853 + }, + { + "epoch": 0.2555487156528065, + "grad_norm": 0.9744657736851683, + "learning_rate": 1.7449791915204418e-05, + "loss": 0.8676, + "step": 2854 + }, + { + "epoch": 0.2556382561978846, + "grad_norm": 0.9248408011755717, + "learning_rate": 1.7447856855017773e-05, + "loss": 0.8879, + "step": 2855 + }, + { + "epoch": 0.2557277967429627, + "grad_norm": 0.9674868138940755, + "learning_rate": 1.7445921168341682e-05, + "loss": 0.867, + "step": 2856 + }, + { + "epoch": 0.25581733728804074, + "grad_norm": 0.9961006464967589, + "learning_rate": 1.7443984855338963e-05, + "loss": 0.8686, + "step": 2857 + }, + { + "epoch": 0.25590687783311883, + "grad_norm": 1.0111043281686516, + "learning_rate": 1.74420479161725e-05, + "loss": 0.8622, + "step": 2858 + }, + { + "epoch": 0.25599641837819687, + "grad_norm": 0.9793036149431199, + "learning_rate": 1.7440110351005212e-05, + "loss": 0.924, + "step": 2859 + }, + { + "epoch": 0.25608595892327496, + "grad_norm": 1.0487794828841637, + "learning_rate": 1.7438172160000094e-05, + "loss": 0.8566, + "step": 2860 + }, + { + "epoch": 0.256175499468353, + "grad_norm": 0.8989867017127804, + "learning_rate": 1.7436233343320168e-05, + "loss": 0.8799, + "step": 2861 + }, + { + "epoch": 0.2562650400134311, + "grad_norm": 0.9160656342354396, + "learning_rate": 1.7434293901128528e-05, + "loss": 0.8809, + "step": 2862 + }, + { + "epoch": 0.2563545805585091, + "grad_norm": 0.9626963100676227, + "learning_rate": 1.7432353833588306e-05, + "loss": 0.9128, + "step": 2863 + }, + { + "epoch": 0.2564441211035872, + "grad_norm": 0.8962621689009838, + "learning_rate": 1.7430413140862705e-05, + "loss": 0.9069, + "step": 2864 + }, + { + "epoch": 0.2565336616486653, + "grad_norm": 0.9602712959631493, + "learning_rate": 1.742847182311496e-05, + "loss": 0.8805, + "step": 2865 + }, + { + "epoch": 0.25662320219374335, + "grad_norm": 0.9292313928933265, + "learning_rate": 1.742652988050838e-05, + "loss": 0.8817, + "step": 2866 + }, + { + "epoch": 0.25671274273882144, + "grad_norm": 0.9170967189453116, + "learning_rate": 1.74245873132063e-05, + "loss": 0.9131, + "step": 2867 + }, + { + "epoch": 0.2568022832838995, + "grad_norm": 0.9782936213636454, + "learning_rate": 1.742264412137213e-05, + "loss": 0.9038, + "step": 2868 + }, + { + "epoch": 0.2568918238289776, + "grad_norm": 0.8919900699314767, + "learning_rate": 1.7420700305169326e-05, + "loss": 0.8331, + "step": 2869 + }, + { + "epoch": 0.2569813643740556, + "grad_norm": 1.0129344774806455, + "learning_rate": 1.7418755864761398e-05, + "loss": 0.8936, + "step": 2870 + }, + { + "epoch": 0.2570709049191337, + "grad_norm": 0.8827368705842703, + "learning_rate": 1.7416810800311897e-05, + "loss": 0.8884, + "step": 2871 + }, + { + "epoch": 0.25716044546421174, + "grad_norm": 1.0060270529812727, + "learning_rate": 1.7414865111984443e-05, + "loss": 0.8374, + "step": 2872 + }, + { + "epoch": 0.25724998600928983, + "grad_norm": 0.8958033252826781, + "learning_rate": 1.7412918799942696e-05, + "loss": 0.8695, + "step": 2873 + }, + { + "epoch": 0.2573395265543679, + "grad_norm": 0.9400351778361435, + "learning_rate": 1.7410971864350377e-05, + "loss": 0.9108, + "step": 2874 + }, + { + "epoch": 0.25742906709944596, + "grad_norm": 0.9277355706856402, + "learning_rate": 1.740902430537126e-05, + "loss": 0.8914, + "step": 2875 + }, + { + "epoch": 0.25751860764452406, + "grad_norm": 0.9185780304022725, + "learning_rate": 1.7407076123169154e-05, + "loss": 0.8697, + "step": 2876 + }, + { + "epoch": 0.2576081481896021, + "grad_norm": 0.913874028195181, + "learning_rate": 1.740512731790795e-05, + "loss": 0.8582, + "step": 2877 + }, + { + "epoch": 0.2576976887346802, + "grad_norm": 1.2109358779364472, + "learning_rate": 1.740317788975156e-05, + "loss": 0.9348, + "step": 2878 + }, + { + "epoch": 0.2577872292797582, + "grad_norm": 0.9191780789798356, + "learning_rate": 1.7401227838863978e-05, + "loss": 0.8337, + "step": 2879 + }, + { + "epoch": 0.2578767698248363, + "grad_norm": 1.2025305586191626, + "learning_rate": 1.7399277165409222e-05, + "loss": 0.923, + "step": 2880 + }, + { + "epoch": 0.25796631036991435, + "grad_norm": 0.906162890261928, + "learning_rate": 1.7397325869551385e-05, + "loss": 0.8327, + "step": 2881 + }, + { + "epoch": 0.25805585091499245, + "grad_norm": 1.14846747653532, + "learning_rate": 1.7395373951454602e-05, + "loss": 0.8846, + "step": 2882 + }, + { + "epoch": 0.25814539146007054, + "grad_norm": 0.9653495825261464, + "learning_rate": 1.7393421411283064e-05, + "loss": 0.8703, + "step": 2883 + }, + { + "epoch": 0.2582349320051486, + "grad_norm": 0.925176230105764, + "learning_rate": 1.7391468249201007e-05, + "loss": 0.8923, + "step": 2884 + }, + { + "epoch": 0.25832447255022667, + "grad_norm": 0.9087061226581351, + "learning_rate": 1.7389514465372727e-05, + "loss": 0.8636, + "step": 2885 + }, + { + "epoch": 0.2584140130953047, + "grad_norm": 0.9229533669653477, + "learning_rate": 1.738756005996257e-05, + "loss": 0.8246, + "step": 2886 + }, + { + "epoch": 0.2585035536403828, + "grad_norm": 0.8878727127881054, + "learning_rate": 1.7385605033134938e-05, + "loss": 0.8828, + "step": 2887 + }, + { + "epoch": 0.25859309418546084, + "grad_norm": 1.0366599559480718, + "learning_rate": 1.7383649385054274e-05, + "loss": 0.9319, + "step": 2888 + }, + { + "epoch": 0.25868263473053893, + "grad_norm": 0.944010389695665, + "learning_rate": 1.738169311588509e-05, + "loss": 0.8463, + "step": 2889 + }, + { + "epoch": 0.25877217527561697, + "grad_norm": 0.9789818657079927, + "learning_rate": 1.737973622579193e-05, + "loss": 0.9352, + "step": 2890 + }, + { + "epoch": 0.25886171582069506, + "grad_norm": 0.9835968545824317, + "learning_rate": 1.737777871493941e-05, + "loss": 0.8759, + "step": 2891 + }, + { + "epoch": 0.25895125636577315, + "grad_norm": 0.9417550040399009, + "learning_rate": 1.7375820583492187e-05, + "loss": 0.8874, + "step": 2892 + }, + { + "epoch": 0.2590407969108512, + "grad_norm": 0.8131937864062204, + "learning_rate": 1.7373861831614972e-05, + "loss": 0.863, + "step": 2893 + }, + { + "epoch": 0.2591303374559293, + "grad_norm": 1.0629441250182083, + "learning_rate": 1.737190245947253e-05, + "loss": 0.8639, + "step": 2894 + }, + { + "epoch": 0.2592198780010073, + "grad_norm": 0.9206779175558812, + "learning_rate": 1.736994246722967e-05, + "loss": 0.8712, + "step": 2895 + }, + { + "epoch": 0.2593094185460854, + "grad_norm": 1.0418122980071844, + "learning_rate": 1.7367981855051275e-05, + "loss": 0.8831, + "step": 2896 + }, + { + "epoch": 0.25939895909116345, + "grad_norm": 0.8692206962093396, + "learning_rate": 1.736602062310225e-05, + "loss": 0.8781, + "step": 2897 + }, + { + "epoch": 0.25948849963624154, + "grad_norm": 1.0075718214722609, + "learning_rate": 1.7364058771547577e-05, + "loss": 0.8534, + "step": 2898 + }, + { + "epoch": 0.2595780401813196, + "grad_norm": 1.044507555111445, + "learning_rate": 1.7362096300552277e-05, + "loss": 0.9219, + "step": 2899 + }, + { + "epoch": 0.2596675807263977, + "grad_norm": 0.9037210582476438, + "learning_rate": 1.736013321028143e-05, + "loss": 0.8477, + "step": 2900 + }, + { + "epoch": 0.25975712127147577, + "grad_norm": 0.8474037971809412, + "learning_rate": 1.7358169500900155e-05, + "loss": 0.783, + "step": 2901 + }, + { + "epoch": 0.2598466618165538, + "grad_norm": 0.9361117081489556, + "learning_rate": 1.735620517257364e-05, + "loss": 0.8512, + "step": 2902 + }, + { + "epoch": 0.2599362023616319, + "grad_norm": 1.028882015887797, + "learning_rate": 1.7354240225467123e-05, + "loss": 0.8696, + "step": 2903 + }, + { + "epoch": 0.26002574290670993, + "grad_norm": 1.0246798562346628, + "learning_rate": 1.735227465974588e-05, + "loss": 0.8775, + "step": 2904 + }, + { + "epoch": 0.260115283451788, + "grad_norm": 0.8859030511238355, + "learning_rate": 1.735030847557525e-05, + "loss": 0.8695, + "step": 2905 + }, + { + "epoch": 0.26020482399686606, + "grad_norm": 1.097505255342631, + "learning_rate": 1.7348341673120627e-05, + "loss": 0.8478, + "step": 2906 + }, + { + "epoch": 0.26029436454194416, + "grad_norm": 0.939091255631859, + "learning_rate": 1.734637425254745e-05, + "loss": 0.8598, + "step": 2907 + }, + { + "epoch": 0.2603839050870222, + "grad_norm": 0.9300800186440121, + "learning_rate": 1.7344406214021207e-05, + "loss": 0.8246, + "step": 2908 + }, + { + "epoch": 0.2604734456321003, + "grad_norm": 0.9840642263662197, + "learning_rate": 1.7342437557707448e-05, + "loss": 0.8536, + "step": 2909 + }, + { + "epoch": 0.2605629861771784, + "grad_norm": 1.0161836042116503, + "learning_rate": 1.734046828377177e-05, + "loss": 0.8091, + "step": 2910 + }, + { + "epoch": 0.2606525267222564, + "grad_norm": 0.9348420316522782, + "learning_rate": 1.7338498392379818e-05, + "loss": 0.8278, + "step": 2911 + }, + { + "epoch": 0.2607420672673345, + "grad_norm": 1.1168685771937086, + "learning_rate": 1.7336527883697293e-05, + "loss": 0.8914, + "step": 2912 + }, + { + "epoch": 0.26083160781241255, + "grad_norm": 1.016188451451451, + "learning_rate": 1.7334556757889954e-05, + "loss": 0.9145, + "step": 2913 + }, + { + "epoch": 0.26092114835749064, + "grad_norm": 1.1298426075186665, + "learning_rate": 1.73325850151236e-05, + "loss": 0.8844, + "step": 2914 + }, + { + "epoch": 0.2610106889025687, + "grad_norm": 0.929745140690549, + "learning_rate": 1.733061265556409e-05, + "loss": 0.9054, + "step": 2915 + }, + { + "epoch": 0.26110022944764677, + "grad_norm": 0.9049104122104006, + "learning_rate": 1.7328639679377333e-05, + "loss": 0.8732, + "step": 2916 + }, + { + "epoch": 0.2611897699927248, + "grad_norm": 0.9371921983312508, + "learning_rate": 1.7326666086729284e-05, + "loss": 0.8548, + "step": 2917 + }, + { + "epoch": 0.2612793105378029, + "grad_norm": 1.0086890987763673, + "learning_rate": 1.7324691877785965e-05, + "loss": 0.8979, + "step": 2918 + }, + { + "epoch": 0.261368851082881, + "grad_norm": 1.0338213928207955, + "learning_rate": 1.7322717052713428e-05, + "loss": 0.8301, + "step": 2919 + }, + { + "epoch": 0.26145839162795903, + "grad_norm": 0.9869678771055899, + "learning_rate": 1.73207416116778e-05, + "loss": 0.9157, + "step": 2920 + }, + { + "epoch": 0.2615479321730371, + "grad_norm": 1.103589413726506, + "learning_rate": 1.731876555484524e-05, + "loss": 0.8806, + "step": 2921 + }, + { + "epoch": 0.26163747271811516, + "grad_norm": 0.9889377914021891, + "learning_rate": 1.7316788882381974e-05, + "loss": 0.852, + "step": 2922 + }, + { + "epoch": 0.26172701326319325, + "grad_norm": 0.8906520294524228, + "learning_rate": 1.7314811594454267e-05, + "loss": 0.8604, + "step": 2923 + }, + { + "epoch": 0.2618165538082713, + "grad_norm": 0.9442631263458445, + "learning_rate": 1.7312833691228448e-05, + "loss": 0.9099, + "step": 2924 + }, + { + "epoch": 0.2619060943533494, + "grad_norm": 0.9261948108668057, + "learning_rate": 1.731085517287089e-05, + "loss": 0.8859, + "step": 2925 + }, + { + "epoch": 0.2619956348984274, + "grad_norm": 1.0949949574509237, + "learning_rate": 1.730887603954802e-05, + "loss": 0.8389, + "step": 2926 + }, + { + "epoch": 0.2620851754435055, + "grad_norm": 0.9173996403361719, + "learning_rate": 1.7306896291426308e-05, + "loss": 0.8901, + "step": 2927 + }, + { + "epoch": 0.2621747159885836, + "grad_norm": 1.0233456452814471, + "learning_rate": 1.73049159286723e-05, + "loss": 0.8699, + "step": 2928 + }, + { + "epoch": 0.26226425653366164, + "grad_norm": 1.0335888197971284, + "learning_rate": 1.730293495145256e-05, + "loss": 0.885, + "step": 2929 + }, + { + "epoch": 0.26235379707873974, + "grad_norm": 0.9667654559815505, + "learning_rate": 1.7300953359933736e-05, + "loss": 0.8574, + "step": 2930 + }, + { + "epoch": 0.2624433376238178, + "grad_norm": 0.8917525848915481, + "learning_rate": 1.7298971154282507e-05, + "loss": 0.9044, + "step": 2931 + }, + { + "epoch": 0.26253287816889587, + "grad_norm": 1.090827913702074, + "learning_rate": 1.729698833466561e-05, + "loss": 0.9278, + "step": 2932 + }, + { + "epoch": 0.2626224187139739, + "grad_norm": 0.9370704714168601, + "learning_rate": 1.729500490124983e-05, + "loss": 0.909, + "step": 2933 + }, + { + "epoch": 0.262711959259052, + "grad_norm": 1.0108821564454133, + "learning_rate": 1.729302085420201e-05, + "loss": 0.8496, + "step": 2934 + }, + { + "epoch": 0.26280149980413003, + "grad_norm": 0.9355897500066436, + "learning_rate": 1.729103619368904e-05, + "loss": 0.8129, + "step": 2935 + }, + { + "epoch": 0.2628910403492081, + "grad_norm": 1.1100949325352596, + "learning_rate": 1.728905091987787e-05, + "loss": 0.9127, + "step": 2936 + }, + { + "epoch": 0.2629805808942862, + "grad_norm": 0.885538827438999, + "learning_rate": 1.7287065032935487e-05, + "loss": 0.8537, + "step": 2937 + }, + { + "epoch": 0.26307012143936426, + "grad_norm": 0.9729968753098472, + "learning_rate": 1.728507853302894e-05, + "loss": 0.9047, + "step": 2938 + }, + { + "epoch": 0.26315966198444235, + "grad_norm": 1.136584430193662, + "learning_rate": 1.7283091420325327e-05, + "loss": 0.9015, + "step": 2939 + }, + { + "epoch": 0.2632492025295204, + "grad_norm": 0.9440257719518842, + "learning_rate": 1.7281103694991798e-05, + "loss": 0.8948, + "step": 2940 + }, + { + "epoch": 0.2633387430745985, + "grad_norm": 1.014813861107895, + "learning_rate": 1.727911535719555e-05, + "loss": 0.8809, + "step": 2941 + }, + { + "epoch": 0.2634282836196765, + "grad_norm": 1.0609261940426649, + "learning_rate": 1.727712640710384e-05, + "loss": 0.8766, + "step": 2942 + }, + { + "epoch": 0.2635178241647546, + "grad_norm": 1.001943359828992, + "learning_rate": 1.7275136844883972e-05, + "loss": 0.8951, + "step": 2943 + }, + { + "epoch": 0.26360736470983265, + "grad_norm": 0.994999284025049, + "learning_rate": 1.7273146670703298e-05, + "loss": 0.8846, + "step": 2944 + }, + { + "epoch": 0.26369690525491074, + "grad_norm": 0.9999653023667543, + "learning_rate": 1.727115588472923e-05, + "loss": 0.8911, + "step": 2945 + }, + { + "epoch": 0.26378644579998883, + "grad_norm": 0.9406300861729852, + "learning_rate": 1.726916448712922e-05, + "loss": 0.9293, + "step": 2946 + }, + { + "epoch": 0.26387598634506687, + "grad_norm": 1.036111310231419, + "learning_rate": 1.7267172478070782e-05, + "loss": 0.8315, + "step": 2947 + }, + { + "epoch": 0.26396552689014496, + "grad_norm": 0.9694063528492727, + "learning_rate": 1.7265179857721478e-05, + "loss": 0.9349, + "step": 2948 + }, + { + "epoch": 0.264055067435223, + "grad_norm": 0.9251737703209791, + "learning_rate": 1.726318662624892e-05, + "loss": 0.8738, + "step": 2949 + }, + { + "epoch": 0.2641446079803011, + "grad_norm": 0.9493334709814716, + "learning_rate": 1.7261192783820774e-05, + "loss": 0.8338, + "step": 2950 + }, + { + "epoch": 0.26423414852537913, + "grad_norm": 0.9720537233085843, + "learning_rate": 1.725919833060475e-05, + "loss": 0.8873, + "step": 2951 + }, + { + "epoch": 0.2643236890704572, + "grad_norm": 1.0088161400724156, + "learning_rate": 1.7257203266768615e-05, + "loss": 0.9017, + "step": 2952 + }, + { + "epoch": 0.26441322961553526, + "grad_norm": 0.9344432955797067, + "learning_rate": 1.7255207592480193e-05, + "loss": 0.864, + "step": 2953 + }, + { + "epoch": 0.26450277016061335, + "grad_norm": 1.1747997269649035, + "learning_rate": 1.7253211307907352e-05, + "loss": 0.9022, + "step": 2954 + }, + { + "epoch": 0.26459231070569145, + "grad_norm": 0.9042505774813997, + "learning_rate": 1.725121441321801e-05, + "loss": 0.9085, + "step": 2955 + }, + { + "epoch": 0.2646818512507695, + "grad_norm": 0.9039367791043005, + "learning_rate": 1.724921690858014e-05, + "loss": 0.8678, + "step": 2956 + }, + { + "epoch": 0.2647713917958476, + "grad_norm": 0.8870713581243852, + "learning_rate": 1.724721879416177e-05, + "loss": 0.8792, + "step": 2957 + }, + { + "epoch": 0.2648609323409256, + "grad_norm": 0.9750039275370983, + "learning_rate": 1.7245220070130974e-05, + "loss": 0.9134, + "step": 2958 + }, + { + "epoch": 0.2649504728860037, + "grad_norm": 0.9161547172453762, + "learning_rate": 1.724322073665587e-05, + "loss": 0.9053, + "step": 2959 + }, + { + "epoch": 0.26504001343108174, + "grad_norm": 0.9762803900951708, + "learning_rate": 1.7241220793904644e-05, + "loss": 0.8437, + "step": 2960 + }, + { + "epoch": 0.26512955397615984, + "grad_norm": 0.9191671117177782, + "learning_rate": 1.7239220242045517e-05, + "loss": 0.8748, + "step": 2961 + }, + { + "epoch": 0.2652190945212379, + "grad_norm": 0.9625698543385949, + "learning_rate": 1.723721908124678e-05, + "loss": 0.8255, + "step": 2962 + }, + { + "epoch": 0.26530863506631597, + "grad_norm": 1.114722387902531, + "learning_rate": 1.7235217311676758e-05, + "loss": 0.8794, + "step": 2963 + }, + { + "epoch": 0.26539817561139406, + "grad_norm": 0.9210928552573481, + "learning_rate": 1.7233214933503828e-05, + "loss": 0.829, + "step": 2964 + }, + { + "epoch": 0.2654877161564721, + "grad_norm": 0.8975709810977502, + "learning_rate": 1.723121194689643e-05, + "loss": 0.8605, + "step": 2965 + }, + { + "epoch": 0.2655772567015502, + "grad_norm": 0.9926316424499927, + "learning_rate": 1.722920835202305e-05, + "loss": 0.9064, + "step": 2966 + }, + { + "epoch": 0.26566679724662823, + "grad_norm": 1.1510854780751034, + "learning_rate": 1.7227204149052223e-05, + "loss": 0.8551, + "step": 2967 + }, + { + "epoch": 0.2657563377917063, + "grad_norm": 0.9576172248559482, + "learning_rate": 1.722519933815253e-05, + "loss": 0.8482, + "step": 2968 + }, + { + "epoch": 0.26584587833678436, + "grad_norm": 0.8874076324267962, + "learning_rate": 1.7223193919492613e-05, + "loss": 0.9231, + "step": 2969 + }, + { + "epoch": 0.26593541888186245, + "grad_norm": 0.9458157752271144, + "learning_rate": 1.7221187893241164e-05, + "loss": 0.844, + "step": 2970 + }, + { + "epoch": 0.2660249594269405, + "grad_norm": 0.9262854908094071, + "learning_rate": 1.7219181259566922e-05, + "loss": 0.8618, + "step": 2971 + }, + { + "epoch": 0.2661144999720186, + "grad_norm": 0.9285890536595901, + "learning_rate": 1.7217174018638676e-05, + "loss": 0.855, + "step": 2972 + }, + { + "epoch": 0.2662040405170967, + "grad_norm": 0.972517520779482, + "learning_rate": 1.721516617062527e-05, + "loss": 0.8427, + "step": 2973 + }, + { + "epoch": 0.2662935810621747, + "grad_norm": 0.8849042617439682, + "learning_rate": 1.7213157715695602e-05, + "loss": 0.8972, + "step": 2974 + }, + { + "epoch": 0.2663831216072528, + "grad_norm": 1.0188266432626452, + "learning_rate": 1.7211148654018604e-05, + "loss": 0.9385, + "step": 2975 + }, + { + "epoch": 0.26647266215233084, + "grad_norm": 1.0754291125110633, + "learning_rate": 1.7209138985763288e-05, + "loss": 0.8738, + "step": 2976 + }, + { + "epoch": 0.26656220269740893, + "grad_norm": 1.003867980266452, + "learning_rate": 1.720712871109869e-05, + "loss": 0.9009, + "step": 2977 + }, + { + "epoch": 0.26665174324248697, + "grad_norm": 0.8281005533493064, + "learning_rate": 1.720511783019391e-05, + "loss": 0.844, + "step": 2978 + }, + { + "epoch": 0.26674128378756506, + "grad_norm": 1.1464497684137798, + "learning_rate": 1.72031063432181e-05, + "loss": 0.8933, + "step": 2979 + }, + { + "epoch": 0.2668308243326431, + "grad_norm": 0.9887753071625773, + "learning_rate": 1.7201094250340453e-05, + "loss": 0.877, + "step": 2980 + }, + { + "epoch": 0.2669203648777212, + "grad_norm": 0.8835637537803408, + "learning_rate": 1.719908155173023e-05, + "loss": 0.8563, + "step": 2981 + }, + { + "epoch": 0.2670099054227993, + "grad_norm": 0.9479598028553524, + "learning_rate": 1.719706824755672e-05, + "loss": 0.8877, + "step": 2982 + }, + { + "epoch": 0.2670994459678773, + "grad_norm": 0.9175059226140866, + "learning_rate": 1.7195054337989285e-05, + "loss": 0.9403, + "step": 2983 + }, + { + "epoch": 0.2671889865129554, + "grad_norm": 1.0770342021760735, + "learning_rate": 1.7193039823197324e-05, + "loss": 0.8717, + "step": 2984 + }, + { + "epoch": 0.26727852705803345, + "grad_norm": 0.8590796192203384, + "learning_rate": 1.7191024703350295e-05, + "loss": 0.8595, + "step": 2985 + }, + { + "epoch": 0.26736806760311155, + "grad_norm": 0.9572147643639068, + "learning_rate": 1.7189008978617702e-05, + "loss": 0.8855, + "step": 2986 + }, + { + "epoch": 0.2674576081481896, + "grad_norm": 0.8686870289377042, + "learning_rate": 1.71869926491691e-05, + "loss": 0.8581, + "step": 2987 + }, + { + "epoch": 0.2675471486932677, + "grad_norm": 1.007483744761067, + "learning_rate": 1.7184975715174096e-05, + "loss": 0.8752, + "step": 2988 + }, + { + "epoch": 0.2676366892383457, + "grad_norm": 0.9344890082206477, + "learning_rate": 1.7182958176802352e-05, + "loss": 0.8583, + "step": 2989 + }, + { + "epoch": 0.2677262297834238, + "grad_norm": 0.9828676832282021, + "learning_rate": 1.7180940034223566e-05, + "loss": 0.8496, + "step": 2990 + }, + { + "epoch": 0.2678157703285019, + "grad_norm": 1.06045556196744, + "learning_rate": 1.717892128760751e-05, + "loss": 0.8655, + "step": 2991 + }, + { + "epoch": 0.26790531087357994, + "grad_norm": 0.9627821456796015, + "learning_rate": 1.717690193712399e-05, + "loss": 0.8977, + "step": 2992 + }, + { + "epoch": 0.26799485141865803, + "grad_norm": 0.944053559039206, + "learning_rate": 1.7174881982942865e-05, + "loss": 0.8988, + "step": 2993 + }, + { + "epoch": 0.26808439196373607, + "grad_norm": 0.9984368175835054, + "learning_rate": 1.717286142523405e-05, + "loss": 0.8453, + "step": 2994 + }, + { + "epoch": 0.26817393250881416, + "grad_norm": 0.922179263049267, + "learning_rate": 1.71708402641675e-05, + "loss": 0.901, + "step": 2995 + }, + { + "epoch": 0.2682634730538922, + "grad_norm": 1.0223060532248, + "learning_rate": 1.716881849991324e-05, + "loss": 0.8952, + "step": 2996 + }, + { + "epoch": 0.2683530135989703, + "grad_norm": 0.9169053924386658, + "learning_rate": 1.716679613264133e-05, + "loss": 0.8601, + "step": 2997 + }, + { + "epoch": 0.26844255414404833, + "grad_norm": 0.9488880944826082, + "learning_rate": 1.716477316252188e-05, + "loss": 0.8166, + "step": 2998 + }, + { + "epoch": 0.2685320946891264, + "grad_norm": 1.0417405292844477, + "learning_rate": 1.716274958972506e-05, + "loss": 0.8374, + "step": 2999 + }, + { + "epoch": 0.2686216352342045, + "grad_norm": 1.0182194694986495, + "learning_rate": 1.7160725414421086e-05, + "loss": 0.8809, + "step": 3000 + }, + { + "epoch": 0.26871117577928255, + "grad_norm": 0.9467863834263519, + "learning_rate": 1.715870063678023e-05, + "loss": 0.8612, + "step": 3001 + }, + { + "epoch": 0.26880071632436064, + "grad_norm": 0.8714370418249684, + "learning_rate": 1.7156675256972797e-05, + "loss": 0.8756, + "step": 3002 + }, + { + "epoch": 0.2688902568694387, + "grad_norm": 0.8648193527507475, + "learning_rate": 1.7154649275169167e-05, + "loss": 0.8433, + "step": 3003 + }, + { + "epoch": 0.2689797974145168, + "grad_norm": 0.963704783617534, + "learning_rate": 1.7152622691539754e-05, + "loss": 0.9282, + "step": 3004 + }, + { + "epoch": 0.2690693379595948, + "grad_norm": 0.9691179898919868, + "learning_rate": 1.715059550625503e-05, + "loss": 0.8674, + "step": 3005 + }, + { + "epoch": 0.2691588785046729, + "grad_norm": 0.9245910145770874, + "learning_rate": 1.714856771948551e-05, + "loss": 0.8638, + "step": 3006 + }, + { + "epoch": 0.26924841904975094, + "grad_norm": 1.0444269751758923, + "learning_rate": 1.714653933140177e-05, + "loss": 0.8999, + "step": 3007 + }, + { + "epoch": 0.26933795959482904, + "grad_norm": 0.9639871616594202, + "learning_rate": 1.714451034217443e-05, + "loss": 0.8979, + "step": 3008 + }, + { + "epoch": 0.26942750013990713, + "grad_norm": 1.0743706570345868, + "learning_rate": 1.7142480751974166e-05, + "loss": 0.8879, + "step": 3009 + }, + { + "epoch": 0.26951704068498517, + "grad_norm": 0.9904629185277329, + "learning_rate": 1.714045056097169e-05, + "loss": 0.8812, + "step": 3010 + }, + { + "epoch": 0.26960658123006326, + "grad_norm": 1.005673568474522, + "learning_rate": 1.7138419769337783e-05, + "loss": 0.9492, + "step": 3011 + }, + { + "epoch": 0.2696961217751413, + "grad_norm": 0.9719798847545754, + "learning_rate": 1.713638837724327e-05, + "loss": 0.8753, + "step": 3012 + }, + { + "epoch": 0.2697856623202194, + "grad_norm": 0.8843175251777998, + "learning_rate": 1.713435638485902e-05, + "loss": 0.8578, + "step": 3013 + }, + { + "epoch": 0.2698752028652974, + "grad_norm": 0.9612583039263236, + "learning_rate": 1.713232379235596e-05, + "loss": 0.8927, + "step": 3014 + }, + { + "epoch": 0.2699647434103755, + "grad_norm": 0.990009204752591, + "learning_rate": 1.7130290599905064e-05, + "loss": 0.8254, + "step": 3015 + }, + { + "epoch": 0.27005428395545356, + "grad_norm": 0.8656763040294388, + "learning_rate": 1.7128256807677357e-05, + "loss": 0.8322, + "step": 3016 + }, + { + "epoch": 0.27014382450053165, + "grad_norm": 0.8575523454398983, + "learning_rate": 1.712622241584392e-05, + "loss": 0.8449, + "step": 3017 + }, + { + "epoch": 0.27023336504560974, + "grad_norm": 0.9570602507319353, + "learning_rate": 1.7124187424575874e-05, + "loss": 0.8874, + "step": 3018 + }, + { + "epoch": 0.2703229055906878, + "grad_norm": 1.0718856139401851, + "learning_rate": 1.7122151834044398e-05, + "loss": 0.7851, + "step": 3019 + }, + { + "epoch": 0.27041244613576587, + "grad_norm": 0.9891111012225225, + "learning_rate": 1.7120115644420715e-05, + "loss": 0.8794, + "step": 3020 + }, + { + "epoch": 0.2705019866808439, + "grad_norm": 1.0637752056060539, + "learning_rate": 1.711807885587611e-05, + "loss": 0.8702, + "step": 3021 + }, + { + "epoch": 0.270591527225922, + "grad_norm": 0.8678973860819694, + "learning_rate": 1.711604146858191e-05, + "loss": 0.9016, + "step": 3022 + }, + { + "epoch": 0.27068106777100004, + "grad_norm": 0.9133847924152949, + "learning_rate": 1.7114003482709485e-05, + "loss": 0.8923, + "step": 3023 + }, + { + "epoch": 0.27077060831607813, + "grad_norm": 1.1361075412547286, + "learning_rate": 1.711196489843027e-05, + "loss": 0.8545, + "step": 3024 + }, + { + "epoch": 0.27086014886115617, + "grad_norm": 0.957147657766586, + "learning_rate": 1.7109925715915746e-05, + "loss": 0.8984, + "step": 3025 + }, + { + "epoch": 0.27094968940623426, + "grad_norm": 0.9842822921013271, + "learning_rate": 1.710788593533744e-05, + "loss": 0.8922, + "step": 3026 + }, + { + "epoch": 0.27103922995131235, + "grad_norm": 1.0467396411551855, + "learning_rate": 1.7105845556866932e-05, + "loss": 0.8785, + "step": 3027 + }, + { + "epoch": 0.2711287704963904, + "grad_norm": 0.9339037570821632, + "learning_rate": 1.7103804580675846e-05, + "loss": 0.8783, + "step": 3028 + }, + { + "epoch": 0.2712183110414685, + "grad_norm": 0.9532689140019491, + "learning_rate": 1.7101763006935873e-05, + "loss": 0.9014, + "step": 3029 + }, + { + "epoch": 0.2713078515865465, + "grad_norm": 1.0961636011208542, + "learning_rate": 1.709972083581874e-05, + "loss": 0.932, + "step": 3030 + }, + { + "epoch": 0.2713973921316246, + "grad_norm": 1.0034877688365238, + "learning_rate": 1.709767806749622e-05, + "loss": 0.8375, + "step": 3031 + }, + { + "epoch": 0.27148693267670265, + "grad_norm": 0.9680004256002208, + "learning_rate": 1.7095634702140154e-05, + "loss": 0.9148, + "step": 3032 + }, + { + "epoch": 0.27157647322178075, + "grad_norm": 1.0393882284921006, + "learning_rate": 1.7093590739922424e-05, + "loss": 0.8703, + "step": 3033 + }, + { + "epoch": 0.2716660137668588, + "grad_norm": 0.9787746862538466, + "learning_rate": 1.7091546181014952e-05, + "loss": 0.8287, + "step": 3034 + }, + { + "epoch": 0.2717555543119369, + "grad_norm": 0.9318422087289375, + "learning_rate": 1.708950102558972e-05, + "loss": 0.878, + "step": 3035 + }, + { + "epoch": 0.27184509485701497, + "grad_norm": 0.8817689498534514, + "learning_rate": 1.7087455273818774e-05, + "loss": 0.8793, + "step": 3036 + }, + { + "epoch": 0.271934635402093, + "grad_norm": 0.9805970947585829, + "learning_rate": 1.708540892587418e-05, + "loss": 0.8464, + "step": 3037 + }, + { + "epoch": 0.2720241759471711, + "grad_norm": 1.1290119685498867, + "learning_rate": 1.7083361981928077e-05, + "loss": 0.8707, + "step": 3038 + }, + { + "epoch": 0.27211371649224914, + "grad_norm": 0.9376039190267978, + "learning_rate": 1.708131444215265e-05, + "loss": 0.8696, + "step": 3039 + }, + { + "epoch": 0.27220325703732723, + "grad_norm": 0.9383608008638069, + "learning_rate": 1.7079266306720125e-05, + "loss": 0.8874, + "step": 3040 + }, + { + "epoch": 0.27229279758240527, + "grad_norm": 0.8972142357320703, + "learning_rate": 1.7077217575802785e-05, + "loss": 0.8176, + "step": 3041 + }, + { + "epoch": 0.27238233812748336, + "grad_norm": 0.9516260153267242, + "learning_rate": 1.707516824957297e-05, + "loss": 0.8596, + "step": 3042 + }, + { + "epoch": 0.2724718786725614, + "grad_norm": 1.1498236350718762, + "learning_rate": 1.7073118328203055e-05, + "loss": 0.8921, + "step": 3043 + }, + { + "epoch": 0.2725614192176395, + "grad_norm": 0.8980761727006406, + "learning_rate": 1.7071067811865477e-05, + "loss": 0.7968, + "step": 3044 + }, + { + "epoch": 0.2726509597627176, + "grad_norm": 1.2016333409470468, + "learning_rate": 1.7069016700732714e-05, + "loss": 0.91, + "step": 3045 + }, + { + "epoch": 0.2727405003077956, + "grad_norm": 0.9310197362402982, + "learning_rate": 1.706696499497731e-05, + "loss": 0.8727, + "step": 3046 + }, + { + "epoch": 0.2728300408528737, + "grad_norm": 1.0248901546481457, + "learning_rate": 1.7064912694771832e-05, + "loss": 0.9117, + "step": 3047 + }, + { + "epoch": 0.27291958139795175, + "grad_norm": 0.9568207149098361, + "learning_rate": 1.7062859800288923e-05, + "loss": 0.866, + "step": 3048 + }, + { + "epoch": 0.27300912194302984, + "grad_norm": 1.0116632966060441, + "learning_rate": 1.706080631170126e-05, + "loss": 0.8721, + "step": 3049 + }, + { + "epoch": 0.2730986624881079, + "grad_norm": 0.8971182858081596, + "learning_rate": 1.7058752229181585e-05, + "loss": 0.8404, + "step": 3050 + }, + { + "epoch": 0.273188203033186, + "grad_norm": 0.96007596800799, + "learning_rate": 1.705669755290267e-05, + "loss": 0.8559, + "step": 3051 + }, + { + "epoch": 0.273277743578264, + "grad_norm": 0.8911357190975704, + "learning_rate": 1.7054642283037356e-05, + "loss": 0.8749, + "step": 3052 + }, + { + "epoch": 0.2733672841233421, + "grad_norm": 0.9376006334398593, + "learning_rate": 1.705258641975852e-05, + "loss": 0.8759, + "step": 3053 + }, + { + "epoch": 0.2734568246684202, + "grad_norm": 1.0219150425146417, + "learning_rate": 1.70505299632391e-05, + "loss": 0.8268, + "step": 3054 + }, + { + "epoch": 0.27354636521349823, + "grad_norm": 0.8999727313506765, + "learning_rate": 1.7048472913652073e-05, + "loss": 0.854, + "step": 3055 + }, + { + "epoch": 0.2736359057585763, + "grad_norm": 0.8654714995750459, + "learning_rate": 1.704641527117047e-05, + "loss": 0.891, + "step": 3056 + }, + { + "epoch": 0.27372544630365436, + "grad_norm": 0.8667614459768594, + "learning_rate": 1.7044357035967382e-05, + "loss": 0.8516, + "step": 3057 + }, + { + "epoch": 0.27381498684873246, + "grad_norm": 0.9826709674736025, + "learning_rate": 1.704229820821593e-05, + "loss": 0.8523, + "step": 3058 + }, + { + "epoch": 0.2739045273938105, + "grad_norm": 0.867346385767419, + "learning_rate": 1.7040238788089304e-05, + "loss": 0.8586, + "step": 3059 + }, + { + "epoch": 0.2739940679388886, + "grad_norm": 0.964219742865869, + "learning_rate": 1.7038178775760738e-05, + "loss": 0.832, + "step": 3060 + }, + { + "epoch": 0.2740836084839666, + "grad_norm": 0.8857639573684032, + "learning_rate": 1.70361181714035e-05, + "loss": 0.8714, + "step": 3061 + }, + { + "epoch": 0.2741731490290447, + "grad_norm": 0.9058464580598033, + "learning_rate": 1.703405697519094e-05, + "loss": 0.8259, + "step": 3062 + }, + { + "epoch": 0.2742626895741228, + "grad_norm": 1.0272622265971423, + "learning_rate": 1.703199518729642e-05, + "loss": 0.8738, + "step": 3063 + }, + { + "epoch": 0.27435223011920085, + "grad_norm": 0.9512762416372345, + "learning_rate": 1.7029932807893383e-05, + "loss": 0.8917, + "step": 3064 + }, + { + "epoch": 0.27444177066427894, + "grad_norm": 0.9845303147881898, + "learning_rate": 1.702786983715531e-05, + "loss": 0.9263, + "step": 3065 + }, + { + "epoch": 0.274531311209357, + "grad_norm": 1.1071745281630738, + "learning_rate": 1.702580627525572e-05, + "loss": 0.9408, + "step": 3066 + }, + { + "epoch": 0.27462085175443507, + "grad_norm": 1.1012996254153433, + "learning_rate": 1.702374212236821e-05, + "loss": 0.8262, + "step": 3067 + }, + { + "epoch": 0.2747103922995131, + "grad_norm": 0.8572665031294724, + "learning_rate": 1.7021677378666398e-05, + "loss": 0.8748, + "step": 3068 + }, + { + "epoch": 0.2747999328445912, + "grad_norm": 0.9098357465077431, + "learning_rate": 1.7019612044323965e-05, + "loss": 0.8504, + "step": 3069 + }, + { + "epoch": 0.27488947338966924, + "grad_norm": 0.892031050161679, + "learning_rate": 1.7017546119514645e-05, + "loss": 0.8496, + "step": 3070 + }, + { + "epoch": 0.27497901393474733, + "grad_norm": 0.9957505953895591, + "learning_rate": 1.701547960441221e-05, + "loss": 0.8411, + "step": 3071 + }, + { + "epoch": 0.2750685544798254, + "grad_norm": 1.0652254095574978, + "learning_rate": 1.7013412499190494e-05, + "loss": 0.8878, + "step": 3072 + }, + { + "epoch": 0.27515809502490346, + "grad_norm": 1.0215215181599415, + "learning_rate": 1.7011344804023373e-05, + "loss": 0.9094, + "step": 3073 + }, + { + "epoch": 0.27524763556998155, + "grad_norm": 1.1046706587742765, + "learning_rate": 1.7009276519084773e-05, + "loss": 0.8987, + "step": 3074 + }, + { + "epoch": 0.2753371761150596, + "grad_norm": 0.8928684793987689, + "learning_rate": 1.7007207644548676e-05, + "loss": 0.8692, + "step": 3075 + }, + { + "epoch": 0.2754267166601377, + "grad_norm": 0.9619248627125876, + "learning_rate": 1.7005138180589106e-05, + "loss": 0.8816, + "step": 3076 + }, + { + "epoch": 0.2755162572052157, + "grad_norm": 0.8712901864519633, + "learning_rate": 1.7003068127380137e-05, + "loss": 0.803, + "step": 3077 + }, + { + "epoch": 0.2756057977502938, + "grad_norm": 0.8991245777475443, + "learning_rate": 1.70009974850959e-05, + "loss": 0.8522, + "step": 3078 + }, + { + "epoch": 0.27569533829537185, + "grad_norm": 1.066699976232185, + "learning_rate": 1.699892625391057e-05, + "loss": 0.8327, + "step": 3079 + }, + { + "epoch": 0.27578487884044994, + "grad_norm": 0.9405816531286452, + "learning_rate": 1.6996854433998368e-05, + "loss": 0.8219, + "step": 3080 + }, + { + "epoch": 0.27587441938552804, + "grad_norm": 0.9143267340472762, + "learning_rate": 1.6994782025533574e-05, + "loss": 0.8814, + "step": 3081 + }, + { + "epoch": 0.2759639599306061, + "grad_norm": 0.9114202102861547, + "learning_rate": 1.699270902869051e-05, + "loss": 0.8652, + "step": 3082 + }, + { + "epoch": 0.27605350047568417, + "grad_norm": 0.8354509720765657, + "learning_rate": 1.6990635443643547e-05, + "loss": 0.818, + "step": 3083 + }, + { + "epoch": 0.2761430410207622, + "grad_norm": 1.0405536079119269, + "learning_rate": 1.6988561270567116e-05, + "loss": 0.8837, + "step": 3084 + }, + { + "epoch": 0.2762325815658403, + "grad_norm": 1.047074511681417, + "learning_rate": 1.698648650963568e-05, + "loss": 0.9219, + "step": 3085 + }, + { + "epoch": 0.27632212211091833, + "grad_norm": 1.085045915828381, + "learning_rate": 1.6984411161023765e-05, + "loss": 0.8885, + "step": 3086 + }, + { + "epoch": 0.2764116626559964, + "grad_norm": 0.9039733612137021, + "learning_rate": 1.698233522490595e-05, + "loss": 0.8394, + "step": 3087 + }, + { + "epoch": 0.27650120320107446, + "grad_norm": 0.9875549274478735, + "learning_rate": 1.6980258701456843e-05, + "loss": 0.826, + "step": 3088 + }, + { + "epoch": 0.27659074374615256, + "grad_norm": 0.9722767019244013, + "learning_rate": 1.6978181590851123e-05, + "loss": 0.9195, + "step": 3089 + }, + { + "epoch": 0.27668028429123065, + "grad_norm": 0.8648326537411496, + "learning_rate": 1.6976103893263507e-05, + "loss": 0.8188, + "step": 3090 + }, + { + "epoch": 0.2767698248363087, + "grad_norm": 0.959990445898637, + "learning_rate": 1.6974025608868765e-05, + "loss": 0.8886, + "step": 3091 + }, + { + "epoch": 0.2768593653813868, + "grad_norm": 0.9331415629386074, + "learning_rate": 1.6971946737841715e-05, + "loss": 0.8691, + "step": 3092 + }, + { + "epoch": 0.2769489059264648, + "grad_norm": 1.1251824690994092, + "learning_rate": 1.6969867280357224e-05, + "loss": 0.9197, + "step": 3093 + }, + { + "epoch": 0.2770384464715429, + "grad_norm": 0.9581851646411722, + "learning_rate": 1.696778723659021e-05, + "loss": 0.8276, + "step": 3094 + }, + { + "epoch": 0.27712798701662095, + "grad_norm": 0.9725773952360081, + "learning_rate": 1.6965706606715642e-05, + "loss": 0.8737, + "step": 3095 + }, + { + "epoch": 0.27721752756169904, + "grad_norm": 1.0160289896436507, + "learning_rate": 1.696362539090853e-05, + "loss": 0.9064, + "step": 3096 + }, + { + "epoch": 0.2773070681067771, + "grad_norm": 1.0309838177317907, + "learning_rate": 1.6961543589343943e-05, + "loss": 0.892, + "step": 3097 + }, + { + "epoch": 0.27739660865185517, + "grad_norm": 1.063620923469998, + "learning_rate": 1.6959461202196996e-05, + "loss": 0.8997, + "step": 3098 + }, + { + "epoch": 0.27748614919693326, + "grad_norm": 0.9414588229692542, + "learning_rate": 1.695737822964285e-05, + "loss": 0.8975, + "step": 3099 + }, + { + "epoch": 0.2775756897420113, + "grad_norm": 0.9080463366377379, + "learning_rate": 1.6955294671856722e-05, + "loss": 0.8409, + "step": 3100 + }, + { + "epoch": 0.2776652302870894, + "grad_norm": 0.9738420195506777, + "learning_rate": 1.695321052901387e-05, + "loss": 0.864, + "step": 3101 + }, + { + "epoch": 0.27775477083216743, + "grad_norm": 1.127570733232605, + "learning_rate": 1.6951125801289607e-05, + "loss": 0.8843, + "step": 3102 + }, + { + "epoch": 0.2778443113772455, + "grad_norm": 0.982627905859027, + "learning_rate": 1.6949040488859295e-05, + "loss": 0.8922, + "step": 3103 + }, + { + "epoch": 0.27793385192232356, + "grad_norm": 0.9799994241542295, + "learning_rate": 1.694695459189834e-05, + "loss": 0.8381, + "step": 3104 + }, + { + "epoch": 0.27802339246740165, + "grad_norm": 1.0105176473099975, + "learning_rate": 1.69448681105822e-05, + "loss": 0.8151, + "step": 3105 + }, + { + "epoch": 0.2781129330124797, + "grad_norm": 0.9097175995774183, + "learning_rate": 1.6942781045086393e-05, + "loss": 0.8855, + "step": 3106 + }, + { + "epoch": 0.2782024735575578, + "grad_norm": 1.0698651249211961, + "learning_rate": 1.6940693395586463e-05, + "loss": 0.849, + "step": 3107 + }, + { + "epoch": 0.2782920141026359, + "grad_norm": 0.8569301023322689, + "learning_rate": 1.6938605162258026e-05, + "loss": 0.9053, + "step": 3108 + }, + { + "epoch": 0.2783815546477139, + "grad_norm": 0.9400385040489173, + "learning_rate": 1.693651634527673e-05, + "loss": 0.8632, + "step": 3109 + }, + { + "epoch": 0.278471095192792, + "grad_norm": 1.0149695002740913, + "learning_rate": 1.6934426944818282e-05, + "loss": 0.8935, + "step": 3110 + }, + { + "epoch": 0.27856063573787004, + "grad_norm": 1.0552194694178423, + "learning_rate": 1.693233696105844e-05, + "loss": 0.8733, + "step": 3111 + }, + { + "epoch": 0.27865017628294814, + "grad_norm": 1.1355533437834913, + "learning_rate": 1.6930246394173004e-05, + "loss": 0.8698, + "step": 3112 + }, + { + "epoch": 0.2787397168280262, + "grad_norm": 1.0666585348230584, + "learning_rate": 1.6928155244337823e-05, + "loss": 0.9067, + "step": 3113 + }, + { + "epoch": 0.27882925737310427, + "grad_norm": 0.9202935513746124, + "learning_rate": 1.69260635117288e-05, + "loss": 0.8713, + "step": 3114 + }, + { + "epoch": 0.2789187979181823, + "grad_norm": 0.8445833839258885, + "learning_rate": 1.6923971196521886e-05, + "loss": 0.8701, + "step": 3115 + }, + { + "epoch": 0.2790083384632604, + "grad_norm": 0.9486270967806315, + "learning_rate": 1.6921878298893076e-05, + "loss": 0.8768, + "step": 3116 + }, + { + "epoch": 0.2790978790083385, + "grad_norm": 0.9661193519913366, + "learning_rate": 1.691978481901842e-05, + "loss": 0.9441, + "step": 3117 + }, + { + "epoch": 0.2791874195534165, + "grad_norm": 0.9714688665814267, + "learning_rate": 1.6917690757074018e-05, + "loss": 0.9137, + "step": 3118 + }, + { + "epoch": 0.2792769600984946, + "grad_norm": 0.9617206889423764, + "learning_rate": 1.6915596113236006e-05, + "loss": 0.8634, + "step": 3119 + }, + { + "epoch": 0.27936650064357266, + "grad_norm": 1.0010342672971355, + "learning_rate": 1.6913500887680588e-05, + "loss": 0.8693, + "step": 3120 + }, + { + "epoch": 0.27945604118865075, + "grad_norm": 1.7189605556600702, + "learning_rate": 1.6911405080584003e-05, + "loss": 0.862, + "step": 3121 + }, + { + "epoch": 0.2795455817337288, + "grad_norm": 0.9527797015057667, + "learning_rate": 1.690930869212255e-05, + "loss": 0.8664, + "step": 3122 + }, + { + "epoch": 0.2796351222788069, + "grad_norm": 0.9070381882554512, + "learning_rate": 1.690721172247256e-05, + "loss": 0.8324, + "step": 3123 + }, + { + "epoch": 0.2797246628238849, + "grad_norm": 0.9154452725309471, + "learning_rate": 1.6905114171810432e-05, + "loss": 0.8702, + "step": 3124 + }, + { + "epoch": 0.279814203368963, + "grad_norm": 0.9517578403734541, + "learning_rate": 1.69030160403126e-05, + "loss": 0.8624, + "step": 3125 + }, + { + "epoch": 0.2799037439140411, + "grad_norm": 1.0221252173679627, + "learning_rate": 1.6900917328155552e-05, + "loss": 0.887, + "step": 3126 + }, + { + "epoch": 0.27999328445911914, + "grad_norm": 0.9692741553919281, + "learning_rate": 1.6898818035515825e-05, + "loss": 0.8901, + "step": 3127 + }, + { + "epoch": 0.28008282500419723, + "grad_norm": 0.877399179411387, + "learning_rate": 1.689671816257001e-05, + "loss": 0.8423, + "step": 3128 + }, + { + "epoch": 0.28017236554927527, + "grad_norm": 1.0635639511469, + "learning_rate": 1.6894617709494738e-05, + "loss": 0.8995, + "step": 3129 + }, + { + "epoch": 0.28026190609435336, + "grad_norm": 0.9578175391218497, + "learning_rate": 1.6892516676466687e-05, + "loss": 0.9025, + "step": 3130 + }, + { + "epoch": 0.2803514466394314, + "grad_norm": 0.8925553036324171, + "learning_rate": 1.6890415063662598e-05, + "loss": 0.9257, + "step": 3131 + }, + { + "epoch": 0.2804409871845095, + "grad_norm": 0.9436066066607104, + "learning_rate": 1.6888312871259247e-05, + "loss": 0.7947, + "step": 3132 + }, + { + "epoch": 0.28053052772958753, + "grad_norm": 0.934782451206911, + "learning_rate": 1.6886210099433464e-05, + "loss": 0.8318, + "step": 3133 + }, + { + "epoch": 0.2806200682746656, + "grad_norm": 0.9893400437244729, + "learning_rate": 1.6884106748362126e-05, + "loss": 0.8912, + "step": 3134 + }, + { + "epoch": 0.2807096088197437, + "grad_norm": 0.9954061664473843, + "learning_rate": 1.6882002818222166e-05, + "loss": 0.9053, + "step": 3135 + }, + { + "epoch": 0.28079914936482175, + "grad_norm": 1.2088354187050214, + "learning_rate": 1.687989830919055e-05, + "loss": 0.8329, + "step": 3136 + }, + { + "epoch": 0.28088868990989985, + "grad_norm": 1.1303027412862616, + "learning_rate": 1.687779322144431e-05, + "loss": 0.8632, + "step": 3137 + }, + { + "epoch": 0.2809782304549779, + "grad_norm": 0.9371182588200657, + "learning_rate": 1.6875687555160518e-05, + "loss": 0.8885, + "step": 3138 + }, + { + "epoch": 0.281067771000056, + "grad_norm": 0.9134839991096796, + "learning_rate": 1.6873581310516294e-05, + "loss": 0.8213, + "step": 3139 + }, + { + "epoch": 0.281157311545134, + "grad_norm": 0.9527635748717829, + "learning_rate": 1.687147448768881e-05, + "loss": 0.8964, + "step": 3140 + }, + { + "epoch": 0.2812468520902121, + "grad_norm": 0.961195586870507, + "learning_rate": 1.6869367086855278e-05, + "loss": 0.8575, + "step": 3141 + }, + { + "epoch": 0.28133639263529014, + "grad_norm": 0.9936313187569966, + "learning_rate": 1.686725910819298e-05, + "loss": 0.8735, + "step": 3142 + }, + { + "epoch": 0.28142593318036824, + "grad_norm": 0.9229324559597707, + "learning_rate": 1.686515055187922e-05, + "loss": 0.8565, + "step": 3143 + }, + { + "epoch": 0.28151547372544633, + "grad_norm": 1.0360846237257146, + "learning_rate": 1.686304141809137e-05, + "loss": 0.8534, + "step": 3144 + }, + { + "epoch": 0.28160501427052437, + "grad_norm": 1.063979130548798, + "learning_rate": 1.6860931707006835e-05, + "loss": 0.8838, + "step": 3145 + }, + { + "epoch": 0.28169455481560246, + "grad_norm": 1.018000566188955, + "learning_rate": 1.6858821418803087e-05, + "loss": 0.8486, + "step": 3146 + }, + { + "epoch": 0.2817840953606805, + "grad_norm": 0.978518777762257, + "learning_rate": 1.6856710553657633e-05, + "loss": 0.8395, + "step": 3147 + }, + { + "epoch": 0.2818736359057586, + "grad_norm": 0.9632930919649931, + "learning_rate": 1.6854599111748027e-05, + "loss": 0.8487, + "step": 3148 + }, + { + "epoch": 0.28196317645083663, + "grad_norm": 0.9913011775405436, + "learning_rate": 1.6852487093251883e-05, + "loss": 0.9697, + "step": 3149 + }, + { + "epoch": 0.2820527169959147, + "grad_norm": 0.9200299120201978, + "learning_rate": 1.6850374498346857e-05, + "loss": 0.8338, + "step": 3150 + }, + { + "epoch": 0.28214225754099276, + "grad_norm": 1.0368439154423343, + "learning_rate": 1.684826132721065e-05, + "loss": 0.8935, + "step": 3151 + }, + { + "epoch": 0.28223179808607085, + "grad_norm": 0.941217170401303, + "learning_rate": 1.6846147580021016e-05, + "loss": 0.8904, + "step": 3152 + }, + { + "epoch": 0.28232133863114894, + "grad_norm": 1.0103885923103557, + "learning_rate": 1.684403325695576e-05, + "loss": 0.8674, + "step": 3153 + }, + { + "epoch": 0.282410879176227, + "grad_norm": 2.2109009147192697, + "learning_rate": 1.6841918358192725e-05, + "loss": 0.8851, + "step": 3154 + }, + { + "epoch": 0.2825004197213051, + "grad_norm": 1.218619033777584, + "learning_rate": 1.6839802883909814e-05, + "loss": 0.8428, + "step": 3155 + }, + { + "epoch": 0.2825899602663831, + "grad_norm": 0.912222411542443, + "learning_rate": 1.6837686834284978e-05, + "loss": 0.8708, + "step": 3156 + }, + { + "epoch": 0.2826795008114612, + "grad_norm": 0.9421602152747818, + "learning_rate": 1.6835570209496198e-05, + "loss": 0.8325, + "step": 3157 + }, + { + "epoch": 0.28276904135653924, + "grad_norm": 0.9882926023918414, + "learning_rate": 1.6833453009721538e-05, + "loss": 0.8711, + "step": 3158 + }, + { + "epoch": 0.28285858190161733, + "grad_norm": 0.9383150192373714, + "learning_rate": 1.6831335235139072e-05, + "loss": 0.8846, + "step": 3159 + }, + { + "epoch": 0.28294812244669537, + "grad_norm": 0.9719857845357589, + "learning_rate": 1.682921688592695e-05, + "loss": 0.8984, + "step": 3160 + }, + { + "epoch": 0.28303766299177346, + "grad_norm": 1.05405485655929, + "learning_rate": 1.6827097962263355e-05, + "loss": 0.8654, + "step": 3161 + }, + { + "epoch": 0.28312720353685156, + "grad_norm": 0.8836666319954309, + "learning_rate": 1.682497846432653e-05, + "loss": 0.8313, + "step": 3162 + }, + { + "epoch": 0.2832167440819296, + "grad_norm": 0.9290851947248366, + "learning_rate": 1.6822858392294757e-05, + "loss": 0.8965, + "step": 3163 + }, + { + "epoch": 0.2833062846270077, + "grad_norm": 1.0476084424923817, + "learning_rate": 1.682073774634637e-05, + "loss": 0.8854, + "step": 3164 + }, + { + "epoch": 0.2833958251720857, + "grad_norm": 1.0092516907196987, + "learning_rate": 1.681861652665975e-05, + "loss": 0.8806, + "step": 3165 + }, + { + "epoch": 0.2834853657171638, + "grad_norm": 0.9410850844630412, + "learning_rate": 1.6816494733413328e-05, + "loss": 0.8895, + "step": 3166 + }, + { + "epoch": 0.28357490626224185, + "grad_norm": 0.9700542279555697, + "learning_rate": 1.6814372366785578e-05, + "loss": 0.8454, + "step": 3167 + }, + { + "epoch": 0.28366444680731995, + "grad_norm": 0.9189909588025574, + "learning_rate": 1.6812249426955033e-05, + "loss": 0.8744, + "step": 3168 + }, + { + "epoch": 0.283753987352398, + "grad_norm": 0.9532373661627619, + "learning_rate": 1.681012591410027e-05, + "loss": 0.8888, + "step": 3169 + }, + { + "epoch": 0.2838435278974761, + "grad_norm": 0.9007629322296989, + "learning_rate": 1.68080018283999e-05, + "loss": 0.8653, + "step": 3170 + }, + { + "epoch": 0.28393306844255417, + "grad_norm": 0.9726798464553322, + "learning_rate": 1.6805877170032606e-05, + "loss": 0.856, + "step": 3171 + }, + { + "epoch": 0.2840226089876322, + "grad_norm": 1.082492427837062, + "learning_rate": 1.68037519391771e-05, + "loss": 0.868, + "step": 3172 + }, + { + "epoch": 0.2841121495327103, + "grad_norm": 0.9337689528416439, + "learning_rate": 1.6801626136012156e-05, + "loss": 0.8919, + "step": 3173 + }, + { + "epoch": 0.28420169007778834, + "grad_norm": 0.9288505031886436, + "learning_rate": 1.6799499760716585e-05, + "loss": 0.8202, + "step": 3174 + }, + { + "epoch": 0.28429123062286643, + "grad_norm": 0.9851516248059862, + "learning_rate": 1.679737281346925e-05, + "loss": 0.7852, + "step": 3175 + }, + { + "epoch": 0.28438077116794447, + "grad_norm": 1.1260358212500687, + "learning_rate": 1.6795245294449064e-05, + "loss": 0.8506, + "step": 3176 + }, + { + "epoch": 0.28447031171302256, + "grad_norm": 1.0816490171705435, + "learning_rate": 1.679311720383499e-05, + "loss": 0.9042, + "step": 3177 + }, + { + "epoch": 0.2845598522581006, + "grad_norm": 0.9284832811636621, + "learning_rate": 1.679098854180603e-05, + "loss": 0.8699, + "step": 3178 + }, + { + "epoch": 0.2846493928031787, + "grad_norm": 0.9240882171752225, + "learning_rate": 1.6788859308541247e-05, + "loss": 0.8503, + "step": 3179 + }, + { + "epoch": 0.2847389333482568, + "grad_norm": 0.9492275023529425, + "learning_rate": 1.6786729504219742e-05, + "loss": 0.9595, + "step": 3180 + }, + { + "epoch": 0.2848284738933348, + "grad_norm": 0.923039712222499, + "learning_rate": 1.678459912902066e-05, + "loss": 0.8494, + "step": 3181 + }, + { + "epoch": 0.2849180144384129, + "grad_norm": 0.9552713670981043, + "learning_rate": 1.6782468183123217e-05, + "loss": 0.9128, + "step": 3182 + }, + { + "epoch": 0.28500755498349095, + "grad_norm": 0.8506558342602634, + "learning_rate": 1.678033666670665e-05, + "loss": 0.8859, + "step": 3183 + }, + { + "epoch": 0.28509709552856904, + "grad_norm": 0.9629396093085503, + "learning_rate": 1.6778204579950258e-05, + "loss": 0.8589, + "step": 3184 + }, + { + "epoch": 0.2851866360736471, + "grad_norm": 1.0037891788764925, + "learning_rate": 1.6776071923033383e-05, + "loss": 0.9333, + "step": 3185 + }, + { + "epoch": 0.2852761766187252, + "grad_norm": 0.9684746932044083, + "learning_rate": 1.677393869613542e-05, + "loss": 0.8025, + "step": 3186 + }, + { + "epoch": 0.2853657171638032, + "grad_norm": 0.8881307168188709, + "learning_rate": 1.6771804899435808e-05, + "loss": 0.9054, + "step": 3187 + }, + { + "epoch": 0.2854552577088813, + "grad_norm": 1.045375343901422, + "learning_rate": 1.6769670533114037e-05, + "loss": 0.8514, + "step": 3188 + }, + { + "epoch": 0.2855447982539594, + "grad_norm": 0.9132102557526443, + "learning_rate": 1.676753559734964e-05, + "loss": 0.8672, + "step": 3189 + }, + { + "epoch": 0.28563433879903743, + "grad_norm": 0.9442172320512818, + "learning_rate": 1.67654000923222e-05, + "loss": 0.892, + "step": 3190 + }, + { + "epoch": 0.28572387934411553, + "grad_norm": 1.0397387459452976, + "learning_rate": 1.676326401821135e-05, + "loss": 0.8724, + "step": 3191 + }, + { + "epoch": 0.28581341988919357, + "grad_norm": 0.9588287503179966, + "learning_rate": 1.6761127375196776e-05, + "loss": 0.879, + "step": 3192 + }, + { + "epoch": 0.28590296043427166, + "grad_norm": 0.9817413888869693, + "learning_rate": 1.6758990163458195e-05, + "loss": 0.9113, + "step": 3193 + }, + { + "epoch": 0.2859925009793497, + "grad_norm": 0.9699630903173093, + "learning_rate": 1.675685238317539e-05, + "loss": 0.8933, + "step": 3194 + }, + { + "epoch": 0.2860820415244278, + "grad_norm": 0.9185487395604305, + "learning_rate": 1.6754714034528176e-05, + "loss": 0.8585, + "step": 3195 + }, + { + "epoch": 0.2861715820695058, + "grad_norm": 0.9762093779643273, + "learning_rate": 1.6752575117696435e-05, + "loss": 0.8256, + "step": 3196 + }, + { + "epoch": 0.2862611226145839, + "grad_norm": 1.083173533962238, + "learning_rate": 1.6750435632860074e-05, + "loss": 0.8921, + "step": 3197 + }, + { + "epoch": 0.286350663159662, + "grad_norm": 1.0208908262826755, + "learning_rate": 1.674829558019907e-05, + "loss": 0.8992, + "step": 3198 + }, + { + "epoch": 0.28644020370474005, + "grad_norm": 0.8953915176464201, + "learning_rate": 1.6746154959893433e-05, + "loss": 0.8369, + "step": 3199 + }, + { + "epoch": 0.28652974424981814, + "grad_norm": 1.1272926372798986, + "learning_rate": 1.674401377212322e-05, + "loss": 0.8733, + "step": 3200 + }, + { + "epoch": 0.2866192847948962, + "grad_norm": 1.0065015684329834, + "learning_rate": 1.6741872017068547e-05, + "loss": 0.9719, + "step": 3201 + }, + { + "epoch": 0.28670882533997427, + "grad_norm": 1.006968106517315, + "learning_rate": 1.673972969490957e-05, + "loss": 0.8977, + "step": 3202 + }, + { + "epoch": 0.2867983658850523, + "grad_norm": 0.885961933597078, + "learning_rate": 1.6737586805826494e-05, + "loss": 0.8764, + "step": 3203 + }, + { + "epoch": 0.2868879064301304, + "grad_norm": 0.9880874783445704, + "learning_rate": 1.673544334999957e-05, + "loss": 0.9062, + "step": 3204 + }, + { + "epoch": 0.28697744697520844, + "grad_norm": 1.036984376291364, + "learning_rate": 1.6733299327609103e-05, + "loss": 0.8396, + "step": 3205 + }, + { + "epoch": 0.28706698752028653, + "grad_norm": 0.978218171581359, + "learning_rate": 1.6731154738835436e-05, + "loss": 0.8775, + "step": 3206 + }, + { + "epoch": 0.2871565280653646, + "grad_norm": 0.9806278416433408, + "learning_rate": 1.6729009583858974e-05, + "loss": 0.8469, + "step": 3207 + }, + { + "epoch": 0.28724606861044266, + "grad_norm": 0.864084149388989, + "learning_rate": 1.6726863862860147e-05, + "loss": 0.8343, + "step": 3208 + }, + { + "epoch": 0.28733560915552075, + "grad_norm": 1.0425967923450619, + "learning_rate": 1.6724717576019452e-05, + "loss": 0.8363, + "step": 3209 + }, + { + "epoch": 0.2874251497005988, + "grad_norm": 0.9728595411255289, + "learning_rate": 1.672257072351743e-05, + "loss": 0.9134, + "step": 3210 + }, + { + "epoch": 0.2875146902456769, + "grad_norm": 0.9194735682346911, + "learning_rate": 1.6720423305534667e-05, + "loss": 0.8803, + "step": 3211 + }, + { + "epoch": 0.2876042307907549, + "grad_norm": 0.9422105704178322, + "learning_rate": 1.6718275322251795e-05, + "loss": 0.8616, + "step": 3212 + }, + { + "epoch": 0.287693771335833, + "grad_norm": 0.8843388795011171, + "learning_rate": 1.6716126773849492e-05, + "loss": 0.8538, + "step": 3213 + }, + { + "epoch": 0.28778331188091105, + "grad_norm": 1.0091168634732492, + "learning_rate": 1.6713977660508493e-05, + "loss": 0.9557, + "step": 3214 + }, + { + "epoch": 0.28787285242598915, + "grad_norm": 0.9747250743109609, + "learning_rate": 1.6711827982409573e-05, + "loss": 0.9586, + "step": 3215 + }, + { + "epoch": 0.28796239297106724, + "grad_norm": 1.02488948442337, + "learning_rate": 1.6709677739733555e-05, + "loss": 0.9058, + "step": 3216 + }, + { + "epoch": 0.2880519335161453, + "grad_norm": 0.9971299706746245, + "learning_rate": 1.670752693266131e-05, + "loss": 0.7917, + "step": 3217 + }, + { + "epoch": 0.28814147406122337, + "grad_norm": 0.9436902565552915, + "learning_rate": 1.670537556137376e-05, + "loss": 0.9243, + "step": 3218 + }, + { + "epoch": 0.2882310146063014, + "grad_norm": 1.2315407220820207, + "learning_rate": 1.6703223626051866e-05, + "loss": 0.8191, + "step": 3219 + }, + { + "epoch": 0.2883205551513795, + "grad_norm": 0.8295536177777809, + "learning_rate": 1.670107112687664e-05, + "loss": 0.8437, + "step": 3220 + }, + { + "epoch": 0.28841009569645754, + "grad_norm": 0.9707409648873437, + "learning_rate": 1.6698918064029155e-05, + "loss": 0.9168, + "step": 3221 + }, + { + "epoch": 0.28849963624153563, + "grad_norm": 0.9772613410653564, + "learning_rate": 1.669676443769051e-05, + "loss": 0.8333, + "step": 3222 + }, + { + "epoch": 0.28858917678661367, + "grad_norm": 0.959326622044151, + "learning_rate": 1.6694610248041864e-05, + "loss": 0.8894, + "step": 3223 + }, + { + "epoch": 0.28867871733169176, + "grad_norm": 0.9642767461677191, + "learning_rate": 1.6692455495264413e-05, + "loss": 0.9108, + "step": 3224 + }, + { + "epoch": 0.28876825787676985, + "grad_norm": 1.0548427345861626, + "learning_rate": 1.6690300179539423e-05, + "loss": 0.8976, + "step": 3225 + }, + { + "epoch": 0.2888577984218479, + "grad_norm": 0.9521922112892662, + "learning_rate": 1.668814430104818e-05, + "loss": 0.8426, + "step": 3226 + }, + { + "epoch": 0.288947338966926, + "grad_norm": 0.9259928196967661, + "learning_rate": 1.6685987859972033e-05, + "loss": 0.8619, + "step": 3227 + }, + { + "epoch": 0.289036879512004, + "grad_norm": 0.9314846439250073, + "learning_rate": 1.6683830856492377e-05, + "loss": 0.8708, + "step": 3228 + }, + { + "epoch": 0.2891264200570821, + "grad_norm": 1.009583004411416, + "learning_rate": 1.6681673290790645e-05, + "loss": 0.8837, + "step": 3229 + }, + { + "epoch": 0.28921596060216015, + "grad_norm": 0.9304154887110127, + "learning_rate": 1.6679515163048333e-05, + "loss": 0.9089, + "step": 3230 + }, + { + "epoch": 0.28930550114723824, + "grad_norm": 0.9192434388647978, + "learning_rate": 1.6677356473446972e-05, + "loss": 0.852, + "step": 3231 + }, + { + "epoch": 0.2893950416923163, + "grad_norm": 0.9679358179116513, + "learning_rate": 1.6675197222168144e-05, + "loss": 0.8551, + "step": 3232 + }, + { + "epoch": 0.28948458223739437, + "grad_norm": 0.9498729899220998, + "learning_rate": 1.667303740939348e-05, + "loss": 0.8624, + "step": 3233 + }, + { + "epoch": 0.28957412278247247, + "grad_norm": 0.8688824298396755, + "learning_rate": 1.6670877035304652e-05, + "loss": 0.8428, + "step": 3234 + }, + { + "epoch": 0.2896636633275505, + "grad_norm": 1.0242323609621278, + "learning_rate": 1.6668716100083386e-05, + "loss": 0.8795, + "step": 3235 + }, + { + "epoch": 0.2897532038726286, + "grad_norm": 0.9165733908228226, + "learning_rate": 1.6666554603911454e-05, + "loss": 0.8246, + "step": 3236 + }, + { + "epoch": 0.28984274441770663, + "grad_norm": 0.8373146859118741, + "learning_rate": 1.6664392546970673e-05, + "loss": 0.859, + "step": 3237 + }, + { + "epoch": 0.2899322849627847, + "grad_norm": 0.8976506763010602, + "learning_rate": 1.6662229929442904e-05, + "loss": 0.8759, + "step": 3238 + }, + { + "epoch": 0.29002182550786276, + "grad_norm": 1.038814382218406, + "learning_rate": 1.6660066751510067e-05, + "loss": 0.8582, + "step": 3239 + }, + { + "epoch": 0.29011136605294086, + "grad_norm": 1.003097881638538, + "learning_rate": 1.665790301335412e-05, + "loss": 0.8108, + "step": 3240 + }, + { + "epoch": 0.2902009065980189, + "grad_norm": 0.8888945467173105, + "learning_rate": 1.6655738715157067e-05, + "loss": 0.892, + "step": 3241 + }, + { + "epoch": 0.290290447143097, + "grad_norm": 0.8655574541263847, + "learning_rate": 1.6653573857100963e-05, + "loss": 0.8591, + "step": 3242 + }, + { + "epoch": 0.2903799876881751, + "grad_norm": 1.1122810281258813, + "learning_rate": 1.6651408439367906e-05, + "loss": 0.8925, + "step": 3243 + }, + { + "epoch": 0.2904695282332531, + "grad_norm": 0.8375975383815422, + "learning_rate": 1.6649242462140046e-05, + "loss": 0.856, + "step": 3244 + }, + { + "epoch": 0.2905590687783312, + "grad_norm": 0.9343012023661711, + "learning_rate": 1.664707592559958e-05, + "loss": 0.8604, + "step": 3245 + }, + { + "epoch": 0.29064860932340925, + "grad_norm": 0.941289958297517, + "learning_rate": 1.6644908829928746e-05, + "loss": 0.9262, + "step": 3246 + }, + { + "epoch": 0.29073814986848734, + "grad_norm": 0.908991697178001, + "learning_rate": 1.6642741175309834e-05, + "loss": 0.8033, + "step": 3247 + }, + { + "epoch": 0.2908276904135654, + "grad_norm": 0.9890487765557584, + "learning_rate": 1.6640572961925182e-05, + "loss": 0.8674, + "step": 3248 + }, + { + "epoch": 0.29091723095864347, + "grad_norm": 0.8785740981735879, + "learning_rate": 1.6638404189957175e-05, + "loss": 0.8695, + "step": 3249 + }, + { + "epoch": 0.2910067715037215, + "grad_norm": 0.9046915537014031, + "learning_rate": 1.6636234859588237e-05, + "loss": 0.8818, + "step": 3250 + }, + { + "epoch": 0.2910963120487996, + "grad_norm": 0.9598828458643593, + "learning_rate": 1.663406497100085e-05, + "loss": 0.9068, + "step": 3251 + }, + { + "epoch": 0.2911858525938777, + "grad_norm": 1.0138962109622558, + "learning_rate": 1.6631894524377534e-05, + "loss": 0.8625, + "step": 3252 + }, + { + "epoch": 0.29127539313895573, + "grad_norm": 0.8407423168014051, + "learning_rate": 1.6629723519900865e-05, + "loss": 0.8587, + "step": 3253 + }, + { + "epoch": 0.2913649336840338, + "grad_norm": 0.9651146221094635, + "learning_rate": 1.6627551957753458e-05, + "loss": 0.8701, + "step": 3254 + }, + { + "epoch": 0.29145447422911186, + "grad_norm": 1.012547741516527, + "learning_rate": 1.662537983811797e-05, + "loss": 0.871, + "step": 3255 + }, + { + "epoch": 0.29154401477418995, + "grad_norm": 1.1275837011289496, + "learning_rate": 1.662320716117713e-05, + "loss": 0.9275, + "step": 3256 + }, + { + "epoch": 0.291633555319268, + "grad_norm": 0.8533431619885825, + "learning_rate": 1.662103392711368e-05, + "loss": 0.8819, + "step": 3257 + }, + { + "epoch": 0.2917230958643461, + "grad_norm": 0.9037538105831064, + "learning_rate": 1.6618860136110434e-05, + "loss": 0.9018, + "step": 3258 + }, + { + "epoch": 0.2918126364094241, + "grad_norm": 0.9027846157991418, + "learning_rate": 1.6616685788350246e-05, + "loss": 0.9206, + "step": 3259 + }, + { + "epoch": 0.2919021769545022, + "grad_norm": 0.8878364206273809, + "learning_rate": 1.6614510884016004e-05, + "loss": 0.8626, + "step": 3260 + }, + { + "epoch": 0.2919917174995803, + "grad_norm": 0.9398855288484764, + "learning_rate": 1.6612335423290667e-05, + "loss": 0.8473, + "step": 3261 + }, + { + "epoch": 0.29208125804465834, + "grad_norm": 0.8573502823502863, + "learning_rate": 1.661015940635722e-05, + "loss": 0.8502, + "step": 3262 + }, + { + "epoch": 0.29217079858973644, + "grad_norm": 0.9793373723115257, + "learning_rate": 1.6607982833398703e-05, + "loss": 0.8486, + "step": 3263 + }, + { + "epoch": 0.2922603391348145, + "grad_norm": 1.2221691881739998, + "learning_rate": 1.6605805704598208e-05, + "loss": 0.8956, + "step": 3264 + }, + { + "epoch": 0.29234987967989257, + "grad_norm": 0.9541275359348135, + "learning_rate": 1.6603628020138857e-05, + "loss": 0.8687, + "step": 3265 + }, + { + "epoch": 0.2924394202249706, + "grad_norm": 0.9582163398397108, + "learning_rate": 1.660144978020384e-05, + "loss": 0.8129, + "step": 3266 + }, + { + "epoch": 0.2925289607700487, + "grad_norm": 1.4375057766377144, + "learning_rate": 1.659927098497638e-05, + "loss": 0.7965, + "step": 3267 + }, + { + "epoch": 0.29261850131512673, + "grad_norm": 0.91491602344137, + "learning_rate": 1.6597091634639747e-05, + "loss": 0.8639, + "step": 3268 + }, + { + "epoch": 0.2927080418602048, + "grad_norm": 0.8799933963508528, + "learning_rate": 1.6594911729377268e-05, + "loss": 0.851, + "step": 3269 + }, + { + "epoch": 0.2927975824052829, + "grad_norm": 0.998306802187008, + "learning_rate": 1.6592731269372303e-05, + "loss": 0.8611, + "step": 3270 + }, + { + "epoch": 0.29288712295036096, + "grad_norm": 0.972013274754095, + "learning_rate": 1.6590550254808266e-05, + "loss": 0.9234, + "step": 3271 + }, + { + "epoch": 0.29297666349543905, + "grad_norm": 0.8279498780570005, + "learning_rate": 1.658836868586862e-05, + "loss": 0.868, + "step": 3272 + }, + { + "epoch": 0.2930662040405171, + "grad_norm": 0.9122430283181979, + "learning_rate": 1.6586186562736868e-05, + "loss": 0.8357, + "step": 3273 + }, + { + "epoch": 0.2931557445855952, + "grad_norm": 0.9127344921300548, + "learning_rate": 1.6584003885596566e-05, + "loss": 0.859, + "step": 3274 + }, + { + "epoch": 0.2932452851306732, + "grad_norm": 1.0029979275262317, + "learning_rate": 1.6581820654631313e-05, + "loss": 0.8577, + "step": 3275 + }, + { + "epoch": 0.2933348256757513, + "grad_norm": 0.9391636952584056, + "learning_rate": 1.6579636870024757e-05, + "loss": 0.8919, + "step": 3276 + }, + { + "epoch": 0.29342436622082935, + "grad_norm": 0.9154703401389772, + "learning_rate": 1.6577452531960584e-05, + "loss": 0.8863, + "step": 3277 + }, + { + "epoch": 0.29351390676590744, + "grad_norm": 0.9661786340970516, + "learning_rate": 1.6575267640622538e-05, + "loss": 0.873, + "step": 3278 + }, + { + "epoch": 0.29360344731098553, + "grad_norm": 0.9282358930917813, + "learning_rate": 1.657308219619441e-05, + "loss": 0.8583, + "step": 3279 + }, + { + "epoch": 0.29369298785606357, + "grad_norm": 0.9965039641540155, + "learning_rate": 1.657089619886002e-05, + "loss": 0.8366, + "step": 3280 + }, + { + "epoch": 0.29378252840114166, + "grad_norm": 0.9749795638790674, + "learning_rate": 1.656870964880326e-05, + "loss": 0.9008, + "step": 3281 + }, + { + "epoch": 0.2938720689462197, + "grad_norm": 0.9306223595961471, + "learning_rate": 1.656652254620805e-05, + "loss": 0.8546, + "step": 3282 + }, + { + "epoch": 0.2939616094912978, + "grad_norm": 0.8798222759587829, + "learning_rate": 1.6564334891258356e-05, + "loss": 0.8712, + "step": 3283 + }, + { + "epoch": 0.29405115003637583, + "grad_norm": 1.000760310311452, + "learning_rate": 1.6562146684138206e-05, + "loss": 0.8989, + "step": 3284 + }, + { + "epoch": 0.2941406905814539, + "grad_norm": 1.0024506878602193, + "learning_rate": 1.655995792503166e-05, + "loss": 0.865, + "step": 3285 + }, + { + "epoch": 0.29423023112653196, + "grad_norm": 0.9693756465244854, + "learning_rate": 1.6557768614122832e-05, + "loss": 0.8784, + "step": 3286 + }, + { + "epoch": 0.29431977167161005, + "grad_norm": 0.9572361990884715, + "learning_rate": 1.655557875159588e-05, + "loss": 0.9233, + "step": 3287 + }, + { + "epoch": 0.29440931221668815, + "grad_norm": 0.9019902760106082, + "learning_rate": 1.6553388337635e-05, + "loss": 0.8539, + "step": 3288 + }, + { + "epoch": 0.2944988527617662, + "grad_norm": 0.9742717789802614, + "learning_rate": 1.6551197372424456e-05, + "loss": 0.864, + "step": 3289 + }, + { + "epoch": 0.2945883933068443, + "grad_norm": 0.9392096403968139, + "learning_rate": 1.6549005856148534e-05, + "loss": 0.926, + "step": 3290 + }, + { + "epoch": 0.2946779338519223, + "grad_norm": 0.8643058765257536, + "learning_rate": 1.6546813788991578e-05, + "loss": 0.8611, + "step": 3291 + }, + { + "epoch": 0.2947674743970004, + "grad_norm": 1.0038257415528673, + "learning_rate": 1.6544621171137984e-05, + "loss": 0.8302, + "step": 3292 + }, + { + "epoch": 0.29485701494207844, + "grad_norm": 0.9232743051631848, + "learning_rate": 1.6542428002772182e-05, + "loss": 0.8365, + "step": 3293 + }, + { + "epoch": 0.29494655548715654, + "grad_norm": 0.8736492805665838, + "learning_rate": 1.6540234284078656e-05, + "loss": 0.9205, + "step": 3294 + }, + { + "epoch": 0.2950360960322346, + "grad_norm": 0.9583720483706979, + "learning_rate": 1.6538040015241937e-05, + "loss": 0.879, + "step": 3295 + }, + { + "epoch": 0.29512563657731267, + "grad_norm": 0.9899434274970295, + "learning_rate": 1.6535845196446593e-05, + "loss": 0.8447, + "step": 3296 + }, + { + "epoch": 0.29521517712239076, + "grad_norm": 0.9914752856463189, + "learning_rate": 1.6533649827877254e-05, + "loss": 0.8967, + "step": 3297 + }, + { + "epoch": 0.2953047176674688, + "grad_norm": 0.9031522174524893, + "learning_rate": 1.653145390971858e-05, + "loss": 0.883, + "step": 3298 + }, + { + "epoch": 0.2953942582125469, + "grad_norm": 0.9549113483601311, + "learning_rate": 1.652925744215529e-05, + "loss": 0.8947, + "step": 3299 + }, + { + "epoch": 0.2954837987576249, + "grad_norm": 0.9020602435368948, + "learning_rate": 1.652706042537214e-05, + "loss": 0.8113, + "step": 3300 + }, + { + "epoch": 0.295573339302703, + "grad_norm": 1.0360156074190718, + "learning_rate": 1.6524862859553935e-05, + "loss": 0.8604, + "step": 3301 + }, + { + "epoch": 0.29566287984778106, + "grad_norm": 0.9433688564932925, + "learning_rate": 1.652266474488553e-05, + "loss": 0.8813, + "step": 3302 + }, + { + "epoch": 0.29575242039285915, + "grad_norm": 0.9183760370081216, + "learning_rate": 1.6520466081551823e-05, + "loss": 0.8737, + "step": 3303 + }, + { + "epoch": 0.2958419609379372, + "grad_norm": 1.0427240380391123, + "learning_rate": 1.6518266869737755e-05, + "loss": 0.8609, + "step": 3304 + }, + { + "epoch": 0.2959315014830153, + "grad_norm": 0.9075751377735736, + "learning_rate": 1.651606710962832e-05, + "loss": 0.8833, + "step": 3305 + }, + { + "epoch": 0.2960210420280934, + "grad_norm": 0.9964647071277793, + "learning_rate": 1.6513866801408553e-05, + "loss": 0.8316, + "step": 3306 + }, + { + "epoch": 0.2961105825731714, + "grad_norm": 1.0561973256810544, + "learning_rate": 1.651166594526354e-05, + "loss": 0.8161, + "step": 3307 + }, + { + "epoch": 0.2962001231182495, + "grad_norm": 1.0149517433178916, + "learning_rate": 1.6509464541378404e-05, + "loss": 0.8647, + "step": 3308 + }, + { + "epoch": 0.29628966366332754, + "grad_norm": 1.057077634484621, + "learning_rate": 1.6507262589938325e-05, + "loss": 0.8666, + "step": 3309 + }, + { + "epoch": 0.29637920420840563, + "grad_norm": 1.0895180933609274, + "learning_rate": 1.650506009112852e-05, + "loss": 0.8858, + "step": 3310 + }, + { + "epoch": 0.29646874475348367, + "grad_norm": 0.9246340361392058, + "learning_rate": 1.6502857045134262e-05, + "loss": 0.905, + "step": 3311 + }, + { + "epoch": 0.29655828529856176, + "grad_norm": 0.9258748623867799, + "learning_rate": 1.650065345214086e-05, + "loss": 0.8547, + "step": 3312 + }, + { + "epoch": 0.2966478258436398, + "grad_norm": 0.9856245009323533, + "learning_rate": 1.6498449312333674e-05, + "loss": 0.8591, + "step": 3313 + }, + { + "epoch": 0.2967373663887179, + "grad_norm": 0.8589078392289878, + "learning_rate": 1.6496244625898103e-05, + "loss": 0.7809, + "step": 3314 + }, + { + "epoch": 0.296826906933796, + "grad_norm": 0.9852228008078571, + "learning_rate": 1.6494039393019606e-05, + "loss": 0.9095, + "step": 3315 + }, + { + "epoch": 0.296916447478874, + "grad_norm": 1.6707114816872342, + "learning_rate": 1.649183361388368e-05, + "loss": 0.8947, + "step": 3316 + }, + { + "epoch": 0.2970059880239521, + "grad_norm": 0.8606948222912678, + "learning_rate": 1.6489627288675865e-05, + "loss": 0.8595, + "step": 3317 + }, + { + "epoch": 0.29709552856903015, + "grad_norm": 0.980090550966696, + "learning_rate": 1.6487420417581746e-05, + "loss": 0.8723, + "step": 3318 + }, + { + "epoch": 0.29718506911410825, + "grad_norm": 1.0250113715154596, + "learning_rate": 1.6485213000786966e-05, + "loss": 0.8781, + "step": 3319 + }, + { + "epoch": 0.2972746096591863, + "grad_norm": 0.9688053476778848, + "learning_rate": 1.64830050384772e-05, + "loss": 0.8721, + "step": 3320 + }, + { + "epoch": 0.2973641502042644, + "grad_norm": 0.8851681997423748, + "learning_rate": 1.6480796530838176e-05, + "loss": 0.8278, + "step": 3321 + }, + { + "epoch": 0.2974536907493424, + "grad_norm": 0.8742978652683395, + "learning_rate": 1.6478587478055668e-05, + "loss": 0.8834, + "step": 3322 + }, + { + "epoch": 0.2975432312944205, + "grad_norm": 1.080073501563653, + "learning_rate": 1.6476377880315495e-05, + "loss": 0.8272, + "step": 3323 + }, + { + "epoch": 0.2976327718394986, + "grad_norm": 1.0062505383933291, + "learning_rate": 1.6474167737803517e-05, + "loss": 0.8796, + "step": 3324 + }, + { + "epoch": 0.29772231238457664, + "grad_norm": 0.9728013528840082, + "learning_rate": 1.6471957050705645e-05, + "loss": 0.8837, + "step": 3325 + }, + { + "epoch": 0.29781185292965473, + "grad_norm": 0.9867169709172918, + "learning_rate": 1.646974581920784e-05, + "loss": 0.84, + "step": 3326 + }, + { + "epoch": 0.29790139347473277, + "grad_norm": 0.9518110546243204, + "learning_rate": 1.6467534043496095e-05, + "loss": 0.8319, + "step": 3327 + }, + { + "epoch": 0.29799093401981086, + "grad_norm": 1.0781699523117905, + "learning_rate": 1.6465321723756464e-05, + "loss": 0.9126, + "step": 3328 + }, + { + "epoch": 0.2980804745648889, + "grad_norm": 0.991606119281339, + "learning_rate": 1.6463108860175036e-05, + "loss": 0.9109, + "step": 3329 + }, + { + "epoch": 0.298170015109967, + "grad_norm": 0.8877881828552697, + "learning_rate": 1.6460895452937956e-05, + "loss": 0.8551, + "step": 3330 + }, + { + "epoch": 0.298259555655045, + "grad_norm": 0.9819466374320167, + "learning_rate": 1.6458681502231405e-05, + "loss": 0.8223, + "step": 3331 + }, + { + "epoch": 0.2983490962001231, + "grad_norm": 0.9108872159909693, + "learning_rate": 1.645646700824161e-05, + "loss": 0.8406, + "step": 3332 + }, + { + "epoch": 0.2984386367452012, + "grad_norm": 0.8629868230494729, + "learning_rate": 1.645425197115485e-05, + "loss": 0.8455, + "step": 3333 + }, + { + "epoch": 0.29852817729027925, + "grad_norm": 0.9489229233062977, + "learning_rate": 1.645203639115745e-05, + "loss": 0.8282, + "step": 3334 + }, + { + "epoch": 0.29861771783535734, + "grad_norm": 0.9034629564276201, + "learning_rate": 1.644982026843577e-05, + "loss": 0.8844, + "step": 3335 + }, + { + "epoch": 0.2987072583804354, + "grad_norm": 0.965359558375752, + "learning_rate": 1.6447603603176227e-05, + "loss": 0.8714, + "step": 3336 + }, + { + "epoch": 0.2987967989255135, + "grad_norm": 0.9872869519565761, + "learning_rate": 1.6445386395565283e-05, + "loss": 0.8225, + "step": 3337 + }, + { + "epoch": 0.2988863394705915, + "grad_norm": 1.3107464558046085, + "learning_rate": 1.6443168645789436e-05, + "loss": 0.8903, + "step": 3338 + }, + { + "epoch": 0.2989758800156696, + "grad_norm": 1.0235286103970958, + "learning_rate": 1.6440950354035242e-05, + "loss": 0.8603, + "step": 3339 + }, + { + "epoch": 0.29906542056074764, + "grad_norm": 0.9734319568708801, + "learning_rate": 1.6438731520489292e-05, + "loss": 0.862, + "step": 3340 + }, + { + "epoch": 0.29915496110582573, + "grad_norm": 0.8913377143496777, + "learning_rate": 1.6436512145338227e-05, + "loss": 0.8367, + "step": 3341 + }, + { + "epoch": 0.2992445016509038, + "grad_norm": 0.8905430230549951, + "learning_rate": 1.6434292228768736e-05, + "loss": 0.841, + "step": 3342 + }, + { + "epoch": 0.29933404219598186, + "grad_norm": 0.8855827955004383, + "learning_rate": 1.643207177096755e-05, + "loss": 0.8673, + "step": 3343 + }, + { + "epoch": 0.29942358274105996, + "grad_norm": 1.0022150252933022, + "learning_rate": 1.6429850772121448e-05, + "loss": 0.9596, + "step": 3344 + }, + { + "epoch": 0.299513123286138, + "grad_norm": 1.058986381359884, + "learning_rate": 1.6427629232417253e-05, + "loss": 0.9042, + "step": 3345 + }, + { + "epoch": 0.2996026638312161, + "grad_norm": 1.139066325193794, + "learning_rate": 1.642540715204183e-05, + "loss": 0.8694, + "step": 3346 + }, + { + "epoch": 0.2996922043762941, + "grad_norm": 0.9809387249031534, + "learning_rate": 1.6423184531182098e-05, + "loss": 0.897, + "step": 3347 + }, + { + "epoch": 0.2997817449213722, + "grad_norm": 0.883297085362577, + "learning_rate": 1.642096137002501e-05, + "loss": 0.7982, + "step": 3348 + }, + { + "epoch": 0.29987128546645025, + "grad_norm": 0.8974921040768915, + "learning_rate": 1.641873766875758e-05, + "loss": 0.8372, + "step": 3349 + }, + { + "epoch": 0.29996082601152835, + "grad_norm": 0.973746135301797, + "learning_rate": 1.6416513427566853e-05, + "loss": 0.8942, + "step": 3350 + }, + { + "epoch": 0.30005036655660644, + "grad_norm": 0.9111712424072251, + "learning_rate": 1.6414288646639928e-05, + "loss": 0.8156, + "step": 3351 + }, + { + "epoch": 0.3001399071016845, + "grad_norm": 0.9164911353043519, + "learning_rate": 1.641206332616394e-05, + "loss": 0.8362, + "step": 3352 + }, + { + "epoch": 0.30022944764676257, + "grad_norm": 0.9425401626791092, + "learning_rate": 1.6409837466326082e-05, + "loss": 0.904, + "step": 3353 + }, + { + "epoch": 0.3003189881918406, + "grad_norm": 1.0007983932076, + "learning_rate": 1.640761106731359e-05, + "loss": 0.8913, + "step": 3354 + }, + { + "epoch": 0.3004085287369187, + "grad_norm": 1.1366846750040638, + "learning_rate": 1.6405384129313725e-05, + "loss": 0.8506, + "step": 3355 + }, + { + "epoch": 0.30049806928199674, + "grad_norm": 1.1316637554447213, + "learning_rate": 1.640315665251383e-05, + "loss": 0.8984, + "step": 3356 + }, + { + "epoch": 0.30058760982707483, + "grad_norm": 1.0725245615813197, + "learning_rate": 1.6400928637101253e-05, + "loss": 0.8415, + "step": 3357 + }, + { + "epoch": 0.30067715037215287, + "grad_norm": 0.8667239395328905, + "learning_rate": 1.6398700083263426e-05, + "loss": 0.8634, + "step": 3358 + }, + { + "epoch": 0.30076669091723096, + "grad_norm": 1.0562908035709986, + "learning_rate": 1.6396470991187796e-05, + "loss": 0.8688, + "step": 3359 + }, + { + "epoch": 0.30085623146230905, + "grad_norm": 1.0092443613129098, + "learning_rate": 1.6394241361061873e-05, + "loss": 0.8906, + "step": 3360 + }, + { + "epoch": 0.3009457720073871, + "grad_norm": 0.8535208591883673, + "learning_rate": 1.63920111930732e-05, + "loss": 0.8361, + "step": 3361 + }, + { + "epoch": 0.3010353125524652, + "grad_norm": 0.9145565018944185, + "learning_rate": 1.6389780487409377e-05, + "loss": 0.8865, + "step": 3362 + }, + { + "epoch": 0.3011248530975432, + "grad_norm": 0.9404076413003393, + "learning_rate": 1.6387549244258043e-05, + "loss": 0.8708, + "step": 3363 + }, + { + "epoch": 0.3012143936426213, + "grad_norm": 0.9249544702683623, + "learning_rate": 1.638531746380688e-05, + "loss": 0.885, + "step": 3364 + }, + { + "epoch": 0.30130393418769935, + "grad_norm": 1.0181360257300796, + "learning_rate": 1.638308514624362e-05, + "loss": 0.8357, + "step": 3365 + }, + { + "epoch": 0.30139347473277744, + "grad_norm": 0.929546369423035, + "learning_rate": 1.6380852291756036e-05, + "loss": 0.862, + "step": 3366 + }, + { + "epoch": 0.3014830152778555, + "grad_norm": 0.8930116290147487, + "learning_rate": 1.6378618900531957e-05, + "loss": 0.9068, + "step": 3367 + }, + { + "epoch": 0.3015725558229336, + "grad_norm": 0.9382718644988309, + "learning_rate": 1.6376384972759238e-05, + "loss": 0.8326, + "step": 3368 + }, + { + "epoch": 0.30166209636801167, + "grad_norm": 0.9441542819356852, + "learning_rate": 1.637415050862579e-05, + "loss": 0.8738, + "step": 3369 + }, + { + "epoch": 0.3017516369130897, + "grad_norm": 0.9873020019489532, + "learning_rate": 1.637191550831958e-05, + "loss": 0.8451, + "step": 3370 + }, + { + "epoch": 0.3018411774581678, + "grad_norm": 0.9349078225057035, + "learning_rate": 1.63696799720286e-05, + "loss": 0.8554, + "step": 3371 + }, + { + "epoch": 0.30193071800324583, + "grad_norm": 1.136421596115118, + "learning_rate": 1.6367443899940895e-05, + "loss": 0.8879, + "step": 3372 + }, + { + "epoch": 0.3020202585483239, + "grad_norm": 1.034531909315919, + "learning_rate": 1.6365207292244557e-05, + "loss": 0.7959, + "step": 3373 + }, + { + "epoch": 0.30210979909340197, + "grad_norm": 0.9056855865082264, + "learning_rate": 1.6362970149127727e-05, + "loss": 0.8496, + "step": 3374 + }, + { + "epoch": 0.30219933963848006, + "grad_norm": 0.9308162316532969, + "learning_rate": 1.6360732470778583e-05, + "loss": 0.8618, + "step": 3375 + }, + { + "epoch": 0.3022888801835581, + "grad_norm": 0.9412597327105108, + "learning_rate": 1.635849425738535e-05, + "loss": 0.9087, + "step": 3376 + }, + { + "epoch": 0.3023784207286362, + "grad_norm": 1.2975027069142038, + "learning_rate": 1.6356255509136304e-05, + "loss": 0.8298, + "step": 3377 + }, + { + "epoch": 0.3024679612737143, + "grad_norm": 0.9485635632596228, + "learning_rate": 1.6354016226219752e-05, + "loss": 0.8793, + "step": 3378 + }, + { + "epoch": 0.3025575018187923, + "grad_norm": 0.8960492780088233, + "learning_rate": 1.6351776408824066e-05, + "loss": 0.8163, + "step": 3379 + }, + { + "epoch": 0.3026470423638704, + "grad_norm": 0.9179515893934462, + "learning_rate": 1.6349536057137646e-05, + "loss": 0.8741, + "step": 3380 + }, + { + "epoch": 0.30273658290894845, + "grad_norm": 1.0386365296587892, + "learning_rate": 1.6347295171348943e-05, + "loss": 0.8547, + "step": 3381 + }, + { + "epoch": 0.30282612345402654, + "grad_norm": 0.9336272672608067, + "learning_rate": 1.6345053751646455e-05, + "loss": 0.8786, + "step": 3382 + }, + { + "epoch": 0.3029156639991046, + "grad_norm": 0.922362835587453, + "learning_rate": 1.634281179821872e-05, + "loss": 0.8521, + "step": 3383 + }, + { + "epoch": 0.30300520454418267, + "grad_norm": 0.9621682680547788, + "learning_rate": 1.6340569311254328e-05, + "loss": 0.8236, + "step": 3384 + }, + { + "epoch": 0.3030947450892607, + "grad_norm": 0.975488648605726, + "learning_rate": 1.6338326290941906e-05, + "loss": 0.8445, + "step": 3385 + }, + { + "epoch": 0.3031842856343388, + "grad_norm": 1.0176065107094208, + "learning_rate": 1.6336082737470132e-05, + "loss": 0.8391, + "step": 3386 + }, + { + "epoch": 0.3032738261794169, + "grad_norm": 0.9761483915339645, + "learning_rate": 1.6333838651027724e-05, + "loss": 0.9061, + "step": 3387 + }, + { + "epoch": 0.30336336672449493, + "grad_norm": 0.9113043096186673, + "learning_rate": 1.6331594031803453e-05, + "loss": 0.8336, + "step": 3388 + }, + { + "epoch": 0.303452907269573, + "grad_norm": 0.8564439519628021, + "learning_rate": 1.632934887998612e-05, + "loss": 0.8567, + "step": 3389 + }, + { + "epoch": 0.30354244781465106, + "grad_norm": 0.963881667457333, + "learning_rate": 1.6327103195764588e-05, + "loss": 0.9046, + "step": 3390 + }, + { + "epoch": 0.30363198835972915, + "grad_norm": 0.9343078740194618, + "learning_rate": 1.6324856979327754e-05, + "loss": 0.8846, + "step": 3391 + }, + { + "epoch": 0.3037215289048072, + "grad_norm": 1.040381157262312, + "learning_rate": 1.632261023086456e-05, + "loss": 0.8473, + "step": 3392 + }, + { + "epoch": 0.3038110694498853, + "grad_norm": 0.9724309471609979, + "learning_rate": 1.6320362950563995e-05, + "loss": 0.8782, + "step": 3393 + }, + { + "epoch": 0.3039006099949633, + "grad_norm": 0.9539440708460019, + "learning_rate": 1.6318115138615095e-05, + "loss": 0.8309, + "step": 3394 + }, + { + "epoch": 0.3039901505400414, + "grad_norm": 1.0809948350659595, + "learning_rate": 1.6315866795206943e-05, + "loss": 0.9079, + "step": 3395 + }, + { + "epoch": 0.3040796910851195, + "grad_norm": 0.8846212167410237, + "learning_rate": 1.6313617920528653e-05, + "loss": 0.8866, + "step": 3396 + }, + { + "epoch": 0.30416923163019755, + "grad_norm": 1.0262091195902667, + "learning_rate": 1.63113685147694e-05, + "loss": 0.8717, + "step": 3397 + }, + { + "epoch": 0.30425877217527564, + "grad_norm": 0.8675087304735325, + "learning_rate": 1.6309118578118396e-05, + "loss": 0.8354, + "step": 3398 + }, + { + "epoch": 0.3043483127203537, + "grad_norm": 1.0415908936065483, + "learning_rate": 1.6306868110764893e-05, + "loss": 0.8328, + "step": 3399 + }, + { + "epoch": 0.30443785326543177, + "grad_norm": 0.8679334027093386, + "learning_rate": 1.63046171128982e-05, + "loss": 0.8683, + "step": 3400 + }, + { + "epoch": 0.3045273938105098, + "grad_norm": 0.9333733051329592, + "learning_rate": 1.630236558470766e-05, + "loss": 0.8942, + "step": 3401 + }, + { + "epoch": 0.3046169343555879, + "grad_norm": 0.9597638885384935, + "learning_rate": 1.630011352638266e-05, + "loss": 0.9216, + "step": 3402 + }, + { + "epoch": 0.30470647490066594, + "grad_norm": 0.9050292168063366, + "learning_rate": 1.6297860938112644e-05, + "loss": 0.8598, + "step": 3403 + }, + { + "epoch": 0.30479601544574403, + "grad_norm": 1.0005228029060493, + "learning_rate": 1.6295607820087087e-05, + "loss": 0.7883, + "step": 3404 + }, + { + "epoch": 0.3048855559908221, + "grad_norm": 0.9225407879910846, + "learning_rate": 1.629335417249552e-05, + "loss": 0.8566, + "step": 3405 + }, + { + "epoch": 0.30497509653590016, + "grad_norm": 0.9969329685815507, + "learning_rate": 1.6291099995527504e-05, + "loss": 0.8716, + "step": 3406 + }, + { + "epoch": 0.30506463708097825, + "grad_norm": 0.9428467799387135, + "learning_rate": 1.6288845289372657e-05, + "loss": 0.9121, + "step": 3407 + }, + { + "epoch": 0.3051541776260563, + "grad_norm": 0.9100311190918421, + "learning_rate": 1.6286590054220643e-05, + "loss": 0.8463, + "step": 3408 + }, + { + "epoch": 0.3052437181711344, + "grad_norm": 0.9801864910993777, + "learning_rate": 1.6284334290261154e-05, + "loss": 0.8714, + "step": 3409 + }, + { + "epoch": 0.3053332587162124, + "grad_norm": 1.0576716361059155, + "learning_rate": 1.6282077997683945e-05, + "loss": 0.8308, + "step": 3410 + }, + { + "epoch": 0.3054227992612905, + "grad_norm": 1.0337224143873354, + "learning_rate": 1.6279821176678805e-05, + "loss": 0.8074, + "step": 3411 + }, + { + "epoch": 0.30551233980636855, + "grad_norm": 0.9620021039486134, + "learning_rate": 1.6277563827435573e-05, + "loss": 0.8811, + "step": 3412 + }, + { + "epoch": 0.30560188035144664, + "grad_norm": 1.089106944049632, + "learning_rate": 1.627530595014413e-05, + "loss": 0.859, + "step": 3413 + }, + { + "epoch": 0.30569142089652473, + "grad_norm": 1.000249419507427, + "learning_rate": 1.6273047544994402e-05, + "loss": 0.8304, + "step": 3414 + }, + { + "epoch": 0.30578096144160277, + "grad_norm": 0.953848023189794, + "learning_rate": 1.6270788612176353e-05, + "loss": 0.819, + "step": 3415 + }, + { + "epoch": 0.30587050198668086, + "grad_norm": 0.9742188500118159, + "learning_rate": 1.626852915188e-05, + "loss": 0.9366, + "step": 3416 + }, + { + "epoch": 0.3059600425317589, + "grad_norm": 0.9415175831265549, + "learning_rate": 1.6266269164295402e-05, + "loss": 0.8248, + "step": 3417 + }, + { + "epoch": 0.306049583076837, + "grad_norm": 0.9130590932669462, + "learning_rate": 1.626400864961266e-05, + "loss": 0.8412, + "step": 3418 + }, + { + "epoch": 0.30613912362191503, + "grad_norm": 0.8876589175345738, + "learning_rate": 1.6261747608021926e-05, + "loss": 0.8483, + "step": 3419 + }, + { + "epoch": 0.3062286641669931, + "grad_norm": 0.8940818677402772, + "learning_rate": 1.625948603971339e-05, + "loss": 0.8661, + "step": 3420 + }, + { + "epoch": 0.30631820471207116, + "grad_norm": 0.9626924951537016, + "learning_rate": 1.6257223944877284e-05, + "loss": 0.8949, + "step": 3421 + }, + { + "epoch": 0.30640774525714926, + "grad_norm": 1.0070905883991625, + "learning_rate": 1.625496132370389e-05, + "loss": 0.8648, + "step": 3422 + }, + { + "epoch": 0.30649728580222735, + "grad_norm": 0.9962808815191857, + "learning_rate": 1.625269817638353e-05, + "loss": 0.9433, + "step": 3423 + }, + { + "epoch": 0.3065868263473054, + "grad_norm": 0.9259661882997582, + "learning_rate": 1.625043450310658e-05, + "loss": 0.9183, + "step": 3424 + }, + { + "epoch": 0.3066763668923835, + "grad_norm": 1.0635674383092117, + "learning_rate": 1.6248170304063448e-05, + "loss": 0.8534, + "step": 3425 + }, + { + "epoch": 0.3067659074374615, + "grad_norm": 0.9960795819882224, + "learning_rate": 1.6245905579444587e-05, + "loss": 0.8659, + "step": 3426 + }, + { + "epoch": 0.3068554479825396, + "grad_norm": 0.9468635227592602, + "learning_rate": 1.6243640329440503e-05, + "loss": 0.9017, + "step": 3427 + }, + { + "epoch": 0.30694498852761765, + "grad_norm": 1.0935174475228768, + "learning_rate": 1.6241374554241744e-05, + "loss": 0.8267, + "step": 3428 + }, + { + "epoch": 0.30703452907269574, + "grad_norm": 0.9405525033799972, + "learning_rate": 1.6239108254038893e-05, + "loss": 0.8524, + "step": 3429 + }, + { + "epoch": 0.3071240696177738, + "grad_norm": 0.8922950735577043, + "learning_rate": 1.6236841429022587e-05, + "loss": 0.8545, + "step": 3430 + }, + { + "epoch": 0.30721361016285187, + "grad_norm": 1.0052641106292792, + "learning_rate": 1.6234574079383505e-05, + "loss": 0.8491, + "step": 3431 + }, + { + "epoch": 0.30730315070792996, + "grad_norm": 1.0724617478302498, + "learning_rate": 1.6232306205312367e-05, + "loss": 0.8644, + "step": 3432 + }, + { + "epoch": 0.307392691253008, + "grad_norm": 0.8658514109629328, + "learning_rate": 1.6230037806999944e-05, + "loss": 0.8624, + "step": 3433 + }, + { + "epoch": 0.3074822317980861, + "grad_norm": 1.0331838310455363, + "learning_rate": 1.622776888463704e-05, + "loss": 0.8331, + "step": 3434 + }, + { + "epoch": 0.30757177234316413, + "grad_norm": 0.9005507906752604, + "learning_rate": 1.6225499438414512e-05, + "loss": 0.8388, + "step": 3435 + }, + { + "epoch": 0.3076613128882422, + "grad_norm": 0.9694621781869465, + "learning_rate": 1.6223229468523258e-05, + "loss": 0.831, + "step": 3436 + }, + { + "epoch": 0.30775085343332026, + "grad_norm": 1.1658138470007087, + "learning_rate": 1.622095897515422e-05, + "loss": 0.9043, + "step": 3437 + }, + { + "epoch": 0.30784039397839835, + "grad_norm": 0.957523192208975, + "learning_rate": 1.6218687958498386e-05, + "loss": 0.8287, + "step": 3438 + }, + { + "epoch": 0.3079299345234764, + "grad_norm": 1.0504540110286282, + "learning_rate": 1.6216416418746787e-05, + "loss": 0.9206, + "step": 3439 + }, + { + "epoch": 0.3080194750685545, + "grad_norm": 1.0384576635004699, + "learning_rate": 1.6214144356090494e-05, + "loss": 0.8235, + "step": 3440 + }, + { + "epoch": 0.3081090156136326, + "grad_norm": 0.9049288741768955, + "learning_rate": 1.621187177072063e-05, + "loss": 0.8796, + "step": 3441 + }, + { + "epoch": 0.3081985561587106, + "grad_norm": 0.902046055993748, + "learning_rate": 1.6209598662828353e-05, + "loss": 0.9254, + "step": 3442 + }, + { + "epoch": 0.3082880967037887, + "grad_norm": 0.8702330630496671, + "learning_rate": 1.6207325032604875e-05, + "loss": 0.812, + "step": 3443 + }, + { + "epoch": 0.30837763724886674, + "grad_norm": 0.9512577595636892, + "learning_rate": 1.620505088024144e-05, + "loss": 0.8584, + "step": 3444 + }, + { + "epoch": 0.30846717779394484, + "grad_norm": 0.8736108024310634, + "learning_rate": 1.6202776205929347e-05, + "loss": 0.8247, + "step": 3445 + }, + { + "epoch": 0.3085567183390229, + "grad_norm": 0.977546182678823, + "learning_rate": 1.620050100985993e-05, + "loss": 0.8109, + "step": 3446 + }, + { + "epoch": 0.30864625888410097, + "grad_norm": 0.9441407883901345, + "learning_rate": 1.6198225292224576e-05, + "loss": 0.8607, + "step": 3447 + }, + { + "epoch": 0.308735799429179, + "grad_norm": 0.9292094808562754, + "learning_rate": 1.619594905321471e-05, + "loss": 0.858, + "step": 3448 + }, + { + "epoch": 0.3088253399742571, + "grad_norm": 0.907658372940407, + "learning_rate": 1.61936722930218e-05, + "loss": 0.8944, + "step": 3449 + }, + { + "epoch": 0.3089148805193352, + "grad_norm": 0.9452040891228245, + "learning_rate": 1.6191395011837355e-05, + "loss": 0.895, + "step": 3450 + }, + { + "epoch": 0.3090044210644132, + "grad_norm": 1.0367338213477804, + "learning_rate": 1.6189117209852945e-05, + "loss": 0.8935, + "step": 3451 + }, + { + "epoch": 0.3090939616094913, + "grad_norm": 0.9653878917870894, + "learning_rate": 1.6186838887260158e-05, + "loss": 0.9038, + "step": 3452 + }, + { + "epoch": 0.30918350215456936, + "grad_norm": 0.9617260902061584, + "learning_rate": 1.618456004425065e-05, + "loss": 0.9008, + "step": 3453 + }, + { + "epoch": 0.30927304269964745, + "grad_norm": 0.9103736868286196, + "learning_rate": 1.61822806810161e-05, + "loss": 0.8599, + "step": 3454 + }, + { + "epoch": 0.3093625832447255, + "grad_norm": 1.0030654231814287, + "learning_rate": 1.6180000797748248e-05, + "loss": 0.8414, + "step": 3455 + }, + { + "epoch": 0.3094521237898036, + "grad_norm": 0.9091806819292904, + "learning_rate": 1.6177720394638865e-05, + "loss": 0.9077, + "step": 3456 + }, + { + "epoch": 0.3095416643348816, + "grad_norm": 0.876744536570522, + "learning_rate": 1.6175439471879776e-05, + "loss": 0.8758, + "step": 3457 + }, + { + "epoch": 0.3096312048799597, + "grad_norm": 0.9355249348209174, + "learning_rate": 1.6173158029662844e-05, + "loss": 0.8592, + "step": 3458 + }, + { + "epoch": 0.3097207454250378, + "grad_norm": 0.9359629254519449, + "learning_rate": 1.617087606817997e-05, + "loss": 0.8678, + "step": 3459 + }, + { + "epoch": 0.30981028597011584, + "grad_norm": 1.0143250348608364, + "learning_rate": 1.6168593587623114e-05, + "loss": 0.8593, + "step": 3460 + }, + { + "epoch": 0.30989982651519393, + "grad_norm": 1.2644287911915526, + "learning_rate": 1.6166310588184265e-05, + "loss": 0.8444, + "step": 3461 + }, + { + "epoch": 0.30998936706027197, + "grad_norm": 1.0247649502788982, + "learning_rate": 1.6164027070055466e-05, + "loss": 0.858, + "step": 3462 + }, + { + "epoch": 0.31007890760535006, + "grad_norm": 1.0590423639682442, + "learning_rate": 1.6161743033428795e-05, + "loss": 0.8993, + "step": 3463 + }, + { + "epoch": 0.3101684481504281, + "grad_norm": 0.8764865389267936, + "learning_rate": 1.615945847849638e-05, + "loss": 0.8397, + "step": 3464 + }, + { + "epoch": 0.3102579886955062, + "grad_norm": 0.9697408210957381, + "learning_rate": 1.615717340545039e-05, + "loss": 0.8329, + "step": 3465 + }, + { + "epoch": 0.31034752924058423, + "grad_norm": 0.9081920502782245, + "learning_rate": 1.6154887814483038e-05, + "loss": 0.8508, + "step": 3466 + }, + { + "epoch": 0.3104370697856623, + "grad_norm": 0.9263684568346056, + "learning_rate": 1.6152601705786576e-05, + "loss": 0.8821, + "step": 3467 + }, + { + "epoch": 0.3105266103307404, + "grad_norm": 1.0993247898987768, + "learning_rate": 1.6150315079553315e-05, + "loss": 0.8289, + "step": 3468 + }, + { + "epoch": 0.31061615087581845, + "grad_norm": 0.9834980267291011, + "learning_rate": 1.6148027935975587e-05, + "loss": 0.7801, + "step": 3469 + }, + { + "epoch": 0.31070569142089655, + "grad_norm": 0.9460613267159045, + "learning_rate": 1.6145740275245782e-05, + "loss": 0.8762, + "step": 3470 + }, + { + "epoch": 0.3107952319659746, + "grad_norm": 0.9314008052556515, + "learning_rate": 1.6143452097556336e-05, + "loss": 0.8427, + "step": 3471 + }, + { + "epoch": 0.3108847725110527, + "grad_norm": 0.9363928298225046, + "learning_rate": 1.6141163403099716e-05, + "loss": 0.8586, + "step": 3472 + }, + { + "epoch": 0.3109743130561307, + "grad_norm": 0.8842561063925621, + "learning_rate": 1.6138874192068446e-05, + "loss": 0.8451, + "step": 3473 + }, + { + "epoch": 0.3110638536012088, + "grad_norm": 1.1796776311004327, + "learning_rate": 1.6136584464655082e-05, + "loss": 0.8522, + "step": 3474 + }, + { + "epoch": 0.31115339414628684, + "grad_norm": 1.0449545602634394, + "learning_rate": 1.613429422105223e-05, + "loss": 0.8484, + "step": 3475 + }, + { + "epoch": 0.31124293469136494, + "grad_norm": 0.9302964571125277, + "learning_rate": 1.613200346145254e-05, + "loss": 0.8783, + "step": 3476 + }, + { + "epoch": 0.31133247523644303, + "grad_norm": 0.9621306508521787, + "learning_rate": 1.61297121860487e-05, + "loss": 0.8763, + "step": 3477 + }, + { + "epoch": 0.31142201578152107, + "grad_norm": 0.9284883083555696, + "learning_rate": 1.612742039503344e-05, + "loss": 0.867, + "step": 3478 + }, + { + "epoch": 0.31151155632659916, + "grad_norm": 1.001961444604598, + "learning_rate": 1.612512808859955e-05, + "loss": 0.852, + "step": 3479 + }, + { + "epoch": 0.3116010968716772, + "grad_norm": 1.002516734014538, + "learning_rate": 1.6122835266939848e-05, + "loss": 0.8608, + "step": 3480 + }, + { + "epoch": 0.3116906374167553, + "grad_norm": 0.9701202265927532, + "learning_rate": 1.612054193024719e-05, + "loss": 0.8427, + "step": 3481 + }, + { + "epoch": 0.3117801779618333, + "grad_norm": 1.0342947808887826, + "learning_rate": 1.6118248078714493e-05, + "loss": 0.8392, + "step": 3482 + }, + { + "epoch": 0.3118697185069114, + "grad_norm": 1.0150538341799913, + "learning_rate": 1.61159537125347e-05, + "loss": 0.8977, + "step": 3483 + }, + { + "epoch": 0.31195925905198946, + "grad_norm": 0.9298670610892577, + "learning_rate": 1.611365883190082e-05, + "loss": 0.8398, + "step": 3484 + }, + { + "epoch": 0.31204879959706755, + "grad_norm": 0.9169537953841247, + "learning_rate": 1.6111363437005875e-05, + "loss": 0.9463, + "step": 3485 + }, + { + "epoch": 0.31213834014214564, + "grad_norm": 0.9678314459038888, + "learning_rate": 1.6109067528042953e-05, + "loss": 0.8831, + "step": 3486 + }, + { + "epoch": 0.3122278806872237, + "grad_norm": 0.9009375979382416, + "learning_rate": 1.6106771105205182e-05, + "loss": 0.8603, + "step": 3487 + }, + { + "epoch": 0.3123174212323018, + "grad_norm": 1.009435064071259, + "learning_rate": 1.6104474168685724e-05, + "loss": 0.8893, + "step": 3488 + }, + { + "epoch": 0.3124069617773798, + "grad_norm": 0.9157814162932284, + "learning_rate": 1.610217671867779e-05, + "loss": 0.8289, + "step": 3489 + }, + { + "epoch": 0.3124965023224579, + "grad_norm": 0.9531630421755719, + "learning_rate": 1.6099878755374636e-05, + "loss": 0.8788, + "step": 3490 + }, + { + "epoch": 0.31258604286753594, + "grad_norm": 0.960214984482796, + "learning_rate": 1.609758027896956e-05, + "loss": 0.925, + "step": 3491 + }, + { + "epoch": 0.31267558341261403, + "grad_norm": 1.0668041262797365, + "learning_rate": 1.60952812896559e-05, + "loss": 0.8405, + "step": 3492 + }, + { + "epoch": 0.31276512395769207, + "grad_norm": 0.880133357254461, + "learning_rate": 1.609298178762704e-05, + "loss": 0.828, + "step": 3493 + }, + { + "epoch": 0.31285466450277016, + "grad_norm": 0.9723038640326397, + "learning_rate": 1.609068177307641e-05, + "loss": 0.8792, + "step": 3494 + }, + { + "epoch": 0.31294420504784826, + "grad_norm": 0.9588627376170388, + "learning_rate": 1.6088381246197476e-05, + "loss": 0.8085, + "step": 3495 + }, + { + "epoch": 0.3130337455929263, + "grad_norm": 0.8730550143396204, + "learning_rate": 1.608608020718375e-05, + "loss": 0.8531, + "step": 3496 + }, + { + "epoch": 0.3131232861380044, + "grad_norm": 1.0147999348922498, + "learning_rate": 1.608377865622879e-05, + "loss": 0.9172, + "step": 3497 + }, + { + "epoch": 0.3132128266830824, + "grad_norm": 1.0644918752840586, + "learning_rate": 1.6081476593526194e-05, + "loss": 0.8946, + "step": 3498 + }, + { + "epoch": 0.3133023672281605, + "grad_norm": 0.8179810735964052, + "learning_rate": 1.607917401926961e-05, + "loss": 0.8287, + "step": 3499 + }, + { + "epoch": 0.31339190777323855, + "grad_norm": 0.935999923340399, + "learning_rate": 1.607687093365271e-05, + "loss": 0.8918, + "step": 3500 + }, + { + "epoch": 0.31348144831831665, + "grad_norm": 0.9826076664014272, + "learning_rate": 1.6074567336869235e-05, + "loss": 0.8523, + "step": 3501 + }, + { + "epoch": 0.3135709888633947, + "grad_norm": 0.9841186147693697, + "learning_rate": 1.607226322911295e-05, + "loss": 0.8491, + "step": 3502 + }, + { + "epoch": 0.3136605294084728, + "grad_norm": 0.9062230088776329, + "learning_rate": 1.6069958610577668e-05, + "loss": 0.885, + "step": 3503 + }, + { + "epoch": 0.31375006995355087, + "grad_norm": 0.9089910204165106, + "learning_rate": 1.6067653481457254e-05, + "loss": 0.8495, + "step": 3504 + }, + { + "epoch": 0.3138396104986289, + "grad_norm": 0.8961527027498256, + "learning_rate": 1.6065347841945595e-05, + "loss": 0.8356, + "step": 3505 + }, + { + "epoch": 0.313929151043707, + "grad_norm": 0.9041681669124759, + "learning_rate": 1.6063041692236643e-05, + "loss": 0.7983, + "step": 3506 + }, + { + "epoch": 0.31401869158878504, + "grad_norm": 0.9278962804605422, + "learning_rate": 1.606073503252438e-05, + "loss": 0.8643, + "step": 3507 + }, + { + "epoch": 0.31410823213386313, + "grad_norm": 1.0549207191776326, + "learning_rate": 1.6058427863002838e-05, + "loss": 0.8414, + "step": 3508 + }, + { + "epoch": 0.31419777267894117, + "grad_norm": 1.0081789037238174, + "learning_rate": 1.6056120183866087e-05, + "loss": 0.8728, + "step": 3509 + }, + { + "epoch": 0.31428731322401926, + "grad_norm": 0.9098956436641146, + "learning_rate": 1.6053811995308242e-05, + "loss": 0.8707, + "step": 3510 + }, + { + "epoch": 0.3143768537690973, + "grad_norm": 1.0453733347437302, + "learning_rate": 1.6051503297523455e-05, + "loss": 0.8722, + "step": 3511 + }, + { + "epoch": 0.3144663943141754, + "grad_norm": 0.9068577241833307, + "learning_rate": 1.6049194090705935e-05, + "loss": 0.8805, + "step": 3512 + }, + { + "epoch": 0.3145559348592535, + "grad_norm": 0.9982183841071748, + "learning_rate": 1.604688437504992e-05, + "loss": 0.894, + "step": 3513 + }, + { + "epoch": 0.3146454754043315, + "grad_norm": 0.9295402601331746, + "learning_rate": 1.6044574150749697e-05, + "loss": 0.8579, + "step": 3514 + }, + { + "epoch": 0.3147350159494096, + "grad_norm": 0.8974535444863458, + "learning_rate": 1.604226341799959e-05, + "loss": 0.7873, + "step": 3515 + }, + { + "epoch": 0.31482455649448765, + "grad_norm": 0.9748587500694583, + "learning_rate": 1.603995217699398e-05, + "loss": 0.8428, + "step": 3516 + }, + { + "epoch": 0.31491409703956574, + "grad_norm": 0.9484601390168033, + "learning_rate": 1.6037640427927272e-05, + "loss": 0.8933, + "step": 3517 + }, + { + "epoch": 0.3150036375846438, + "grad_norm": 0.9326034565771101, + "learning_rate": 1.6035328170993928e-05, + "loss": 0.8811, + "step": 3518 + }, + { + "epoch": 0.3150931781297219, + "grad_norm": 1.122842311282288, + "learning_rate": 1.6033015406388442e-05, + "loss": 0.9004, + "step": 3519 + }, + { + "epoch": 0.3151827186747999, + "grad_norm": 0.914674073279445, + "learning_rate": 1.603070213430536e-05, + "loss": 0.8891, + "step": 3520 + }, + { + "epoch": 0.315272259219878, + "grad_norm": 1.01870486409183, + "learning_rate": 1.602838835493927e-05, + "loss": 0.8493, + "step": 3521 + }, + { + "epoch": 0.3153617997649561, + "grad_norm": 0.9358650050328511, + "learning_rate": 1.6026074068484794e-05, + "loss": 0.8028, + "step": 3522 + }, + { + "epoch": 0.31545134031003413, + "grad_norm": 0.9768410024986681, + "learning_rate": 1.6023759275136605e-05, + "loss": 0.822, + "step": 3523 + }, + { + "epoch": 0.3155408808551122, + "grad_norm": 0.8508494016505629, + "learning_rate": 1.6021443975089417e-05, + "loss": 0.8848, + "step": 3524 + }, + { + "epoch": 0.31563042140019026, + "grad_norm": 0.9943791218580922, + "learning_rate": 1.601912816853798e-05, + "loss": 0.9129, + "step": 3525 + }, + { + "epoch": 0.31571996194526836, + "grad_norm": 0.8702139822027839, + "learning_rate": 1.60168118556771e-05, + "loss": 0.8538, + "step": 3526 + }, + { + "epoch": 0.3158095024903464, + "grad_norm": 0.9749660282212825, + "learning_rate": 1.6014495036701613e-05, + "loss": 0.8836, + "step": 3527 + }, + { + "epoch": 0.3158990430354245, + "grad_norm": 0.9245308102039224, + "learning_rate": 1.6012177711806403e-05, + "loss": 0.8642, + "step": 3528 + }, + { + "epoch": 0.3159885835805025, + "grad_norm": 1.027412622282684, + "learning_rate": 1.6009859881186395e-05, + "loss": 0.933, + "step": 3529 + }, + { + "epoch": 0.3160781241255806, + "grad_norm": 0.8696898481773648, + "learning_rate": 1.6007541545036558e-05, + "loss": 0.814, + "step": 3530 + }, + { + "epoch": 0.3161676646706587, + "grad_norm": 0.9797723255521389, + "learning_rate": 1.6005222703551902e-05, + "loss": 0.9227, + "step": 3531 + }, + { + "epoch": 0.31625720521573675, + "grad_norm": 0.8750169194670149, + "learning_rate": 1.6002903356927487e-05, + "loss": 0.8595, + "step": 3532 + }, + { + "epoch": 0.31634674576081484, + "grad_norm": 0.9161886209008, + "learning_rate": 1.6000583505358397e-05, + "loss": 0.8625, + "step": 3533 + }, + { + "epoch": 0.3164362863058929, + "grad_norm": 0.9616566569002498, + "learning_rate": 1.5998263149039778e-05, + "loss": 0.92, + "step": 3534 + }, + { + "epoch": 0.31652582685097097, + "grad_norm": 0.935846953925903, + "learning_rate": 1.599594228816681e-05, + "loss": 0.9136, + "step": 3535 + }, + { + "epoch": 0.316615367396049, + "grad_norm": 0.9713035539621584, + "learning_rate": 1.5993620922934716e-05, + "loss": 0.857, + "step": 3536 + }, + { + "epoch": 0.3167049079411271, + "grad_norm": 0.8505154489010355, + "learning_rate": 1.599129905353876e-05, + "loss": 0.8814, + "step": 3537 + }, + { + "epoch": 0.31679444848620514, + "grad_norm": 0.8925383585190358, + "learning_rate": 1.5988976680174257e-05, + "loss": 0.8343, + "step": 3538 + }, + { + "epoch": 0.31688398903128323, + "grad_norm": 0.9489930095399801, + "learning_rate": 1.5986653803036544e-05, + "loss": 0.8838, + "step": 3539 + }, + { + "epoch": 0.3169735295763613, + "grad_norm": 1.020732977407151, + "learning_rate": 1.598433042232103e-05, + "loss": 0.8464, + "step": 3540 + }, + { + "epoch": 0.31706307012143936, + "grad_norm": 0.9124141936440842, + "learning_rate": 1.5982006538223136e-05, + "loss": 0.8875, + "step": 3541 + }, + { + "epoch": 0.31715261066651745, + "grad_norm": 0.9635543852592855, + "learning_rate": 1.5979682150938343e-05, + "loss": 0.8652, + "step": 3542 + }, + { + "epoch": 0.3172421512115955, + "grad_norm": 0.9290033642681926, + "learning_rate": 1.597735726066218e-05, + "loss": 0.7978, + "step": 3543 + }, + { + "epoch": 0.3173316917566736, + "grad_norm": 0.9349539303385449, + "learning_rate": 1.59750318675902e-05, + "loss": 0.8477, + "step": 3544 + }, + { + "epoch": 0.3174212323017516, + "grad_norm": 0.9855831692658552, + "learning_rate": 1.5972705971918012e-05, + "loss": 0.8757, + "step": 3545 + }, + { + "epoch": 0.3175107728468297, + "grad_norm": 0.8786012984894488, + "learning_rate": 1.597037957384126e-05, + "loss": 0.8732, + "step": 3546 + }, + { + "epoch": 0.31760031339190775, + "grad_norm": 0.9698153538446342, + "learning_rate": 1.5968052673555632e-05, + "loss": 0.816, + "step": 3547 + }, + { + "epoch": 0.31768985393698584, + "grad_norm": 0.9173539829192748, + "learning_rate": 1.5965725271256864e-05, + "loss": 0.8858, + "step": 3548 + }, + { + "epoch": 0.31777939448206394, + "grad_norm": 0.97370645288233, + "learning_rate": 1.5963397367140724e-05, + "loss": 0.8764, + "step": 3549 + }, + { + "epoch": 0.317868935027142, + "grad_norm": 0.864031651030753, + "learning_rate": 1.5961068961403033e-05, + "loss": 0.8322, + "step": 3550 + }, + { + "epoch": 0.31795847557222007, + "grad_norm": 0.9107709531188253, + "learning_rate": 1.5958740054239643e-05, + "loss": 0.9138, + "step": 3551 + }, + { + "epoch": 0.3180480161172981, + "grad_norm": 1.1097718267394971, + "learning_rate": 1.595641064584646e-05, + "loss": 0.8755, + "step": 3552 + }, + { + "epoch": 0.3181375566623762, + "grad_norm": 1.0110341934662181, + "learning_rate": 1.5954080736419425e-05, + "loss": 0.8707, + "step": 3553 + }, + { + "epoch": 0.31822709720745423, + "grad_norm": 1.0214249900325971, + "learning_rate": 1.5951750326154517e-05, + "loss": 0.8617, + "step": 3554 + }, + { + "epoch": 0.3183166377525323, + "grad_norm": 0.8283023031458524, + "learning_rate": 1.5949419415247767e-05, + "loss": 0.8465, + "step": 3555 + }, + { + "epoch": 0.31840617829761036, + "grad_norm": 1.0258574500585769, + "learning_rate": 1.594708800389525e-05, + "loss": 0.7986, + "step": 3556 + }, + { + "epoch": 0.31849571884268846, + "grad_norm": 0.8966298464584821, + "learning_rate": 1.5944756092293062e-05, + "loss": 0.8257, + "step": 3557 + }, + { + "epoch": 0.31858525938776655, + "grad_norm": 0.9306855140791443, + "learning_rate": 1.5942423680637368e-05, + "loss": 0.8881, + "step": 3558 + }, + { + "epoch": 0.3186747999328446, + "grad_norm": 1.0708481517779538, + "learning_rate": 1.5940090769124357e-05, + "loss": 0.8391, + "step": 3559 + }, + { + "epoch": 0.3187643404779227, + "grad_norm": 1.2900298195717073, + "learning_rate": 1.5937757357950266e-05, + "loss": 0.9022, + "step": 3560 + }, + { + "epoch": 0.3188538810230007, + "grad_norm": 0.9029206559905374, + "learning_rate": 1.5935423447311377e-05, + "loss": 0.8541, + "step": 3561 + }, + { + "epoch": 0.3189434215680788, + "grad_norm": 0.9774341117370221, + "learning_rate": 1.593308903740401e-05, + "loss": 0.8507, + "step": 3562 + }, + { + "epoch": 0.31903296211315685, + "grad_norm": 1.0067474092359003, + "learning_rate": 1.5930754128424527e-05, + "loss": 0.8563, + "step": 3563 + }, + { + "epoch": 0.31912250265823494, + "grad_norm": 0.9383787999477323, + "learning_rate": 1.5928418720569333e-05, + "loss": 0.8932, + "step": 3564 + }, + { + "epoch": 0.319212043203313, + "grad_norm": 1.03813093061488, + "learning_rate": 1.5926082814034875e-05, + "loss": 0.9109, + "step": 3565 + }, + { + "epoch": 0.31930158374839107, + "grad_norm": 1.1467969563531681, + "learning_rate": 1.5923746409017642e-05, + "loss": 0.846, + "step": 3566 + }, + { + "epoch": 0.31939112429346916, + "grad_norm": 0.9972992927564741, + "learning_rate": 1.5921409505714165e-05, + "loss": 0.7978, + "step": 3567 + }, + { + "epoch": 0.3194806648385472, + "grad_norm": 1.1015570006544695, + "learning_rate": 1.591907210432102e-05, + "loss": 0.8624, + "step": 3568 + }, + { + "epoch": 0.3195702053836253, + "grad_norm": 0.9711106023435543, + "learning_rate": 1.591673420503481e-05, + "loss": 0.8706, + "step": 3569 + }, + { + "epoch": 0.31965974592870333, + "grad_norm": 1.0271826440338592, + "learning_rate": 1.5914395808052207e-05, + "loss": 0.9213, + "step": 3570 + }, + { + "epoch": 0.3197492864737814, + "grad_norm": 1.035025036565157, + "learning_rate": 1.59120569135699e-05, + "loss": 0.9111, + "step": 3571 + }, + { + "epoch": 0.31983882701885946, + "grad_norm": 0.9130146026195757, + "learning_rate": 1.590971752178463e-05, + "loss": 0.8692, + "step": 3572 + }, + { + "epoch": 0.31992836756393755, + "grad_norm": 0.8753357899151957, + "learning_rate": 1.590737763289318e-05, + "loss": 0.8893, + "step": 3573 + }, + { + "epoch": 0.3200179081090156, + "grad_norm": 0.9186210597382566, + "learning_rate": 1.5905037247092374e-05, + "loss": 0.8879, + "step": 3574 + }, + { + "epoch": 0.3201074486540937, + "grad_norm": 0.9216688202659082, + "learning_rate": 1.590269636457908e-05, + "loss": 0.8324, + "step": 3575 + }, + { + "epoch": 0.3201969891991718, + "grad_norm": 1.0384590831013387, + "learning_rate": 1.59003549855502e-05, + "loss": 0.8251, + "step": 3576 + }, + { + "epoch": 0.3202865297442498, + "grad_norm": 0.9179907825399464, + "learning_rate": 1.5898013110202684e-05, + "loss": 0.8322, + "step": 3577 + }, + { + "epoch": 0.3203760702893279, + "grad_norm": 0.9727147976061713, + "learning_rate": 1.589567073873353e-05, + "loss": 0.9224, + "step": 3578 + }, + { + "epoch": 0.32046561083440595, + "grad_norm": 1.0736353696288954, + "learning_rate": 1.589332787133976e-05, + "loss": 0.8207, + "step": 3579 + }, + { + "epoch": 0.32055515137948404, + "grad_norm": 0.9303985515634942, + "learning_rate": 1.589098450821846e-05, + "loss": 0.9148, + "step": 3580 + }, + { + "epoch": 0.3206446919245621, + "grad_norm": 0.8916387034799939, + "learning_rate": 1.588864064956674e-05, + "loss": 0.8275, + "step": 3581 + }, + { + "epoch": 0.32073423246964017, + "grad_norm": 0.9500591067831453, + "learning_rate": 1.5886296295581752e-05, + "loss": 0.8486, + "step": 3582 + }, + { + "epoch": 0.3208237730147182, + "grad_norm": 1.0141093979458402, + "learning_rate": 1.5883951446460707e-05, + "loss": 0.8916, + "step": 3583 + }, + { + "epoch": 0.3209133135597963, + "grad_norm": 0.956192812681069, + "learning_rate": 1.588160610240084e-05, + "loss": 0.8498, + "step": 3584 + }, + { + "epoch": 0.3210028541048744, + "grad_norm": 0.9102389731818618, + "learning_rate": 1.587926026359943e-05, + "loss": 0.8565, + "step": 3585 + }, + { + "epoch": 0.32109239464995243, + "grad_norm": 1.0205222005341894, + "learning_rate": 1.587691393025381e-05, + "loss": 0.8315, + "step": 3586 + }, + { + "epoch": 0.3211819351950305, + "grad_norm": 0.9907235447065051, + "learning_rate": 1.5874567102561336e-05, + "loss": 0.848, + "step": 3587 + }, + { + "epoch": 0.32127147574010856, + "grad_norm": 0.8879169629226085, + "learning_rate": 1.5872219780719428e-05, + "loss": 0.8263, + "step": 3588 + }, + { + "epoch": 0.32136101628518665, + "grad_norm": 0.8801380073048135, + "learning_rate": 1.5869871964925523e-05, + "loss": 0.8449, + "step": 3589 + }, + { + "epoch": 0.3214505568302647, + "grad_norm": 0.9816475732305109, + "learning_rate": 1.5867523655377116e-05, + "loss": 0.8584, + "step": 3590 + }, + { + "epoch": 0.3215400973753428, + "grad_norm": 1.0090436799412859, + "learning_rate": 1.5865174852271742e-05, + "loss": 0.8674, + "step": 3591 + }, + { + "epoch": 0.3216296379204208, + "grad_norm": 1.0368188817338386, + "learning_rate": 1.5862825555806972e-05, + "loss": 0.8615, + "step": 3592 + }, + { + "epoch": 0.3217191784654989, + "grad_norm": 1.0561364274093863, + "learning_rate": 1.586047576618042e-05, + "loss": 0.8596, + "step": 3593 + }, + { + "epoch": 0.321808719010577, + "grad_norm": 0.9232289144563027, + "learning_rate": 1.5858125483589743e-05, + "loss": 0.8779, + "step": 3594 + }, + { + "epoch": 0.32189825955565504, + "grad_norm": 0.8947961456163048, + "learning_rate": 1.5855774708232644e-05, + "loss": 0.8982, + "step": 3595 + }, + { + "epoch": 0.32198780010073313, + "grad_norm": 0.9500325962339439, + "learning_rate": 1.5853423440306858e-05, + "loss": 0.8244, + "step": 3596 + }, + { + "epoch": 0.32207734064581117, + "grad_norm": 0.9470003193027838, + "learning_rate": 1.5851071680010165e-05, + "loss": 0.8721, + "step": 3597 + }, + { + "epoch": 0.32216688119088926, + "grad_norm": 1.1659575903612587, + "learning_rate": 1.584871942754039e-05, + "loss": 0.8513, + "step": 3598 + }, + { + "epoch": 0.3222564217359673, + "grad_norm": 1.0506990655518231, + "learning_rate": 1.5846366683095394e-05, + "loss": 0.873, + "step": 3599 + }, + { + "epoch": 0.3223459622810454, + "grad_norm": 0.8366654532631679, + "learning_rate": 1.5844013446873087e-05, + "loss": 0.8369, + "step": 3600 + }, + { + "epoch": 0.32243550282612343, + "grad_norm": 0.8702368526793697, + "learning_rate": 1.584165971907141e-05, + "loss": 0.8761, + "step": 3601 + }, + { + "epoch": 0.3225250433712015, + "grad_norm": 0.9589636439059769, + "learning_rate": 1.5839305499888355e-05, + "loss": 0.8524, + "step": 3602 + }, + { + "epoch": 0.3226145839162796, + "grad_norm": 0.8808853090698026, + "learning_rate": 1.5836950789521952e-05, + "loss": 0.8669, + "step": 3603 + }, + { + "epoch": 0.32270412446135766, + "grad_norm": 0.9127365606072017, + "learning_rate": 1.583459558817027e-05, + "loss": 0.8412, + "step": 3604 + }, + { + "epoch": 0.32279366500643575, + "grad_norm": 1.0161410372567297, + "learning_rate": 1.5832239896031415e-05, + "loss": 0.8593, + "step": 3605 + }, + { + "epoch": 0.3228832055515138, + "grad_norm": 0.9521009589524897, + "learning_rate": 1.5829883713303547e-05, + "loss": 0.862, + "step": 3606 + }, + { + "epoch": 0.3229727460965919, + "grad_norm": 0.9233511338982374, + "learning_rate": 1.5827527040184864e-05, + "loss": 0.8509, + "step": 3607 + }, + { + "epoch": 0.3230622866416699, + "grad_norm": 0.9223131453171549, + "learning_rate": 1.582516987687359e-05, + "loss": 0.876, + "step": 3608 + }, + { + "epoch": 0.323151827186748, + "grad_norm": 1.0361683951732445, + "learning_rate": 1.5822812223568014e-05, + "loss": 0.8554, + "step": 3609 + }, + { + "epoch": 0.32324136773182605, + "grad_norm": 0.8869414599092794, + "learning_rate": 1.5820454080466446e-05, + "loss": 0.8378, + "step": 3610 + }, + { + "epoch": 0.32333090827690414, + "grad_norm": 0.9589668484237807, + "learning_rate": 1.581809544776725e-05, + "loss": 0.833, + "step": 3611 + }, + { + "epoch": 0.32342044882198223, + "grad_norm": 1.0014261328693184, + "learning_rate": 1.581573632566882e-05, + "loss": 0.8555, + "step": 3612 + }, + { + "epoch": 0.32350998936706027, + "grad_norm": 0.927480464984033, + "learning_rate": 1.5813376714369605e-05, + "loss": 0.8083, + "step": 3613 + }, + { + "epoch": 0.32359952991213836, + "grad_norm": 0.9068144629186506, + "learning_rate": 1.5811016614068084e-05, + "loss": 0.8586, + "step": 3614 + }, + { + "epoch": 0.3236890704572164, + "grad_norm": 0.9305728096425411, + "learning_rate": 1.5808656024962782e-05, + "loss": 0.8883, + "step": 3615 + }, + { + "epoch": 0.3237786110022945, + "grad_norm": 0.8993854827916744, + "learning_rate": 1.5806294947252264e-05, + "loss": 0.8359, + "step": 3616 + }, + { + "epoch": 0.32386815154737253, + "grad_norm": 0.9022886733965982, + "learning_rate": 1.5803933381135136e-05, + "loss": 0.8868, + "step": 3617 + }, + { + "epoch": 0.3239576920924506, + "grad_norm": 0.9662876173454276, + "learning_rate": 1.5801571326810046e-05, + "loss": 0.8468, + "step": 3618 + }, + { + "epoch": 0.32404723263752866, + "grad_norm": 0.8634980823650235, + "learning_rate": 1.5799208784475683e-05, + "loss": 0.8909, + "step": 3619 + }, + { + "epoch": 0.32413677318260675, + "grad_norm": 0.8760839141388197, + "learning_rate": 1.5796845754330772e-05, + "loss": 0.8605, + "step": 3620 + }, + { + "epoch": 0.32422631372768485, + "grad_norm": 0.9690571081398535, + "learning_rate": 1.5794482236574083e-05, + "loss": 0.9117, + "step": 3621 + }, + { + "epoch": 0.3243158542727629, + "grad_norm": 0.8794280041663629, + "learning_rate": 1.5792118231404438e-05, + "loss": 0.8784, + "step": 3622 + }, + { + "epoch": 0.324405394817841, + "grad_norm": 0.9284514992633226, + "learning_rate": 1.578975373902068e-05, + "loss": 0.8812, + "step": 3623 + }, + { + "epoch": 0.324494935362919, + "grad_norm": 1.0304635493841716, + "learning_rate": 1.5787388759621703e-05, + "loss": 0.8704, + "step": 3624 + }, + { + "epoch": 0.3245844759079971, + "grad_norm": 0.9614529455593678, + "learning_rate": 1.5785023293406445e-05, + "loss": 0.8854, + "step": 3625 + }, + { + "epoch": 0.32467401645307514, + "grad_norm": 0.9689922971077647, + "learning_rate": 1.5782657340573875e-05, + "loss": 0.9054, + "step": 3626 + }, + { + "epoch": 0.32476355699815324, + "grad_norm": 0.9543309059230699, + "learning_rate": 1.5780290901323017e-05, + "loss": 0.8522, + "step": 3627 + }, + { + "epoch": 0.3248530975432313, + "grad_norm": 1.3114182392384317, + "learning_rate": 1.5777923975852926e-05, + "loss": 0.8984, + "step": 3628 + }, + { + "epoch": 0.32494263808830937, + "grad_norm": 0.8892923116981535, + "learning_rate": 1.5775556564362696e-05, + "loss": 0.8151, + "step": 3629 + }, + { + "epoch": 0.3250321786333874, + "grad_norm": 0.9914580392729705, + "learning_rate": 1.577318866705147e-05, + "loss": 0.8563, + "step": 3630 + }, + { + "epoch": 0.3251217191784655, + "grad_norm": 0.8528123291944163, + "learning_rate": 1.5770820284118425e-05, + "loss": 0.7794, + "step": 3631 + }, + { + "epoch": 0.3252112597235436, + "grad_norm": 0.8788062646237809, + "learning_rate": 1.5768451415762784e-05, + "loss": 0.827, + "step": 3632 + }, + { + "epoch": 0.3253008002686216, + "grad_norm": 0.9459152611388139, + "learning_rate": 1.5766082062183808e-05, + "loss": 0.8192, + "step": 3633 + }, + { + "epoch": 0.3253903408136997, + "grad_norm": 1.1430681007791503, + "learning_rate": 1.5763712223580796e-05, + "loss": 0.8922, + "step": 3634 + }, + { + "epoch": 0.32547988135877776, + "grad_norm": 1.1687986959245797, + "learning_rate": 1.5761341900153094e-05, + "loss": 0.906, + "step": 3635 + }, + { + "epoch": 0.32556942190385585, + "grad_norm": 0.8768524924153864, + "learning_rate": 1.575897109210009e-05, + "loss": 0.8753, + "step": 3636 + }, + { + "epoch": 0.3256589624489339, + "grad_norm": 0.9597904507300347, + "learning_rate": 1.5756599799621204e-05, + "loss": 0.8822, + "step": 3637 + }, + { + "epoch": 0.325748502994012, + "grad_norm": 0.8746253956284374, + "learning_rate": 1.5754228022915903e-05, + "loss": 0.8364, + "step": 3638 + }, + { + "epoch": 0.32583804353909, + "grad_norm": 0.9219672188959224, + "learning_rate": 1.5751855762183686e-05, + "loss": 0.8416, + "step": 3639 + }, + { + "epoch": 0.3259275840841681, + "grad_norm": 1.0526968315843568, + "learning_rate": 1.5749483017624112e-05, + "loss": 0.8332, + "step": 3640 + }, + { + "epoch": 0.3260171246292462, + "grad_norm": 0.9146187868479909, + "learning_rate": 1.5747109789436762e-05, + "loss": 0.8471, + "step": 3641 + }, + { + "epoch": 0.32610666517432424, + "grad_norm": 0.9427175798447344, + "learning_rate": 1.5744736077821257e-05, + "loss": 0.855, + "step": 3642 + }, + { + "epoch": 0.32619620571940233, + "grad_norm": 0.935223314761867, + "learning_rate": 1.5742361882977282e-05, + "loss": 0.8169, + "step": 3643 + }, + { + "epoch": 0.32628574626448037, + "grad_norm": 0.9900847981136247, + "learning_rate": 1.5739987205104535e-05, + "loss": 0.8949, + "step": 3644 + }, + { + "epoch": 0.32637528680955846, + "grad_norm": 0.9391341896833509, + "learning_rate": 1.573761204440277e-05, + "loss": 0.8229, + "step": 3645 + }, + { + "epoch": 0.3264648273546365, + "grad_norm": 1.1258803425471366, + "learning_rate": 1.5735236401071778e-05, + "loss": 0.8404, + "step": 3646 + }, + { + "epoch": 0.3265543678997146, + "grad_norm": 0.9773098058488157, + "learning_rate": 1.5732860275311387e-05, + "loss": 0.87, + "step": 3647 + }, + { + "epoch": 0.32664390844479263, + "grad_norm": 1.0253147978242285, + "learning_rate": 1.573048366732147e-05, + "loss": 0.8187, + "step": 3648 + }, + { + "epoch": 0.3267334489898707, + "grad_norm": 0.9680557857369011, + "learning_rate": 1.5728106577301945e-05, + "loss": 0.8373, + "step": 3649 + }, + { + "epoch": 0.3268229895349488, + "grad_norm": 0.9595440163983757, + "learning_rate": 1.5725729005452758e-05, + "loss": 0.9162, + "step": 3650 + }, + { + "epoch": 0.32691253008002685, + "grad_norm": 0.9608819872708337, + "learning_rate": 1.5723350951973905e-05, + "loss": 0.8752, + "step": 3651 + }, + { + "epoch": 0.32700207062510495, + "grad_norm": 0.9745222880738017, + "learning_rate": 1.5720972417065424e-05, + "loss": 0.8789, + "step": 3652 + }, + { + "epoch": 0.327091611170183, + "grad_norm": 1.0002507804909697, + "learning_rate": 1.5718593400927385e-05, + "loss": 0.8433, + "step": 3653 + }, + { + "epoch": 0.3271811517152611, + "grad_norm": 0.9360896822621942, + "learning_rate": 1.5716213903759902e-05, + "loss": 0.9099, + "step": 3654 + }, + { + "epoch": 0.3272706922603391, + "grad_norm": 1.0009490756621653, + "learning_rate": 1.5713833925763137e-05, + "loss": 0.8993, + "step": 3655 + }, + { + "epoch": 0.3273602328054172, + "grad_norm": 0.9973717391791578, + "learning_rate": 1.5711453467137276e-05, + "loss": 0.8655, + "step": 3656 + }, + { + "epoch": 0.32744977335049524, + "grad_norm": 0.8976154387949733, + "learning_rate": 1.5709072528082567e-05, + "loss": 0.8458, + "step": 3657 + }, + { + "epoch": 0.32753931389557334, + "grad_norm": 0.9019576717589594, + "learning_rate": 1.5706691108799277e-05, + "loss": 0.8573, + "step": 3658 + }, + { + "epoch": 0.32762885444065143, + "grad_norm": 0.945092574554595, + "learning_rate": 1.570430920948773e-05, + "loss": 0.8825, + "step": 3659 + }, + { + "epoch": 0.32771839498572947, + "grad_norm": 0.9191838558943229, + "learning_rate": 1.570192683034828e-05, + "loss": 0.8675, + "step": 3660 + }, + { + "epoch": 0.32780793553080756, + "grad_norm": 0.8866495700893718, + "learning_rate": 1.5699543971581324e-05, + "loss": 0.889, + "step": 3661 + }, + { + "epoch": 0.3278974760758856, + "grad_norm": 1.0356205395855966, + "learning_rate": 1.5697160633387304e-05, + "loss": 0.8718, + "step": 3662 + }, + { + "epoch": 0.3279870166209637, + "grad_norm": 0.9485569645193066, + "learning_rate": 1.5694776815966698e-05, + "loss": 0.799, + "step": 3663 + }, + { + "epoch": 0.3280765571660417, + "grad_norm": 1.1097511370801718, + "learning_rate": 1.5692392519520022e-05, + "loss": 0.8737, + "step": 3664 + }, + { + "epoch": 0.3281660977111198, + "grad_norm": 1.0609603172803252, + "learning_rate": 1.569000774424784e-05, + "loss": 0.8222, + "step": 3665 + }, + { + "epoch": 0.32825563825619786, + "grad_norm": 1.0242180777562753, + "learning_rate": 1.5687622490350743e-05, + "loss": 0.8781, + "step": 3666 + }, + { + "epoch": 0.32834517880127595, + "grad_norm": 0.9346930443834084, + "learning_rate": 1.5685236758029383e-05, + "loss": 0.8944, + "step": 3667 + }, + { + "epoch": 0.32843471934635404, + "grad_norm": 1.0364674046752969, + "learning_rate": 1.5682850547484433e-05, + "loss": 0.8975, + "step": 3668 + }, + { + "epoch": 0.3285242598914321, + "grad_norm": 0.9236252124603934, + "learning_rate": 1.5680463858916608e-05, + "loss": 0.818, + "step": 3669 + }, + { + "epoch": 0.3286138004365102, + "grad_norm": 1.0180194484332112, + "learning_rate": 1.567807669252668e-05, + "loss": 0.8812, + "step": 3670 + }, + { + "epoch": 0.3287033409815882, + "grad_norm": 0.8536268704647232, + "learning_rate": 1.5675689048515438e-05, + "loss": 0.8739, + "step": 3671 + }, + { + "epoch": 0.3287928815266663, + "grad_norm": 0.9625526289732876, + "learning_rate": 1.5673300927083732e-05, + "loss": 0.8319, + "step": 3672 + }, + { + "epoch": 0.32888242207174434, + "grad_norm": 0.9420534141712468, + "learning_rate": 1.567091232843244e-05, + "loss": 0.8314, + "step": 3673 + }, + { + "epoch": 0.32897196261682243, + "grad_norm": 0.9807560107732121, + "learning_rate": 1.5668523252762482e-05, + "loss": 0.9363, + "step": 3674 + }, + { + "epoch": 0.32906150316190047, + "grad_norm": 0.9417233166381623, + "learning_rate": 1.566613370027482e-05, + "loss": 0.8818, + "step": 3675 + }, + { + "epoch": 0.32915104370697856, + "grad_norm": 0.9456448250219259, + "learning_rate": 1.5663743671170454e-05, + "loss": 0.7935, + "step": 3676 + }, + { + "epoch": 0.32924058425205666, + "grad_norm": 0.9817787621694393, + "learning_rate": 1.566135316565043e-05, + "loss": 0.8664, + "step": 3677 + }, + { + "epoch": 0.3293301247971347, + "grad_norm": 0.9158494247948236, + "learning_rate": 1.5658962183915823e-05, + "loss": 0.8618, + "step": 3678 + }, + { + "epoch": 0.3294196653422128, + "grad_norm": 0.9608444008780501, + "learning_rate": 1.5656570726167763e-05, + "loss": 0.9373, + "step": 3679 + }, + { + "epoch": 0.3295092058872908, + "grad_norm": 0.8816596462490449, + "learning_rate": 1.56541787926074e-05, + "loss": 0.8445, + "step": 3680 + }, + { + "epoch": 0.3295987464323689, + "grad_norm": 0.9505472058799227, + "learning_rate": 1.5651786383435945e-05, + "loss": 0.8939, + "step": 3681 + }, + { + "epoch": 0.32968828697744695, + "grad_norm": 0.9017922955167217, + "learning_rate": 1.5649393498854637e-05, + "loss": 0.8409, + "step": 3682 + }, + { + "epoch": 0.32977782752252505, + "grad_norm": 1.2141596734855504, + "learning_rate": 1.564700013906476e-05, + "loss": 0.8523, + "step": 3683 + }, + { + "epoch": 0.3298673680676031, + "grad_norm": 0.8983192060791162, + "learning_rate": 1.564460630426763e-05, + "loss": 0.801, + "step": 3684 + }, + { + "epoch": 0.3299569086126812, + "grad_norm": 0.958042280532552, + "learning_rate": 1.5642211994664614e-05, + "loss": 0.826, + "step": 3685 + }, + { + "epoch": 0.33004644915775927, + "grad_norm": 0.9046980479715719, + "learning_rate": 1.5639817210457108e-05, + "loss": 0.8361, + "step": 3686 + }, + { + "epoch": 0.3301359897028373, + "grad_norm": 1.1548514754331594, + "learning_rate": 1.563742195184656e-05, + "loss": 0.8516, + "step": 3687 + }, + { + "epoch": 0.3302255302479154, + "grad_norm": 0.9284305644578263, + "learning_rate": 1.5635026219034446e-05, + "loss": 0.8435, + "step": 3688 + }, + { + "epoch": 0.33031507079299344, + "grad_norm": 0.9451406310583375, + "learning_rate": 1.563263001222229e-05, + "loss": 0.8211, + "step": 3689 + }, + { + "epoch": 0.33040461133807153, + "grad_norm": 0.9703726326225346, + "learning_rate": 1.5630233331611656e-05, + "loss": 0.8509, + "step": 3690 + }, + { + "epoch": 0.33049415188314957, + "grad_norm": 0.9066613904628877, + "learning_rate": 1.5627836177404137e-05, + "loss": 0.9098, + "step": 3691 + }, + { + "epoch": 0.33058369242822766, + "grad_norm": 0.9046250797759379, + "learning_rate": 1.5625438549801377e-05, + "loss": 0.8264, + "step": 3692 + }, + { + "epoch": 0.3306732329733057, + "grad_norm": 0.953880747872513, + "learning_rate": 1.5623040449005063e-05, + "loss": 0.8717, + "step": 3693 + }, + { + "epoch": 0.3307627735183838, + "grad_norm": 0.9589971412249996, + "learning_rate": 1.5620641875216908e-05, + "loss": 0.8818, + "step": 3694 + }, + { + "epoch": 0.3308523140634619, + "grad_norm": 0.8695905110945504, + "learning_rate": 1.5618242828638672e-05, + "loss": 0.8275, + "step": 3695 + }, + { + "epoch": 0.3309418546085399, + "grad_norm": 1.0182129307099206, + "learning_rate": 1.5615843309472162e-05, + "loss": 0.8756, + "step": 3696 + }, + { + "epoch": 0.331031395153618, + "grad_norm": 0.9418077565038715, + "learning_rate": 1.5613443317919207e-05, + "loss": 0.8403, + "step": 3697 + }, + { + "epoch": 0.33112093569869605, + "grad_norm": 0.9514319438492587, + "learning_rate": 1.56110428541817e-05, + "loss": 0.8958, + "step": 3698 + }, + { + "epoch": 0.33121047624377414, + "grad_norm": 1.2269311557315061, + "learning_rate": 1.5608641918461545e-05, + "loss": 0.8293, + "step": 3699 + }, + { + "epoch": 0.3313000167888522, + "grad_norm": 1.0245858604786116, + "learning_rate": 1.5606240510960715e-05, + "loss": 0.8063, + "step": 3700 + }, + { + "epoch": 0.3313895573339303, + "grad_norm": 1.1365608616917942, + "learning_rate": 1.56038386318812e-05, + "loss": 0.8037, + "step": 3701 + }, + { + "epoch": 0.3314790978790083, + "grad_norm": 1.0118970539372367, + "learning_rate": 1.560143628142504e-05, + "loss": 0.8572, + "step": 3702 + }, + { + "epoch": 0.3315686384240864, + "grad_norm": 1.0706775076143242, + "learning_rate": 1.5599033459794317e-05, + "loss": 0.85, + "step": 3703 + }, + { + "epoch": 0.3316581789691645, + "grad_norm": 1.080742392291737, + "learning_rate": 1.559663016719114e-05, + "loss": 0.8303, + "step": 3704 + }, + { + "epoch": 0.33174771951424253, + "grad_norm": 0.9085441099897575, + "learning_rate": 1.5594226403817674e-05, + "loss": 0.8134, + "step": 3705 + }, + { + "epoch": 0.3318372600593206, + "grad_norm": 0.9314097035205126, + "learning_rate": 1.5591822169876116e-05, + "loss": 0.854, + "step": 3706 + }, + { + "epoch": 0.33192680060439866, + "grad_norm": 0.8923386938942766, + "learning_rate": 1.558941746556869e-05, + "loss": 0.8318, + "step": 3707 + }, + { + "epoch": 0.33201634114947676, + "grad_norm": 0.9018864916936062, + "learning_rate": 1.5587012291097686e-05, + "loss": 0.8701, + "step": 3708 + }, + { + "epoch": 0.3321058816945548, + "grad_norm": 0.9327631315906499, + "learning_rate": 1.5584606646665416e-05, + "loss": 0.9287, + "step": 3709 + }, + { + "epoch": 0.3321954222396329, + "grad_norm": 1.0559700180665932, + "learning_rate": 1.5582200532474233e-05, + "loss": 0.8343, + "step": 3710 + }, + { + "epoch": 0.3322849627847109, + "grad_norm": 0.9091869066086047, + "learning_rate": 1.557979394872653e-05, + "loss": 0.8434, + "step": 3711 + }, + { + "epoch": 0.332374503329789, + "grad_norm": 0.9686305962665044, + "learning_rate": 1.5577386895624743e-05, + "loss": 0.8193, + "step": 3712 + }, + { + "epoch": 0.3324640438748671, + "grad_norm": 0.9950069532982954, + "learning_rate": 1.557497937337135e-05, + "loss": 0.8779, + "step": 3713 + }, + { + "epoch": 0.33255358441994515, + "grad_norm": 1.0106282485530667, + "learning_rate": 1.5572571382168853e-05, + "loss": 0.9211, + "step": 3714 + }, + { + "epoch": 0.33264312496502324, + "grad_norm": 1.1747121137378411, + "learning_rate": 1.5570162922219815e-05, + "loss": 0.8116, + "step": 3715 + }, + { + "epoch": 0.3327326655101013, + "grad_norm": 0.9011452497357115, + "learning_rate": 1.556775399372682e-05, + "loss": 0.7967, + "step": 3716 + }, + { + "epoch": 0.33282220605517937, + "grad_norm": 0.8806567559699375, + "learning_rate": 1.5565344596892505e-05, + "loss": 0.8503, + "step": 3717 + }, + { + "epoch": 0.3329117466002574, + "grad_norm": 0.8551702542947183, + "learning_rate": 1.556293473191954e-05, + "loss": 0.8816, + "step": 3718 + }, + { + "epoch": 0.3330012871453355, + "grad_norm": 0.82463751371181, + "learning_rate": 1.556052439901063e-05, + "loss": 0.8636, + "step": 3719 + }, + { + "epoch": 0.33309082769041354, + "grad_norm": 1.0238240603108388, + "learning_rate": 1.555811359836853e-05, + "loss": 0.8705, + "step": 3720 + }, + { + "epoch": 0.33318036823549163, + "grad_norm": 0.9269602907071586, + "learning_rate": 1.5555702330196024e-05, + "loss": 0.8832, + "step": 3721 + }, + { + "epoch": 0.3332699087805697, + "grad_norm": 0.9038445810980802, + "learning_rate": 1.5553290594695942e-05, + "loss": 0.8478, + "step": 3722 + }, + { + "epoch": 0.33335944932564776, + "grad_norm": 1.1059008595351187, + "learning_rate": 1.5550878392071155e-05, + "loss": 0.8891, + "step": 3723 + }, + { + "epoch": 0.33344898987072585, + "grad_norm": 0.9516241392686325, + "learning_rate": 1.5548465722524565e-05, + "loss": 0.8403, + "step": 3724 + }, + { + "epoch": 0.3335385304158039, + "grad_norm": 1.0058112975618558, + "learning_rate": 1.5546052586259118e-05, + "loss": 0.8249, + "step": 3725 + }, + { + "epoch": 0.333628070960882, + "grad_norm": 1.1832204229415506, + "learning_rate": 1.5543638983477804e-05, + "loss": 0.8737, + "step": 3726 + }, + { + "epoch": 0.33371761150596, + "grad_norm": 0.8906055364691648, + "learning_rate": 1.554122491438364e-05, + "loss": 0.8185, + "step": 3727 + }, + { + "epoch": 0.3338071520510381, + "grad_norm": 0.9814521584592724, + "learning_rate": 1.5538810379179694e-05, + "loss": 0.8419, + "step": 3728 + }, + { + "epoch": 0.33389669259611615, + "grad_norm": 1.0282048597644162, + "learning_rate": 1.553639537806907e-05, + "loss": 0.8568, + "step": 3729 + }, + { + "epoch": 0.33398623314119424, + "grad_norm": 0.9057934455692483, + "learning_rate": 1.5533979911254907e-05, + "loss": 0.8205, + "step": 3730 + }, + { + "epoch": 0.33407577368627234, + "grad_norm": 1.0727746560167528, + "learning_rate": 1.5531563978940386e-05, + "loss": 0.7874, + "step": 3731 + }, + { + "epoch": 0.3341653142313504, + "grad_norm": 0.9769472122986363, + "learning_rate": 1.552914758132873e-05, + "loss": 0.865, + "step": 3732 + }, + { + "epoch": 0.33425485477642847, + "grad_norm": 0.9522246829164233, + "learning_rate": 1.5526730718623197e-05, + "loss": 0.8955, + "step": 3733 + }, + { + "epoch": 0.3343443953215065, + "grad_norm": 0.9774585857492755, + "learning_rate": 1.5524313391027087e-05, + "loss": 0.8164, + "step": 3734 + }, + { + "epoch": 0.3344339358665846, + "grad_norm": 0.9372843261795946, + "learning_rate": 1.5521895598743735e-05, + "loss": 0.8858, + "step": 3735 + }, + { + "epoch": 0.33452347641166263, + "grad_norm": 1.0109896203935234, + "learning_rate": 1.551947734197652e-05, + "loss": 0.8566, + "step": 3736 + }, + { + "epoch": 0.3346130169567407, + "grad_norm": 1.15493879535932, + "learning_rate": 1.551705862092886e-05, + "loss": 0.848, + "step": 3737 + }, + { + "epoch": 0.33470255750181876, + "grad_norm": 0.9203061676032983, + "learning_rate": 1.5514639435804207e-05, + "loss": 0.8229, + "step": 3738 + }, + { + "epoch": 0.33479209804689686, + "grad_norm": 0.9807189993737404, + "learning_rate": 1.551221978680605e-05, + "loss": 0.9021, + "step": 3739 + }, + { + "epoch": 0.33488163859197495, + "grad_norm": 1.1392174938310522, + "learning_rate": 1.550979967413793e-05, + "loss": 0.8701, + "step": 3740 + }, + { + "epoch": 0.334971179137053, + "grad_norm": 0.8590881594439866, + "learning_rate": 1.550737909800342e-05, + "loss": 0.8687, + "step": 3741 + }, + { + "epoch": 0.3350607196821311, + "grad_norm": 0.9090037832050619, + "learning_rate": 1.5504958058606125e-05, + "loss": 0.87, + "step": 3742 + }, + { + "epoch": 0.3351502602272091, + "grad_norm": 1.0665061137261056, + "learning_rate": 1.5502536556149695e-05, + "loss": 0.7945, + "step": 3743 + }, + { + "epoch": 0.3352398007722872, + "grad_norm": 1.222201922956993, + "learning_rate": 1.5500114590837823e-05, + "loss": 0.9085, + "step": 3744 + }, + { + "epoch": 0.33532934131736525, + "grad_norm": 0.9590013934279815, + "learning_rate": 1.5497692162874235e-05, + "loss": 0.8418, + "step": 3745 + }, + { + "epoch": 0.33541888186244334, + "grad_norm": 0.8867051267190553, + "learning_rate": 1.5495269272462695e-05, + "loss": 0.8045, + "step": 3746 + }, + { + "epoch": 0.3355084224075214, + "grad_norm": 0.9160259233989024, + "learning_rate": 1.5492845919807014e-05, + "loss": 0.8447, + "step": 3747 + }, + { + "epoch": 0.33559796295259947, + "grad_norm": 1.0292276087299104, + "learning_rate": 1.5490422105111032e-05, + "loss": 0.8388, + "step": 3748 + }, + { + "epoch": 0.33568750349767756, + "grad_norm": 1.0766755207053724, + "learning_rate": 1.5487997828578634e-05, + "loss": 0.8838, + "step": 3749 + }, + { + "epoch": 0.3357770440427556, + "grad_norm": 0.930822666624386, + "learning_rate": 1.5485573090413746e-05, + "loss": 0.8756, + "step": 3750 + }, + { + "epoch": 0.3358665845878337, + "grad_norm": 1.013399877217967, + "learning_rate": 1.548314789082032e-05, + "loss": 0.8337, + "step": 3751 + }, + { + "epoch": 0.33595612513291173, + "grad_norm": 1.0630448041184852, + "learning_rate": 1.5480722230002367e-05, + "loss": 0.9031, + "step": 3752 + }, + { + "epoch": 0.3360456656779898, + "grad_norm": 1.050760655326706, + "learning_rate": 1.5478296108163918e-05, + "loss": 0.8863, + "step": 3753 + }, + { + "epoch": 0.33613520622306786, + "grad_norm": 1.0290828846463238, + "learning_rate": 1.547586952550905e-05, + "loss": 0.8972, + "step": 3754 + }, + { + "epoch": 0.33622474676814595, + "grad_norm": 0.8714750795387245, + "learning_rate": 1.5473442482241883e-05, + "loss": 0.8391, + "step": 3755 + }, + { + "epoch": 0.336314287313224, + "grad_norm": 0.9152757476415232, + "learning_rate": 1.5471014978566572e-05, + "loss": 0.7885, + "step": 3756 + }, + { + "epoch": 0.3364038278583021, + "grad_norm": 0.8537405892465879, + "learning_rate": 1.5468587014687308e-05, + "loss": 0.8505, + "step": 3757 + }, + { + "epoch": 0.3364933684033802, + "grad_norm": 0.9662354341030726, + "learning_rate": 1.5466158590808326e-05, + "loss": 0.8411, + "step": 3758 + }, + { + "epoch": 0.3365829089484582, + "grad_norm": 0.9908717423771062, + "learning_rate": 1.5463729707133897e-05, + "loss": 0.8364, + "step": 3759 + }, + { + "epoch": 0.3366724494935363, + "grad_norm": 0.965234107078259, + "learning_rate": 1.5461300363868326e-05, + "loss": 0.8877, + "step": 3760 + }, + { + "epoch": 0.33676199003861434, + "grad_norm": 0.892688975598758, + "learning_rate": 1.5458870561215967e-05, + "loss": 0.8814, + "step": 3761 + }, + { + "epoch": 0.33685153058369244, + "grad_norm": 1.1265633413803315, + "learning_rate": 1.545644029938121e-05, + "loss": 0.8416, + "step": 3762 + }, + { + "epoch": 0.3369410711287705, + "grad_norm": 1.1982058437476673, + "learning_rate": 1.5454009578568466e-05, + "loss": 0.8748, + "step": 3763 + }, + { + "epoch": 0.33703061167384857, + "grad_norm": 0.8623490260410338, + "learning_rate": 1.5451578398982218e-05, + "loss": 0.8051, + "step": 3764 + }, + { + "epoch": 0.3371201522189266, + "grad_norm": 0.9060696774249142, + "learning_rate": 1.5449146760826955e-05, + "loss": 0.8604, + "step": 3765 + }, + { + "epoch": 0.3372096927640047, + "grad_norm": 0.9436553003179557, + "learning_rate": 1.5446714664307226e-05, + "loss": 0.8476, + "step": 3766 + }, + { + "epoch": 0.3372992333090828, + "grad_norm": 0.9636474211173599, + "learning_rate": 1.544428210962761e-05, + "loss": 0.8115, + "step": 3767 + }, + { + "epoch": 0.33738877385416083, + "grad_norm": 0.9141887151876072, + "learning_rate": 1.544184909699272e-05, + "loss": 0.8653, + "step": 3768 + }, + { + "epoch": 0.3374783143992389, + "grad_norm": 0.9422262461309175, + "learning_rate": 1.5439415626607223e-05, + "loss": 0.8415, + "step": 3769 + }, + { + "epoch": 0.33756785494431696, + "grad_norm": 0.9048275364385754, + "learning_rate": 1.5436981698675807e-05, + "loss": 0.8878, + "step": 3770 + }, + { + "epoch": 0.33765739548939505, + "grad_norm": 0.995027655945389, + "learning_rate": 1.5434547313403205e-05, + "loss": 0.8496, + "step": 3771 + }, + { + "epoch": 0.3377469360344731, + "grad_norm": 0.9069485808886016, + "learning_rate": 1.5432112470994195e-05, + "loss": 0.832, + "step": 3772 + }, + { + "epoch": 0.3378364765795512, + "grad_norm": 1.0880520286335649, + "learning_rate": 1.5429677171653584e-05, + "loss": 0.879, + "step": 3773 + }, + { + "epoch": 0.3379260171246292, + "grad_norm": 0.9330914187533275, + "learning_rate": 1.542724141558622e-05, + "loss": 0.8242, + "step": 3774 + }, + { + "epoch": 0.3380155576697073, + "grad_norm": 0.9638798298354745, + "learning_rate": 1.5424805202997e-05, + "loss": 0.8447, + "step": 3775 + }, + { + "epoch": 0.3381050982147854, + "grad_norm": 0.9114027554088435, + "learning_rate": 1.5422368534090844e-05, + "loss": 0.8415, + "step": 3776 + }, + { + "epoch": 0.33819463875986344, + "grad_norm": 1.118946716761861, + "learning_rate": 1.5419931409072715e-05, + "loss": 0.8856, + "step": 3777 + }, + { + "epoch": 0.33828417930494153, + "grad_norm": 0.888712856809204, + "learning_rate": 1.5417493828147616e-05, + "loss": 0.8402, + "step": 3778 + }, + { + "epoch": 0.33837371985001957, + "grad_norm": 0.9558994540633312, + "learning_rate": 1.541505579152059e-05, + "loss": 0.8546, + "step": 3779 + }, + { + "epoch": 0.33846326039509766, + "grad_norm": 0.9184775548791609, + "learning_rate": 1.5412617299396723e-05, + "loss": 0.8746, + "step": 3780 + }, + { + "epoch": 0.3385528009401757, + "grad_norm": 0.8970495025990053, + "learning_rate": 1.5410178351981123e-05, + "loss": 0.8884, + "step": 3781 + }, + { + "epoch": 0.3386423414852538, + "grad_norm": 0.9371371627641085, + "learning_rate": 1.540773894947895e-05, + "loss": 0.8829, + "step": 3782 + }, + { + "epoch": 0.33873188203033183, + "grad_norm": 0.9476143064996031, + "learning_rate": 1.54052990920954e-05, + "loss": 0.86, + "step": 3783 + }, + { + "epoch": 0.3388214225754099, + "grad_norm": 0.9498284392829476, + "learning_rate": 1.54028587800357e-05, + "loss": 0.8682, + "step": 3784 + }, + { + "epoch": 0.338910963120488, + "grad_norm": 0.9498579907834941, + "learning_rate": 1.540041801350513e-05, + "loss": 0.8515, + "step": 3785 + }, + { + "epoch": 0.33900050366556606, + "grad_norm": 0.8708035168199026, + "learning_rate": 1.5397976792708992e-05, + "loss": 0.8754, + "step": 3786 + }, + { + "epoch": 0.33909004421064415, + "grad_norm": 1.0139393955611922, + "learning_rate": 1.539553511785264e-05, + "loss": 0.8798, + "step": 3787 + }, + { + "epoch": 0.3391795847557222, + "grad_norm": 0.9473010375295183, + "learning_rate": 1.539309298914146e-05, + "loss": 0.9326, + "step": 3788 + }, + { + "epoch": 0.3392691253008003, + "grad_norm": 1.0037784770821752, + "learning_rate": 1.5390650406780862e-05, + "loss": 0.8691, + "step": 3789 + }, + { + "epoch": 0.3393586658458783, + "grad_norm": 0.90485127451467, + "learning_rate": 1.5388207370976323e-05, + "loss": 0.8444, + "step": 3790 + }, + { + "epoch": 0.3394482063909564, + "grad_norm": 1.0129675195287833, + "learning_rate": 1.538576388193334e-05, + "loss": 0.8939, + "step": 3791 + }, + { + "epoch": 0.33953774693603445, + "grad_norm": 0.8633996745150577, + "learning_rate": 1.538331993985745e-05, + "loss": 0.8255, + "step": 3792 + }, + { + "epoch": 0.33962728748111254, + "grad_norm": 0.9041308623142068, + "learning_rate": 1.5380875544954227e-05, + "loss": 0.8578, + "step": 3793 + }, + { + "epoch": 0.33971682802619063, + "grad_norm": 0.9554547345468418, + "learning_rate": 1.537843069742929e-05, + "loss": 0.8592, + "step": 3794 + }, + { + "epoch": 0.33980636857126867, + "grad_norm": 0.9999572802320026, + "learning_rate": 1.537598539748829e-05, + "loss": 0.8905, + "step": 3795 + }, + { + "epoch": 0.33989590911634676, + "grad_norm": 1.055529033762274, + "learning_rate": 1.537353964533691e-05, + "loss": 0.8969, + "step": 3796 + }, + { + "epoch": 0.3399854496614248, + "grad_norm": 0.964714699315358, + "learning_rate": 1.53710934411809e-05, + "loss": 0.8462, + "step": 3797 + }, + { + "epoch": 0.3400749902065029, + "grad_norm": 0.8540414406235691, + "learning_rate": 1.5368646785225996e-05, + "loss": 0.8565, + "step": 3798 + }, + { + "epoch": 0.34016453075158093, + "grad_norm": 1.0773546335442135, + "learning_rate": 1.536619967767803e-05, + "loss": 0.8743, + "step": 3799 + }, + { + "epoch": 0.340254071296659, + "grad_norm": 0.9334614161590481, + "learning_rate": 1.536375211874283e-05, + "loss": 0.8322, + "step": 3800 + }, + { + "epoch": 0.34034361184173706, + "grad_norm": 0.9057358499027224, + "learning_rate": 1.5361304108626282e-05, + "loss": 0.8555, + "step": 3801 + }, + { + "epoch": 0.34043315238681515, + "grad_norm": 0.8819048027022858, + "learning_rate": 1.5358855647534306e-05, + "loss": 0.808, + "step": 3802 + }, + { + "epoch": 0.34052269293189324, + "grad_norm": 0.8488072954913346, + "learning_rate": 1.5356406735672852e-05, + "loss": 0.8341, + "step": 3803 + }, + { + "epoch": 0.3406122334769713, + "grad_norm": 0.9898413074898648, + "learning_rate": 1.535395737324792e-05, + "loss": 0.8765, + "step": 3804 + }, + { + "epoch": 0.3407017740220494, + "grad_norm": 1.0330843180762026, + "learning_rate": 1.535150756046554e-05, + "loss": 0.8396, + "step": 3805 + }, + { + "epoch": 0.3407913145671274, + "grad_norm": 0.9476915491993404, + "learning_rate": 1.5349057297531782e-05, + "loss": 0.8583, + "step": 3806 + }, + { + "epoch": 0.3408808551122055, + "grad_norm": 0.9192136044542062, + "learning_rate": 1.5346606584652758e-05, + "loss": 0.8985, + "step": 3807 + }, + { + "epoch": 0.34097039565728354, + "grad_norm": 1.049577571971932, + "learning_rate": 1.5344155422034608e-05, + "loss": 0.8628, + "step": 3808 + }, + { + "epoch": 0.34105993620236164, + "grad_norm": 0.862338895901733, + "learning_rate": 1.5341703809883523e-05, + "loss": 0.8336, + "step": 3809 + }, + { + "epoch": 0.3411494767474397, + "grad_norm": 0.9639019218230677, + "learning_rate": 1.5339251748405715e-05, + "loss": 0.844, + "step": 3810 + }, + { + "epoch": 0.34123901729251777, + "grad_norm": 0.8264070158407661, + "learning_rate": 1.533679923780745e-05, + "loss": 0.8313, + "step": 3811 + }, + { + "epoch": 0.34132855783759586, + "grad_norm": 0.9203581606062318, + "learning_rate": 1.533434627829503e-05, + "loss": 0.7886, + "step": 3812 + }, + { + "epoch": 0.3414180983826739, + "grad_norm": 0.8789911178748009, + "learning_rate": 1.5331892870074777e-05, + "loss": 0.7943, + "step": 3813 + }, + { + "epoch": 0.341507638927752, + "grad_norm": 0.9920213006181874, + "learning_rate": 1.5329439013353074e-05, + "loss": 0.8844, + "step": 3814 + }, + { + "epoch": 0.34159717947283, + "grad_norm": 0.947287664247967, + "learning_rate": 1.532698470833633e-05, + "loss": 0.8461, + "step": 3815 + }, + { + "epoch": 0.3416867200179081, + "grad_norm": 1.0064172516296754, + "learning_rate": 1.532452995523099e-05, + "loss": 0.8721, + "step": 3816 + }, + { + "epoch": 0.34177626056298616, + "grad_norm": 0.9103733284369846, + "learning_rate": 1.532207475424354e-05, + "loss": 0.859, + "step": 3817 + }, + { + "epoch": 0.34186580110806425, + "grad_norm": 0.9855977863965022, + "learning_rate": 1.5319619105580506e-05, + "loss": 0.8248, + "step": 3818 + }, + { + "epoch": 0.3419553416531423, + "grad_norm": 0.9164174798325228, + "learning_rate": 1.5317163009448444e-05, + "loss": 0.847, + "step": 3819 + }, + { + "epoch": 0.3420448821982204, + "grad_norm": 0.8699045960859396, + "learning_rate": 1.531470646605396e-05, + "loss": 0.8671, + "step": 3820 + }, + { + "epoch": 0.34213442274329847, + "grad_norm": 1.2001096650296608, + "learning_rate": 1.531224947560369e-05, + "loss": 0.8681, + "step": 3821 + }, + { + "epoch": 0.3422239632883765, + "grad_norm": 0.9058794180545245, + "learning_rate": 1.5309792038304302e-05, + "loss": 0.8867, + "step": 3822 + }, + { + "epoch": 0.3423135038334546, + "grad_norm": 0.822295197490177, + "learning_rate": 1.530733415436251e-05, + "loss": 0.8305, + "step": 3823 + }, + { + "epoch": 0.34240304437853264, + "grad_norm": 0.9739994656764144, + "learning_rate": 1.5304875823985067e-05, + "loss": 0.8414, + "step": 3824 + }, + { + "epoch": 0.34249258492361073, + "grad_norm": 0.9829670787987514, + "learning_rate": 1.530241704737875e-05, + "loss": 0.8661, + "step": 3825 + }, + { + "epoch": 0.34258212546868877, + "grad_norm": 0.8655978068765721, + "learning_rate": 1.52999578247504e-05, + "loss": 0.8408, + "step": 3826 + }, + { + "epoch": 0.34267166601376686, + "grad_norm": 0.9748409300151503, + "learning_rate": 1.5297498156306864e-05, + "loss": 0.8618, + "step": 3827 + }, + { + "epoch": 0.3427612065588449, + "grad_norm": 0.9191711409415992, + "learning_rate": 1.529503804225504e-05, + "loss": 0.7627, + "step": 3828 + }, + { + "epoch": 0.342850747103923, + "grad_norm": 1.0525824746564418, + "learning_rate": 1.529257748280188e-05, + "loss": 0.8216, + "step": 3829 + }, + { + "epoch": 0.3429402876490011, + "grad_norm": 1.2537178737960688, + "learning_rate": 1.5290116478154346e-05, + "loss": 0.8782, + "step": 3830 + }, + { + "epoch": 0.3430298281940791, + "grad_norm": 0.9549147507849366, + "learning_rate": 1.5287655028519453e-05, + "loss": 0.9269, + "step": 3831 + }, + { + "epoch": 0.3431193687391572, + "grad_norm": 0.9596048063390664, + "learning_rate": 1.528519313410425e-05, + "loss": 0.891, + "step": 3832 + }, + { + "epoch": 0.34320890928423525, + "grad_norm": 1.2417933070577973, + "learning_rate": 1.5282730795115822e-05, + "loss": 0.9077, + "step": 3833 + }, + { + "epoch": 0.34329844982931335, + "grad_norm": 1.0097239403296414, + "learning_rate": 1.5280268011761296e-05, + "loss": 0.9237, + "step": 3834 + }, + { + "epoch": 0.3433879903743914, + "grad_norm": 0.9730894959132692, + "learning_rate": 1.527780478424783e-05, + "loss": 0.8688, + "step": 3835 + }, + { + "epoch": 0.3434775309194695, + "grad_norm": 0.926194904513807, + "learning_rate": 1.5275341112782625e-05, + "loss": 0.8317, + "step": 3836 + }, + { + "epoch": 0.3435670714645475, + "grad_norm": 0.9703703941546321, + "learning_rate": 1.5272876997572916e-05, + "loss": 0.8615, + "step": 3837 + }, + { + "epoch": 0.3436566120096256, + "grad_norm": 0.8971043374811823, + "learning_rate": 1.527041243882598e-05, + "loss": 0.8181, + "step": 3838 + }, + { + "epoch": 0.3437461525547037, + "grad_norm": 0.8574412943492389, + "learning_rate": 1.526794743674912e-05, + "loss": 0.8449, + "step": 3839 + }, + { + "epoch": 0.34383569309978174, + "grad_norm": 0.9519693342302483, + "learning_rate": 1.526548199154969e-05, + "loss": 0.8546, + "step": 3840 + }, + { + "epoch": 0.34392523364485983, + "grad_norm": 1.0447711226794831, + "learning_rate": 1.5263016103435072e-05, + "loss": 0.8735, + "step": 3841 + }, + { + "epoch": 0.34401477418993787, + "grad_norm": 0.9045378033159213, + "learning_rate": 1.526054977261269e-05, + "loss": 0.8123, + "step": 3842 + }, + { + "epoch": 0.34410431473501596, + "grad_norm": 0.8618110882958003, + "learning_rate": 1.5258082999290004e-05, + "loss": 0.889, + "step": 3843 + }, + { + "epoch": 0.344193855280094, + "grad_norm": 0.8853325841756551, + "learning_rate": 1.5255615783674513e-05, + "loss": 0.8732, + "step": 3844 + }, + { + "epoch": 0.3442833958251721, + "grad_norm": 0.9281580088014069, + "learning_rate": 1.5253148125973746e-05, + "loss": 0.872, + "step": 3845 + }, + { + "epoch": 0.3443729363702501, + "grad_norm": 0.9732980784194987, + "learning_rate": 1.525068002639528e-05, + "loss": 0.8501, + "step": 3846 + }, + { + "epoch": 0.3444624769153282, + "grad_norm": 0.9339493691422398, + "learning_rate": 1.524821148514672e-05, + "loss": 0.8417, + "step": 3847 + }, + { + "epoch": 0.3445520174604063, + "grad_norm": 1.02786635635532, + "learning_rate": 1.5245742502435713e-05, + "loss": 0.8594, + "step": 3848 + }, + { + "epoch": 0.34464155800548435, + "grad_norm": 1.0865579406765522, + "learning_rate": 1.5243273078469938e-05, + "loss": 0.9129, + "step": 3849 + }, + { + "epoch": 0.34473109855056244, + "grad_norm": 0.9527993610785306, + "learning_rate": 1.524080321345712e-05, + "loss": 0.9007, + "step": 3850 + }, + { + "epoch": 0.3448206390956405, + "grad_norm": 0.8772472196066003, + "learning_rate": 1.5238332907605014e-05, + "loss": 0.8038, + "step": 3851 + }, + { + "epoch": 0.3449101796407186, + "grad_norm": 0.9477423440766604, + "learning_rate": 1.5235862161121412e-05, + "loss": 0.864, + "step": 3852 + }, + { + "epoch": 0.3449997201857966, + "grad_norm": 0.8618935685308358, + "learning_rate": 1.5233390974214146e-05, + "loss": 0.7888, + "step": 3853 + }, + { + "epoch": 0.3450892607308747, + "grad_norm": 0.93746703898179, + "learning_rate": 1.5230919347091092e-05, + "loss": 0.8315, + "step": 3854 + }, + { + "epoch": 0.34517880127595274, + "grad_norm": 0.9461773417400678, + "learning_rate": 1.522844727996014e-05, + "loss": 0.8752, + "step": 3855 + }, + { + "epoch": 0.34526834182103083, + "grad_norm": 0.916368679058873, + "learning_rate": 1.5225974773029246e-05, + "loss": 0.7965, + "step": 3856 + }, + { + "epoch": 0.3453578823661089, + "grad_norm": 1.001557934153696, + "learning_rate": 1.5223501826506386e-05, + "loss": 0.7992, + "step": 3857 + }, + { + "epoch": 0.34544742291118696, + "grad_norm": 0.9410352148934408, + "learning_rate": 1.522102844059957e-05, + "loss": 0.8657, + "step": 3858 + }, + { + "epoch": 0.34553696345626506, + "grad_norm": 1.117751099714368, + "learning_rate": 1.5218554615516857e-05, + "loss": 0.8805, + "step": 3859 + }, + { + "epoch": 0.3456265040013431, + "grad_norm": 1.0477389525397895, + "learning_rate": 1.5216080351466333e-05, + "loss": 0.8797, + "step": 3860 + }, + { + "epoch": 0.3457160445464212, + "grad_norm": 0.9500500564910868, + "learning_rate": 1.5213605648656132e-05, + "loss": 0.8338, + "step": 3861 + }, + { + "epoch": 0.3458055850914992, + "grad_norm": 0.9656886624057628, + "learning_rate": 1.521113050729441e-05, + "loss": 0.8448, + "step": 3862 + }, + { + "epoch": 0.3458951256365773, + "grad_norm": 1.2063491629719156, + "learning_rate": 1.5208654927589372e-05, + "loss": 0.8676, + "step": 3863 + }, + { + "epoch": 0.34598466618165535, + "grad_norm": 0.9604753016354344, + "learning_rate": 1.5206178909749256e-05, + "loss": 0.8235, + "step": 3864 + }, + { + "epoch": 0.34607420672673345, + "grad_norm": 0.9838223077573088, + "learning_rate": 1.5203702453982335e-05, + "loss": 0.8455, + "step": 3865 + }, + { + "epoch": 0.34616374727181154, + "grad_norm": 1.0384524178269148, + "learning_rate": 1.520122556049692e-05, + "loss": 0.9041, + "step": 3866 + }, + { + "epoch": 0.3462532878168896, + "grad_norm": 1.0865067671525488, + "learning_rate": 1.5198748229501358e-05, + "loss": 0.8422, + "step": 3867 + }, + { + "epoch": 0.34634282836196767, + "grad_norm": 0.9441735043841237, + "learning_rate": 1.5196270461204041e-05, + "loss": 0.8328, + "step": 3868 + }, + { + "epoch": 0.3464323689070457, + "grad_norm": 0.9610505945450045, + "learning_rate": 1.5193792255813384e-05, + "loss": 0.7907, + "step": 3869 + }, + { + "epoch": 0.3465219094521238, + "grad_norm": 0.9565827905743597, + "learning_rate": 1.5191313613537846e-05, + "loss": 0.8491, + "step": 3870 + }, + { + "epoch": 0.34661144999720184, + "grad_norm": 0.9168807353150401, + "learning_rate": 1.5188834534585926e-05, + "loss": 0.9017, + "step": 3871 + }, + { + "epoch": 0.34670099054227993, + "grad_norm": 1.1993016137904005, + "learning_rate": 1.5186355019166153e-05, + "loss": 0.8842, + "step": 3872 + }, + { + "epoch": 0.34679053108735797, + "grad_norm": 0.9912875115147707, + "learning_rate": 1.5183875067487095e-05, + "loss": 0.8817, + "step": 3873 + }, + { + "epoch": 0.34688007163243606, + "grad_norm": 0.898752358158883, + "learning_rate": 1.5181394679757363e-05, + "loss": 0.8598, + "step": 3874 + }, + { + "epoch": 0.34696961217751415, + "grad_norm": 0.8794468945455675, + "learning_rate": 1.517891385618559e-05, + "loss": 0.8283, + "step": 3875 + }, + { + "epoch": 0.3470591527225922, + "grad_norm": 0.8635876594728162, + "learning_rate": 1.5176432596980465e-05, + "loss": 0.885, + "step": 3876 + }, + { + "epoch": 0.3471486932676703, + "grad_norm": 0.9503130061250759, + "learning_rate": 1.5173950902350694e-05, + "loss": 0.806, + "step": 3877 + }, + { + "epoch": 0.3472382338127483, + "grad_norm": 0.9726805220063456, + "learning_rate": 1.5171468772505038e-05, + "loss": 0.9332, + "step": 3878 + }, + { + "epoch": 0.3473277743578264, + "grad_norm": 0.9567696880020461, + "learning_rate": 1.5168986207652277e-05, + "loss": 0.874, + "step": 3879 + }, + { + "epoch": 0.34741731490290445, + "grad_norm": 1.2150698791731538, + "learning_rate": 1.516650320800124e-05, + "loss": 0.8729, + "step": 3880 + }, + { + "epoch": 0.34750685544798254, + "grad_norm": 0.9839961594413172, + "learning_rate": 1.5164019773760794e-05, + "loss": 0.8327, + "step": 3881 + }, + { + "epoch": 0.3475963959930606, + "grad_norm": 0.9308726600539514, + "learning_rate": 1.5161535905139829e-05, + "loss": 0.8733, + "step": 3882 + }, + { + "epoch": 0.3476859365381387, + "grad_norm": 0.9164058038747945, + "learning_rate": 1.5159051602347283e-05, + "loss": 0.8855, + "step": 3883 + }, + { + "epoch": 0.34777547708321677, + "grad_norm": 0.9472958820406885, + "learning_rate": 1.515656686559213e-05, + "loss": 0.8925, + "step": 3884 + }, + { + "epoch": 0.3478650176282948, + "grad_norm": 1.0523456510468796, + "learning_rate": 1.5154081695083376e-05, + "loss": 0.8157, + "step": 3885 + }, + { + "epoch": 0.3479545581733729, + "grad_norm": 0.8936604672590607, + "learning_rate": 1.5151596091030063e-05, + "loss": 0.8231, + "step": 3886 + }, + { + "epoch": 0.34804409871845093, + "grad_norm": 0.8679223467581099, + "learning_rate": 1.5149110053641278e-05, + "loss": 0.8986, + "step": 3887 + }, + { + "epoch": 0.348133639263529, + "grad_norm": 0.909766781543616, + "learning_rate": 1.5146623583126134e-05, + "loss": 0.8742, + "step": 3888 + }, + { + "epoch": 0.34822317980860706, + "grad_norm": 0.9073702293037776, + "learning_rate": 1.5144136679693784e-05, + "loss": 0.8727, + "step": 3889 + }, + { + "epoch": 0.34831272035368516, + "grad_norm": 0.9613482522838903, + "learning_rate": 1.5141649343553419e-05, + "loss": 0.866, + "step": 3890 + }, + { + "epoch": 0.3484022608987632, + "grad_norm": 1.0186264856750307, + "learning_rate": 1.5139161574914267e-05, + "loss": 0.843, + "step": 3891 + }, + { + "epoch": 0.3484918014438413, + "grad_norm": 1.2572013534105926, + "learning_rate": 1.5136673373985593e-05, + "loss": 0.8322, + "step": 3892 + }, + { + "epoch": 0.3485813419889194, + "grad_norm": 1.0558487531450107, + "learning_rate": 1.513418474097669e-05, + "loss": 0.9316, + "step": 3893 + }, + { + "epoch": 0.3486708825339974, + "grad_norm": 0.8280851841782433, + "learning_rate": 1.51316956760969e-05, + "loss": 0.8877, + "step": 3894 + }, + { + "epoch": 0.3487604230790755, + "grad_norm": 0.8910115021814877, + "learning_rate": 1.5129206179555591e-05, + "loss": 0.8599, + "step": 3895 + }, + { + "epoch": 0.34884996362415355, + "grad_norm": 0.9698876265160217, + "learning_rate": 1.5126716251562173e-05, + "loss": 0.8422, + "step": 3896 + }, + { + "epoch": 0.34893950416923164, + "grad_norm": 0.9484585757566176, + "learning_rate": 1.512422589232609e-05, + "loss": 0.8488, + "step": 3897 + }, + { + "epoch": 0.3490290447143097, + "grad_norm": 0.9626678539537833, + "learning_rate": 1.5121735102056825e-05, + "loss": 0.8354, + "step": 3898 + }, + { + "epoch": 0.34911858525938777, + "grad_norm": 0.9896372535790691, + "learning_rate": 1.511924388096389e-05, + "loss": 0.8741, + "step": 3899 + }, + { + "epoch": 0.3492081258044658, + "grad_norm": 0.997184360705059, + "learning_rate": 1.5116752229256844e-05, + "loss": 0.8694, + "step": 3900 + }, + { + "epoch": 0.3492976663495439, + "grad_norm": 0.9399181414900208, + "learning_rate": 1.5114260147145274e-05, + "loss": 0.871, + "step": 3901 + }, + { + "epoch": 0.349387206894622, + "grad_norm": 0.9596841835715545, + "learning_rate": 1.5111767634838805e-05, + "loss": 0.8888, + "step": 3902 + }, + { + "epoch": 0.34947674743970003, + "grad_norm": 1.0089352578317965, + "learning_rate": 1.5109274692547104e-05, + "loss": 0.8701, + "step": 3903 + }, + { + "epoch": 0.3495662879847781, + "grad_norm": 1.0440021871417409, + "learning_rate": 1.5106781320479864e-05, + "loss": 0.8935, + "step": 3904 + }, + { + "epoch": 0.34965582852985616, + "grad_norm": 0.8934495846600866, + "learning_rate": 1.5104287518846818e-05, + "loss": 0.8965, + "step": 3905 + }, + { + "epoch": 0.34974536907493425, + "grad_norm": 0.8895411672924293, + "learning_rate": 1.5101793287857743e-05, + "loss": 0.8145, + "step": 3906 + }, + { + "epoch": 0.3498349096200123, + "grad_norm": 0.9595862698373742, + "learning_rate": 1.509929862772244e-05, + "loss": 0.8477, + "step": 3907 + }, + { + "epoch": 0.3499244501650904, + "grad_norm": 0.9554606480378743, + "learning_rate": 1.5096803538650754e-05, + "loss": 0.8532, + "step": 3908 + }, + { + "epoch": 0.3500139907101684, + "grad_norm": 0.8762636141502056, + "learning_rate": 1.5094308020852564e-05, + "loss": 0.8377, + "step": 3909 + }, + { + "epoch": 0.3501035312552465, + "grad_norm": 0.8531600565090199, + "learning_rate": 1.509181207453778e-05, + "loss": 0.8648, + "step": 3910 + }, + { + "epoch": 0.3501930718003246, + "grad_norm": 0.8715589321284145, + "learning_rate": 1.5089315699916364e-05, + "loss": 0.8494, + "step": 3911 + }, + { + "epoch": 0.35028261234540264, + "grad_norm": 0.9391168854697806, + "learning_rate": 1.5086818897198292e-05, + "loss": 0.865, + "step": 3912 + }, + { + "epoch": 0.35037215289048074, + "grad_norm": 1.0732189912939272, + "learning_rate": 1.5084321666593589e-05, + "loss": 0.8606, + "step": 3913 + }, + { + "epoch": 0.3504616934355588, + "grad_norm": 1.2491541359483513, + "learning_rate": 1.508182400831232e-05, + "loss": 0.849, + "step": 3914 + }, + { + "epoch": 0.35055123398063687, + "grad_norm": 0.9413897656289163, + "learning_rate": 1.5079325922564574e-05, + "loss": 0.8821, + "step": 3915 + }, + { + "epoch": 0.3506407745257149, + "grad_norm": 0.9399070851264855, + "learning_rate": 1.5076827409560481e-05, + "loss": 0.8648, + "step": 3916 + }, + { + "epoch": 0.350730315070793, + "grad_norm": 0.955577486784344, + "learning_rate": 1.5074328469510212e-05, + "loss": 0.782, + "step": 3917 + }, + { + "epoch": 0.35081985561587103, + "grad_norm": 0.9483996096090402, + "learning_rate": 1.5071829102623969e-05, + "loss": 0.8988, + "step": 3918 + }, + { + "epoch": 0.3509093961609491, + "grad_norm": 1.0435256049509705, + "learning_rate": 1.5069329309111988e-05, + "loss": 0.9141, + "step": 3919 + }, + { + "epoch": 0.3509989367060272, + "grad_norm": 0.9369752645346466, + "learning_rate": 1.5066829089184545e-05, + "loss": 0.8251, + "step": 3920 + }, + { + "epoch": 0.35108847725110526, + "grad_norm": 0.8928919093481668, + "learning_rate": 1.506432844305195e-05, + "loss": 0.8765, + "step": 3921 + }, + { + "epoch": 0.35117801779618335, + "grad_norm": 0.9916226807939872, + "learning_rate": 1.5061827370924551e-05, + "loss": 0.9395, + "step": 3922 + }, + { + "epoch": 0.3512675583412614, + "grad_norm": 0.9814741589499576, + "learning_rate": 1.5059325873012727e-05, + "loss": 0.8443, + "step": 3923 + }, + { + "epoch": 0.3513570988863395, + "grad_norm": 0.9138014496094762, + "learning_rate": 1.50568239495269e-05, + "loss": 0.8734, + "step": 3924 + }, + { + "epoch": 0.3514466394314175, + "grad_norm": 0.9705963395916672, + "learning_rate": 1.505432160067752e-05, + "loss": 0.8611, + "step": 3925 + }, + { + "epoch": 0.3515361799764956, + "grad_norm": 1.1895696939115223, + "learning_rate": 1.5051818826675076e-05, + "loss": 0.8517, + "step": 3926 + }, + { + "epoch": 0.35162572052157365, + "grad_norm": 1.1797515896118147, + "learning_rate": 1.5049315627730093e-05, + "loss": 0.8414, + "step": 3927 + }, + { + "epoch": 0.35171526106665174, + "grad_norm": 0.9503095175887297, + "learning_rate": 1.5046812004053135e-05, + "loss": 0.8036, + "step": 3928 + }, + { + "epoch": 0.35180480161172983, + "grad_norm": 0.9701961351933339, + "learning_rate": 1.50443079558548e-05, + "loss": 0.8828, + "step": 3929 + }, + { + "epoch": 0.35189434215680787, + "grad_norm": 0.9125553107076922, + "learning_rate": 1.5041803483345715e-05, + "loss": 0.8422, + "step": 3930 + }, + { + "epoch": 0.35198388270188596, + "grad_norm": 0.9911840870158602, + "learning_rate": 1.5039298586736553e-05, + "loss": 0.8456, + "step": 3931 + }, + { + "epoch": 0.352073423246964, + "grad_norm": 0.9895231162495137, + "learning_rate": 1.5036793266238013e-05, + "loss": 0.8789, + "step": 3932 + }, + { + "epoch": 0.3521629637920421, + "grad_norm": 0.9681345323486902, + "learning_rate": 1.5034287522060838e-05, + "loss": 0.8627, + "step": 3933 + }, + { + "epoch": 0.35225250433712013, + "grad_norm": 0.8867903443526222, + "learning_rate": 1.50317813544158e-05, + "loss": 0.8858, + "step": 3934 + }, + { + "epoch": 0.3523420448821982, + "grad_norm": 0.9259796971721358, + "learning_rate": 1.5029274763513716e-05, + "loss": 0.8493, + "step": 3935 + }, + { + "epoch": 0.35243158542727626, + "grad_norm": 0.9767020867195255, + "learning_rate": 1.5026767749565423e-05, + "loss": 0.8526, + "step": 3936 + }, + { + "epoch": 0.35252112597235435, + "grad_norm": 0.9342679943746612, + "learning_rate": 1.5024260312781812e-05, + "loss": 0.815, + "step": 3937 + }, + { + "epoch": 0.35261066651743245, + "grad_norm": 0.9172558108437532, + "learning_rate": 1.5021752453373793e-05, + "loss": 0.7808, + "step": 3938 + }, + { + "epoch": 0.3527002070625105, + "grad_norm": 1.1711110308975234, + "learning_rate": 1.5019244171552326e-05, + "loss": 0.8673, + "step": 3939 + }, + { + "epoch": 0.3527897476075886, + "grad_norm": 0.9770321217887352, + "learning_rate": 1.5016735467528389e-05, + "loss": 0.8673, + "step": 3940 + }, + { + "epoch": 0.3528792881526666, + "grad_norm": 1.0105731489932666, + "learning_rate": 1.5014226341513016e-05, + "loss": 0.8565, + "step": 3941 + }, + { + "epoch": 0.3529688286977447, + "grad_norm": 0.9112453746323449, + "learning_rate": 1.5011716793717264e-05, + "loss": 0.877, + "step": 3942 + }, + { + "epoch": 0.35305836924282274, + "grad_norm": 1.0846777652944848, + "learning_rate": 1.5009206824352226e-05, + "loss": 0.779, + "step": 3943 + }, + { + "epoch": 0.35314790978790084, + "grad_norm": 1.1087094114060112, + "learning_rate": 1.5006696433629033e-05, + "loss": 0.8369, + "step": 3944 + }, + { + "epoch": 0.3532374503329789, + "grad_norm": 1.0708153279954185, + "learning_rate": 1.5004185621758853e-05, + "loss": 0.879, + "step": 3945 + }, + { + "epoch": 0.35332699087805697, + "grad_norm": 0.9203650064787073, + "learning_rate": 1.500167438895288e-05, + "loss": 0.8846, + "step": 3946 + }, + { + "epoch": 0.35341653142313506, + "grad_norm": 1.002084220792609, + "learning_rate": 1.4999162735422363e-05, + "loss": 0.9191, + "step": 3947 + }, + { + "epoch": 0.3535060719682131, + "grad_norm": 1.0025798121287472, + "learning_rate": 1.4996650661378567e-05, + "loss": 0.8654, + "step": 3948 + }, + { + "epoch": 0.3535956125132912, + "grad_norm": 1.000348914388443, + "learning_rate": 1.4994138167032798e-05, + "loss": 0.8703, + "step": 3949 + }, + { + "epoch": 0.35368515305836923, + "grad_norm": 0.9438194945155277, + "learning_rate": 1.49916252525964e-05, + "loss": 0.8284, + "step": 3950 + }, + { + "epoch": 0.3537746936034473, + "grad_norm": 0.900275860149152, + "learning_rate": 1.4989111918280755e-05, + "loss": 0.8637, + "step": 3951 + }, + { + "epoch": 0.35386423414852536, + "grad_norm": 0.9952525473553556, + "learning_rate": 1.498659816429727e-05, + "loss": 0.8409, + "step": 3952 + }, + { + "epoch": 0.35395377469360345, + "grad_norm": 1.0103762891662074, + "learning_rate": 1.4984083990857398e-05, + "loss": 0.8049, + "step": 3953 + }, + { + "epoch": 0.3540433152386815, + "grad_norm": 0.881035963127236, + "learning_rate": 1.4981569398172624e-05, + "loss": 0.8558, + "step": 3954 + }, + { + "epoch": 0.3541328557837596, + "grad_norm": 0.9063096293754465, + "learning_rate": 1.4979054386454465e-05, + "loss": 0.8538, + "step": 3955 + }, + { + "epoch": 0.3542223963288377, + "grad_norm": 0.9926465691497112, + "learning_rate": 1.4976538955914474e-05, + "loss": 0.851, + "step": 3956 + }, + { + "epoch": 0.3543119368739157, + "grad_norm": 1.0003253182625675, + "learning_rate": 1.4974023106764248e-05, + "loss": 0.8885, + "step": 3957 + }, + { + "epoch": 0.3544014774189938, + "grad_norm": 0.9066325681820581, + "learning_rate": 1.4971506839215404e-05, + "loss": 0.8138, + "step": 3958 + }, + { + "epoch": 0.35449101796407184, + "grad_norm": 1.0152014413483348, + "learning_rate": 1.4968990153479605e-05, + "loss": 0.8768, + "step": 3959 + }, + { + "epoch": 0.35458055850914993, + "grad_norm": 1.252522606505696, + "learning_rate": 1.4966473049768548e-05, + "loss": 0.8601, + "step": 3960 + }, + { + "epoch": 0.35467009905422797, + "grad_norm": 0.9535075526718158, + "learning_rate": 1.4963955528293961e-05, + "loss": 0.845, + "step": 3961 + }, + { + "epoch": 0.35475963959930606, + "grad_norm": 1.0927258466243515, + "learning_rate": 1.4961437589267611e-05, + "loss": 0.8533, + "step": 3962 + }, + { + "epoch": 0.3548491801443841, + "grad_norm": 1.070004456412874, + "learning_rate": 1.4958919232901301e-05, + "loss": 0.8363, + "step": 3963 + }, + { + "epoch": 0.3549387206894622, + "grad_norm": 0.9558127770766579, + "learning_rate": 1.4956400459406864e-05, + "loss": 0.8851, + "step": 3964 + }, + { + "epoch": 0.3550282612345403, + "grad_norm": 0.9479647573640971, + "learning_rate": 1.4953881268996169e-05, + "loss": 0.9248, + "step": 3965 + }, + { + "epoch": 0.3551178017796183, + "grad_norm": 0.9421883241057183, + "learning_rate": 1.495136166188113e-05, + "loss": 0.8765, + "step": 3966 + }, + { + "epoch": 0.3552073423246964, + "grad_norm": 0.8811124302527993, + "learning_rate": 1.4948841638273677e-05, + "loss": 0.83, + "step": 3967 + }, + { + "epoch": 0.35529688286977446, + "grad_norm": 0.8921003573685975, + "learning_rate": 1.4946321198385796e-05, + "loss": 0.8501, + "step": 3968 + }, + { + "epoch": 0.35538642341485255, + "grad_norm": 1.2053438652054258, + "learning_rate": 1.4943800342429495e-05, + "loss": 0.8611, + "step": 3969 + }, + { + "epoch": 0.3554759639599306, + "grad_norm": 1.0018680082260272, + "learning_rate": 1.4941279070616816e-05, + "loss": 0.8282, + "step": 3970 + }, + { + "epoch": 0.3555655045050087, + "grad_norm": 1.06883740713149, + "learning_rate": 1.493875738315985e-05, + "loss": 0.7919, + "step": 3971 + }, + { + "epoch": 0.3556550450500867, + "grad_norm": 0.8919671471160332, + "learning_rate": 1.4936235280270702e-05, + "loss": 0.8296, + "step": 3972 + }, + { + "epoch": 0.3557445855951648, + "grad_norm": 0.9520179686323305, + "learning_rate": 1.4933712762161525e-05, + "loss": 0.838, + "step": 3973 + }, + { + "epoch": 0.3558341261402429, + "grad_norm": 1.0363774531151329, + "learning_rate": 1.4931189829044514e-05, + "loss": 0.8727, + "step": 3974 + }, + { + "epoch": 0.35592366668532094, + "grad_norm": 1.1249006352208268, + "learning_rate": 1.4928666481131884e-05, + "loss": 0.861, + "step": 3975 + }, + { + "epoch": 0.35601320723039903, + "grad_norm": 0.9735390645226156, + "learning_rate": 1.4926142718635886e-05, + "loss": 0.8921, + "step": 3976 + }, + { + "epoch": 0.35610274777547707, + "grad_norm": 0.8965790523836814, + "learning_rate": 1.4923618541768819e-05, + "loss": 0.8681, + "step": 3977 + }, + { + "epoch": 0.35619228832055516, + "grad_norm": 0.9810827849055104, + "learning_rate": 1.4921093950743002e-05, + "loss": 0.8995, + "step": 3978 + }, + { + "epoch": 0.3562818288656332, + "grad_norm": 1.0141182664712898, + "learning_rate": 1.4918568945770801e-05, + "loss": 0.906, + "step": 3979 + }, + { + "epoch": 0.3563713694107113, + "grad_norm": 1.0145444768600687, + "learning_rate": 1.4916043527064608e-05, + "loss": 0.8941, + "step": 3980 + }, + { + "epoch": 0.35646090995578933, + "grad_norm": 1.0139159043896746, + "learning_rate": 1.4913517694836851e-05, + "loss": 0.8614, + "step": 3981 + }, + { + "epoch": 0.3565504505008674, + "grad_norm": 0.8543208214084534, + "learning_rate": 1.4910991449299998e-05, + "loss": 0.8901, + "step": 3982 + }, + { + "epoch": 0.3566399910459455, + "grad_norm": 0.9086471593959841, + "learning_rate": 1.490846479066655e-05, + "loss": 0.8213, + "step": 3983 + }, + { + "epoch": 0.35672953159102355, + "grad_norm": 1.0055538116106704, + "learning_rate": 1.4905937719149038e-05, + "loss": 0.9009, + "step": 3984 + }, + { + "epoch": 0.35681907213610164, + "grad_norm": 0.9945893144854023, + "learning_rate": 1.4903410234960032e-05, + "loss": 0.8706, + "step": 3985 + }, + { + "epoch": 0.3569086126811797, + "grad_norm": 0.8762873363231536, + "learning_rate": 1.4900882338312134e-05, + "loss": 0.8599, + "step": 3986 + }, + { + "epoch": 0.3569981532262578, + "grad_norm": 0.9382703022649406, + "learning_rate": 1.4898354029417987e-05, + "loss": 0.8114, + "step": 3987 + }, + { + "epoch": 0.3570876937713358, + "grad_norm": 0.8947749929853646, + "learning_rate": 1.4895825308490259e-05, + "loss": 0.889, + "step": 3988 + }, + { + "epoch": 0.3571772343164139, + "grad_norm": 0.9020415971229506, + "learning_rate": 1.4893296175741663e-05, + "loss": 0.8255, + "step": 3989 + }, + { + "epoch": 0.35726677486149194, + "grad_norm": 0.8827857204131178, + "learning_rate": 1.4890766631384934e-05, + "loss": 0.8771, + "step": 3990 + }, + { + "epoch": 0.35735631540657004, + "grad_norm": 1.0047935358583926, + "learning_rate": 1.4888236675632857e-05, + "loss": 0.8368, + "step": 3991 + }, + { + "epoch": 0.35744585595164813, + "grad_norm": 0.9719191902868516, + "learning_rate": 1.488570630869824e-05, + "loss": 0.8789, + "step": 3992 + }, + { + "epoch": 0.35753539649672617, + "grad_norm": 0.9044832073080918, + "learning_rate": 1.488317553079393e-05, + "loss": 0.8511, + "step": 3993 + }, + { + "epoch": 0.35762493704180426, + "grad_norm": 0.9119614247703369, + "learning_rate": 1.4880644342132804e-05, + "loss": 0.8425, + "step": 3994 + }, + { + "epoch": 0.3577144775868823, + "grad_norm": 0.8731226108467127, + "learning_rate": 1.4878112742927784e-05, + "loss": 0.8657, + "step": 3995 + }, + { + "epoch": 0.3578040181319604, + "grad_norm": 0.9368926264624609, + "learning_rate": 1.4875580733391814e-05, + "loss": 0.8549, + "step": 3996 + }, + { + "epoch": 0.3578935586770384, + "grad_norm": 0.9281394912926532, + "learning_rate": 1.4873048313737881e-05, + "loss": 0.8474, + "step": 3997 + }, + { + "epoch": 0.3579830992221165, + "grad_norm": 0.9095304979047474, + "learning_rate": 1.4870515484179005e-05, + "loss": 0.9027, + "step": 3998 + }, + { + "epoch": 0.35807263976719456, + "grad_norm": 0.8558355670174908, + "learning_rate": 1.4867982244928238e-05, + "loss": 0.8397, + "step": 3999 + }, + { + "epoch": 0.35816218031227265, + "grad_norm": 0.9499847223776043, + "learning_rate": 1.4865448596198666e-05, + "loss": 0.8067, + "step": 4000 + }, + { + "epoch": 0.35825172085735074, + "grad_norm": 0.9465277207326475, + "learning_rate": 1.4862914538203416e-05, + "loss": 0.801, + "step": 4001 + }, + { + "epoch": 0.3583412614024288, + "grad_norm": 0.9309723660707486, + "learning_rate": 1.4860380071155641e-05, + "loss": 0.8441, + "step": 4002 + }, + { + "epoch": 0.35843080194750687, + "grad_norm": 1.0109531801666056, + "learning_rate": 1.485784519526853e-05, + "loss": 0.8919, + "step": 4003 + }, + { + "epoch": 0.3585203424925849, + "grad_norm": 0.9360921943844651, + "learning_rate": 1.4855309910755315e-05, + "loss": 0.8808, + "step": 4004 + }, + { + "epoch": 0.358609883037663, + "grad_norm": 0.9745386655068174, + "learning_rate": 1.485277421782925e-05, + "loss": 0.8509, + "step": 4005 + }, + { + "epoch": 0.35869942358274104, + "grad_norm": 0.9036447989275697, + "learning_rate": 1.485023811670363e-05, + "loss": 0.8549, + "step": 4006 + }, + { + "epoch": 0.35878896412781913, + "grad_norm": 1.0781452688504636, + "learning_rate": 1.4847701607591791e-05, + "loss": 0.8284, + "step": 4007 + }, + { + "epoch": 0.35887850467289717, + "grad_norm": 0.9981096948196267, + "learning_rate": 1.4845164690707087e-05, + "loss": 0.8312, + "step": 4008 + }, + { + "epoch": 0.35896804521797526, + "grad_norm": 0.9138844107706523, + "learning_rate": 1.4842627366262918e-05, + "loss": 0.8504, + "step": 4009 + }, + { + "epoch": 0.35905758576305336, + "grad_norm": 0.970251279851938, + "learning_rate": 1.4840089634472715e-05, + "loss": 0.8141, + "step": 4010 + }, + { + "epoch": 0.3591471263081314, + "grad_norm": 0.8766481046911421, + "learning_rate": 1.4837551495549944e-05, + "loss": 0.8595, + "step": 4011 + }, + { + "epoch": 0.3592366668532095, + "grad_norm": 0.9393628554931694, + "learning_rate": 1.4835012949708105e-05, + "loss": 0.8623, + "step": 4012 + }, + { + "epoch": 0.3593262073982875, + "grad_norm": 1.1619033550296851, + "learning_rate": 1.4832473997160735e-05, + "loss": 0.8889, + "step": 4013 + }, + { + "epoch": 0.3594157479433656, + "grad_norm": 0.9114933278405927, + "learning_rate": 1.48299346381214e-05, + "loss": 0.835, + "step": 4014 + }, + { + "epoch": 0.35950528848844365, + "grad_norm": 1.0021328170446315, + "learning_rate": 1.48273948728037e-05, + "loss": 0.8099, + "step": 4015 + }, + { + "epoch": 0.35959482903352175, + "grad_norm": 0.84380845670878, + "learning_rate": 1.4824854701421277e-05, + "loss": 0.8568, + "step": 4016 + }, + { + "epoch": 0.3596843695785998, + "grad_norm": 0.8336619936350709, + "learning_rate": 1.4822314124187795e-05, + "loss": 0.8245, + "step": 4017 + }, + { + "epoch": 0.3597739101236779, + "grad_norm": 0.9653655240524449, + "learning_rate": 1.4819773141316967e-05, + "loss": 0.8724, + "step": 4018 + }, + { + "epoch": 0.35986345066875597, + "grad_norm": 0.9926892922993221, + "learning_rate": 1.4817231753022528e-05, + "loss": 0.8477, + "step": 4019 + }, + { + "epoch": 0.359952991213834, + "grad_norm": 0.896176376730794, + "learning_rate": 1.4814689959518254e-05, + "loss": 0.8274, + "step": 4020 + }, + { + "epoch": 0.3600425317589121, + "grad_norm": 0.900490633457732, + "learning_rate": 1.4812147761017946e-05, + "loss": 0.8348, + "step": 4021 + }, + { + "epoch": 0.36013207230399014, + "grad_norm": 0.9283388486767167, + "learning_rate": 1.480960515773545e-05, + "loss": 0.8528, + "step": 4022 + }, + { + "epoch": 0.36022161284906823, + "grad_norm": 0.961354230676862, + "learning_rate": 1.4807062149884645e-05, + "loss": 0.8956, + "step": 4023 + }, + { + "epoch": 0.36031115339414627, + "grad_norm": 0.8707301391479813, + "learning_rate": 1.4804518737679435e-05, + "loss": 0.8515, + "step": 4024 + }, + { + "epoch": 0.36040069393922436, + "grad_norm": 0.8910716818537476, + "learning_rate": 1.4801974921333763e-05, + "loss": 0.811, + "step": 4025 + }, + { + "epoch": 0.3604902344843024, + "grad_norm": 1.0146513302106128, + "learning_rate": 1.4799430701061613e-05, + "loss": 0.8897, + "step": 4026 + }, + { + "epoch": 0.3605797750293805, + "grad_norm": 1.0512585860498647, + "learning_rate": 1.4796886077076988e-05, + "loss": 0.8856, + "step": 4027 + }, + { + "epoch": 0.3606693155744586, + "grad_norm": 1.0093057152977183, + "learning_rate": 1.4794341049593939e-05, + "loss": 0.8472, + "step": 4028 + }, + { + "epoch": 0.3607588561195366, + "grad_norm": 1.052685762546745, + "learning_rate": 1.4791795618826548e-05, + "loss": 0.8864, + "step": 4029 + }, + { + "epoch": 0.3608483966646147, + "grad_norm": 0.9893494121114546, + "learning_rate": 1.4789249784988919e-05, + "loss": 0.8434, + "step": 4030 + }, + { + "epoch": 0.36093793720969275, + "grad_norm": 0.9449777376451948, + "learning_rate": 1.478670354829521e-05, + "loss": 0.8074, + "step": 4031 + }, + { + "epoch": 0.36102747775477084, + "grad_norm": 0.8373353355657409, + "learning_rate": 1.4784156908959593e-05, + "loss": 0.8377, + "step": 4032 + }, + { + "epoch": 0.3611170182998489, + "grad_norm": 0.9255538441038482, + "learning_rate": 1.4781609867196288e-05, + "loss": 0.8994, + "step": 4033 + }, + { + "epoch": 0.361206558844927, + "grad_norm": 0.8821222426449012, + "learning_rate": 1.4779062423219543e-05, + "loss": 0.8686, + "step": 4034 + }, + { + "epoch": 0.361296099390005, + "grad_norm": 1.0393899978040426, + "learning_rate": 1.4776514577243641e-05, + "loss": 0.9001, + "step": 4035 + }, + { + "epoch": 0.3613856399350831, + "grad_norm": 0.9929826756024304, + "learning_rate": 1.4773966329482896e-05, + "loss": 0.8957, + "step": 4036 + }, + { + "epoch": 0.3614751804801612, + "grad_norm": 0.9391545345948109, + "learning_rate": 1.4771417680151665e-05, + "loss": 0.8668, + "step": 4037 + }, + { + "epoch": 0.36156472102523923, + "grad_norm": 1.0267193633512912, + "learning_rate": 1.4768868629464323e-05, + "loss": 0.8427, + "step": 4038 + }, + { + "epoch": 0.3616542615703173, + "grad_norm": 0.9031494240910067, + "learning_rate": 1.4766319177635292e-05, + "loss": 0.7593, + "step": 4039 + }, + { + "epoch": 0.36174380211539536, + "grad_norm": 1.0102326389506426, + "learning_rate": 1.4763769324879027e-05, + "loss": 0.8962, + "step": 4040 + }, + { + "epoch": 0.36183334266047346, + "grad_norm": 1.7522725429409525, + "learning_rate": 1.476121907141001e-05, + "loss": 0.8607, + "step": 4041 + }, + { + "epoch": 0.3619228832055515, + "grad_norm": 1.1429766071364311, + "learning_rate": 1.4758668417442758e-05, + "loss": 0.9142, + "step": 4042 + }, + { + "epoch": 0.3620124237506296, + "grad_norm": 0.9184820020074588, + "learning_rate": 1.4756117363191826e-05, + "loss": 0.869, + "step": 4043 + }, + { + "epoch": 0.3621019642957076, + "grad_norm": 0.9298283306943418, + "learning_rate": 1.47535659088718e-05, + "loss": 0.9037, + "step": 4044 + }, + { + "epoch": 0.3621915048407857, + "grad_norm": 0.9260994231600933, + "learning_rate": 1.4751014054697303e-05, + "loss": 0.8354, + "step": 4045 + }, + { + "epoch": 0.3622810453858638, + "grad_norm": 1.0571478987673144, + "learning_rate": 1.4748461800882983e-05, + "loss": 0.8365, + "step": 4046 + }, + { + "epoch": 0.36237058593094185, + "grad_norm": 0.8745635579504719, + "learning_rate": 1.4745909147643532e-05, + "loss": 0.816, + "step": 4047 + }, + { + "epoch": 0.36246012647601994, + "grad_norm": 1.0076007197914887, + "learning_rate": 1.4743356095193665e-05, + "loss": 0.8339, + "step": 4048 + }, + { + "epoch": 0.362549667021098, + "grad_norm": 0.8623204778969524, + "learning_rate": 1.4740802643748145e-05, + "loss": 0.8735, + "step": 4049 + }, + { + "epoch": 0.36263920756617607, + "grad_norm": 0.9306466292765032, + "learning_rate": 1.4738248793521756e-05, + "loss": 0.8923, + "step": 4050 + }, + { + "epoch": 0.3627287481112541, + "grad_norm": 0.973520307813799, + "learning_rate": 1.4735694544729315e-05, + "loss": 0.8853, + "step": 4051 + }, + { + "epoch": 0.3628182886563322, + "grad_norm": 0.9408571165343537, + "learning_rate": 1.4733139897585682e-05, + "loss": 0.8519, + "step": 4052 + }, + { + "epoch": 0.36290782920141024, + "grad_norm": 1.0694960168730903, + "learning_rate": 1.473058485230575e-05, + "loss": 0.8447, + "step": 4053 + }, + { + "epoch": 0.36299736974648833, + "grad_norm": 0.8625521884335589, + "learning_rate": 1.4728029409104428e-05, + "loss": 0.88, + "step": 4054 + }, + { + "epoch": 0.3630869102915664, + "grad_norm": 0.9511602530717933, + "learning_rate": 1.4725473568196682e-05, + "loss": 0.8597, + "step": 4055 + }, + { + "epoch": 0.36317645083664446, + "grad_norm": 0.9235567102628609, + "learning_rate": 1.4722917329797502e-05, + "loss": 0.8488, + "step": 4056 + }, + { + "epoch": 0.36326599138172255, + "grad_norm": 0.9710407996319418, + "learning_rate": 1.4720360694121902e-05, + "loss": 0.8449, + "step": 4057 + }, + { + "epoch": 0.3633555319268006, + "grad_norm": 1.0127019393547076, + "learning_rate": 1.4717803661384946e-05, + "loss": 0.8287, + "step": 4058 + }, + { + "epoch": 0.3634450724718787, + "grad_norm": 1.0016754295269792, + "learning_rate": 1.4715246231801722e-05, + "loss": 0.9266, + "step": 4059 + }, + { + "epoch": 0.3635346130169567, + "grad_norm": 1.0414652776828093, + "learning_rate": 1.4712688405587344e-05, + "loss": 0.8345, + "step": 4060 + }, + { + "epoch": 0.3636241535620348, + "grad_norm": 0.9147906583948842, + "learning_rate": 1.4710130182956979e-05, + "loss": 0.8703, + "step": 4061 + }, + { + "epoch": 0.36371369410711285, + "grad_norm": 0.9039883098756201, + "learning_rate": 1.4707571564125812e-05, + "loss": 0.8111, + "step": 4062 + }, + { + "epoch": 0.36380323465219094, + "grad_norm": 1.0104084563859532, + "learning_rate": 1.470501254930906e-05, + "loss": 0.8534, + "step": 4063 + }, + { + "epoch": 0.36389277519726904, + "grad_norm": 0.9348460603919654, + "learning_rate": 1.4702453138721993e-05, + "loss": 0.8104, + "step": 4064 + }, + { + "epoch": 0.3639823157423471, + "grad_norm": 1.1858454653745654, + "learning_rate": 1.4699893332579886e-05, + "loss": 0.8519, + "step": 4065 + }, + { + "epoch": 0.36407185628742517, + "grad_norm": 1.0272632778017143, + "learning_rate": 1.4697333131098069e-05, + "loss": 0.9099, + "step": 4066 + }, + { + "epoch": 0.3641613968325032, + "grad_norm": 0.9827629962373259, + "learning_rate": 1.4694772534491897e-05, + "loss": 0.8043, + "step": 4067 + }, + { + "epoch": 0.3642509373775813, + "grad_norm": 0.8777019465298066, + "learning_rate": 1.4692211542976757e-05, + "loss": 0.843, + "step": 4068 + }, + { + "epoch": 0.36434047792265933, + "grad_norm": 0.8673015446226611, + "learning_rate": 1.4689650156768071e-05, + "loss": 0.8959, + "step": 4069 + }, + { + "epoch": 0.3644300184677374, + "grad_norm": 0.9435678343627695, + "learning_rate": 1.46870883760813e-05, + "loss": 0.861, + "step": 4070 + }, + { + "epoch": 0.36451955901281546, + "grad_norm": 0.8985379523982656, + "learning_rate": 1.4684526201131928e-05, + "loss": 0.8689, + "step": 4071 + }, + { + "epoch": 0.36460909955789356, + "grad_norm": 1.0688693823840476, + "learning_rate": 1.4681963632135476e-05, + "loss": 0.8521, + "step": 4072 + }, + { + "epoch": 0.36469864010297165, + "grad_norm": 0.9256763920799816, + "learning_rate": 1.46794006693075e-05, + "loss": 0.8737, + "step": 4073 + }, + { + "epoch": 0.3647881806480497, + "grad_norm": 0.9408529298359314, + "learning_rate": 1.467683731286359e-05, + "loss": 0.8832, + "step": 4074 + }, + { + "epoch": 0.3648777211931278, + "grad_norm": 0.895891875152209, + "learning_rate": 1.4674273563019365e-05, + "loss": 0.8303, + "step": 4075 + }, + { + "epoch": 0.3649672617382058, + "grad_norm": 0.8205494219956654, + "learning_rate": 1.467170941999048e-05, + "loss": 0.8115, + "step": 4076 + }, + { + "epoch": 0.3650568022832839, + "grad_norm": 0.9518379564802395, + "learning_rate": 1.466914488399262e-05, + "loss": 0.8454, + "step": 4077 + }, + { + "epoch": 0.36514634282836195, + "grad_norm": 1.0390404653472753, + "learning_rate": 1.4666579955241512e-05, + "loss": 0.8613, + "step": 4078 + }, + { + "epoch": 0.36523588337344004, + "grad_norm": 1.0364938891315036, + "learning_rate": 1.4664014633952902e-05, + "loss": 0.857, + "step": 4079 + }, + { + "epoch": 0.3653254239185181, + "grad_norm": 0.8691771682474251, + "learning_rate": 1.4661448920342585e-05, + "loss": 0.8169, + "step": 4080 + }, + { + "epoch": 0.36541496446359617, + "grad_norm": 0.9953302089039852, + "learning_rate": 1.4658882814626367e-05, + "loss": 0.9031, + "step": 4081 + }, + { + "epoch": 0.36550450500867426, + "grad_norm": 0.9682627622132935, + "learning_rate": 1.4656316317020113e-05, + "loss": 0.8016, + "step": 4082 + }, + { + "epoch": 0.3655940455537523, + "grad_norm": 0.959822597413384, + "learning_rate": 1.4653749427739704e-05, + "loss": 0.8048, + "step": 4083 + }, + { + "epoch": 0.3656835860988304, + "grad_norm": 0.913700034180063, + "learning_rate": 1.4651182147001057e-05, + "loss": 0.8153, + "step": 4084 + }, + { + "epoch": 0.36577312664390843, + "grad_norm": 1.2243079953148666, + "learning_rate": 1.4648614475020125e-05, + "loss": 0.9083, + "step": 4085 + }, + { + "epoch": 0.3658626671889865, + "grad_norm": 0.9506877471484193, + "learning_rate": 1.4646046412012893e-05, + "loss": 0.8195, + "step": 4086 + }, + { + "epoch": 0.36595220773406456, + "grad_norm": 0.8011070135513193, + "learning_rate": 1.4643477958195376e-05, + "loss": 0.7589, + "step": 4087 + }, + { + "epoch": 0.36604174827914265, + "grad_norm": 0.9288589637605866, + "learning_rate": 1.4640909113783623e-05, + "loss": 0.8725, + "step": 4088 + }, + { + "epoch": 0.3661312888242207, + "grad_norm": 0.9405992575363072, + "learning_rate": 1.4638339878993723e-05, + "loss": 0.8677, + "step": 4089 + }, + { + "epoch": 0.3662208293692988, + "grad_norm": 1.0380543353325462, + "learning_rate": 1.4635770254041784e-05, + "loss": 0.7548, + "step": 4090 + }, + { + "epoch": 0.3663103699143769, + "grad_norm": 0.8970078123160518, + "learning_rate": 1.4633200239143958e-05, + "loss": 0.8583, + "step": 4091 + }, + { + "epoch": 0.3663999104594549, + "grad_norm": 0.9097403396290786, + "learning_rate": 1.4630629834516427e-05, + "loss": 0.8919, + "step": 4092 + }, + { + "epoch": 0.366489451004533, + "grad_norm": 0.9371330768865324, + "learning_rate": 1.4628059040375404e-05, + "loss": 0.839, + "step": 4093 + }, + { + "epoch": 0.36657899154961104, + "grad_norm": 0.9171870033562859, + "learning_rate": 1.4625487856937138e-05, + "loss": 0.8278, + "step": 4094 + }, + { + "epoch": 0.36666853209468914, + "grad_norm": 0.9689193482290918, + "learning_rate": 1.4622916284417903e-05, + "loss": 0.849, + "step": 4095 + }, + { + "epoch": 0.3667580726397672, + "grad_norm": 0.8347713221596132, + "learning_rate": 1.4620344323034016e-05, + "loss": 0.8802, + "step": 4096 + }, + { + "epoch": 0.36684761318484527, + "grad_norm": 0.8840334704281035, + "learning_rate": 1.4617771973001822e-05, + "loss": 0.8319, + "step": 4097 + }, + { + "epoch": 0.3669371537299233, + "grad_norm": 0.8216425413124275, + "learning_rate": 1.4615199234537698e-05, + "loss": 0.8732, + "step": 4098 + }, + { + "epoch": 0.3670266942750014, + "grad_norm": 0.9754660316412291, + "learning_rate": 1.461262610785805e-05, + "loss": 0.8795, + "step": 4099 + }, + { + "epoch": 0.3671162348200795, + "grad_norm": 0.9026359820102634, + "learning_rate": 1.461005259317933e-05, + "loss": 0.9458, + "step": 4100 + }, + { + "epoch": 0.3672057753651575, + "grad_norm": 1.0746453418878956, + "learning_rate": 1.4607478690718006e-05, + "loss": 0.8649, + "step": 4101 + }, + { + "epoch": 0.3672953159102356, + "grad_norm": 0.9559400659691023, + "learning_rate": 1.4604904400690591e-05, + "loss": 0.795, + "step": 4102 + }, + { + "epoch": 0.36738485645531366, + "grad_norm": 0.9036957099192082, + "learning_rate": 1.4602329723313623e-05, + "loss": 0.8097, + "step": 4103 + }, + { + "epoch": 0.36747439700039175, + "grad_norm": 0.9045081647667311, + "learning_rate": 1.4599754658803673e-05, + "loss": 0.9519, + "step": 4104 + }, + { + "epoch": 0.3675639375454698, + "grad_norm": 0.8277504622275791, + "learning_rate": 1.4597179207377354e-05, + "loss": 0.8073, + "step": 4105 + }, + { + "epoch": 0.3676534780905479, + "grad_norm": 0.875719161653309, + "learning_rate": 1.4594603369251302e-05, + "loss": 0.8678, + "step": 4106 + }, + { + "epoch": 0.3677430186356259, + "grad_norm": 0.9519674453999357, + "learning_rate": 1.4592027144642183e-05, + "loss": 0.8155, + "step": 4107 + }, + { + "epoch": 0.367832559180704, + "grad_norm": 1.1021867470081759, + "learning_rate": 1.4589450533766707e-05, + "loss": 0.8075, + "step": 4108 + }, + { + "epoch": 0.3679220997257821, + "grad_norm": 0.8844108959018988, + "learning_rate": 1.4586873536841607e-05, + "loss": 0.8426, + "step": 4109 + }, + { + "epoch": 0.36801164027086014, + "grad_norm": 0.8576527569185451, + "learning_rate": 1.4584296154083653e-05, + "loss": 0.7999, + "step": 4110 + }, + { + "epoch": 0.36810118081593823, + "grad_norm": 0.922963579957153, + "learning_rate": 1.4581718385709645e-05, + "loss": 0.8432, + "step": 4111 + }, + { + "epoch": 0.36819072136101627, + "grad_norm": 0.9087362793791527, + "learning_rate": 1.4579140231936415e-05, + "loss": 0.9006, + "step": 4112 + }, + { + "epoch": 0.36828026190609436, + "grad_norm": 1.002410940660549, + "learning_rate": 1.4576561692980834e-05, + "loss": 0.8766, + "step": 4113 + }, + { + "epoch": 0.3683698024511724, + "grad_norm": 0.9253837969336944, + "learning_rate": 1.4573982769059796e-05, + "loss": 0.8403, + "step": 4114 + }, + { + "epoch": 0.3684593429962505, + "grad_norm": 1.0720434226150808, + "learning_rate": 1.4571403460390233e-05, + "loss": 0.9115, + "step": 4115 + }, + { + "epoch": 0.36854888354132853, + "grad_norm": 0.8762742283650113, + "learning_rate": 1.4568823767189109e-05, + "loss": 0.7979, + "step": 4116 + }, + { + "epoch": 0.3686384240864066, + "grad_norm": 0.9164485334793443, + "learning_rate": 1.4566243689673413e-05, + "loss": 0.8665, + "step": 4117 + }, + { + "epoch": 0.3687279646314847, + "grad_norm": 0.9216615852090195, + "learning_rate": 1.456366322806018e-05, + "loss": 0.8808, + "step": 4118 + }, + { + "epoch": 0.36881750517656275, + "grad_norm": 1.037505096457901, + "learning_rate": 1.4561082382566472e-05, + "loss": 0.8749, + "step": 4119 + }, + { + "epoch": 0.36890704572164085, + "grad_norm": 0.9662641545534558, + "learning_rate": 1.4558501153409372e-05, + "loss": 0.889, + "step": 4120 + }, + { + "epoch": 0.3689965862667189, + "grad_norm": 0.9436247487062716, + "learning_rate": 1.4555919540806015e-05, + "loss": 0.7996, + "step": 4121 + }, + { + "epoch": 0.369086126811797, + "grad_norm": 0.9530414673661675, + "learning_rate": 1.4553337544973549e-05, + "loss": 0.8855, + "step": 4122 + }, + { + "epoch": 0.369175667356875, + "grad_norm": 1.0157256461677562, + "learning_rate": 1.4550755166129165e-05, + "loss": 0.863, + "step": 4123 + }, + { + "epoch": 0.3692652079019531, + "grad_norm": 1.0917150189980733, + "learning_rate": 1.454817240449009e-05, + "loss": 0.818, + "step": 4124 + }, + { + "epoch": 0.36935474844703114, + "grad_norm": 1.082301371864195, + "learning_rate": 1.4545589260273572e-05, + "loss": 0.8133, + "step": 4125 + }, + { + "epoch": 0.36944428899210924, + "grad_norm": 0.8593234056065762, + "learning_rate": 1.4543005733696896e-05, + "loss": 0.8903, + "step": 4126 + }, + { + "epoch": 0.36953382953718733, + "grad_norm": 0.8789815034499544, + "learning_rate": 1.4540421824977386e-05, + "loss": 0.8555, + "step": 4127 + }, + { + "epoch": 0.36962337008226537, + "grad_norm": 0.9931615463947052, + "learning_rate": 1.4537837534332386e-05, + "loss": 0.8427, + "step": 4128 + }, + { + "epoch": 0.36971291062734346, + "grad_norm": 0.9386252408354195, + "learning_rate": 1.453525286197928e-05, + "loss": 0.8675, + "step": 4129 + }, + { + "epoch": 0.3698024511724215, + "grad_norm": 1.1073360248027586, + "learning_rate": 1.4532667808135484e-05, + "loss": 0.8911, + "step": 4130 + }, + { + "epoch": 0.3698919917174996, + "grad_norm": 1.1958180215896763, + "learning_rate": 1.4530082373018439e-05, + "loss": 0.8355, + "step": 4131 + }, + { + "epoch": 0.36998153226257763, + "grad_norm": 1.126802437089102, + "learning_rate": 1.4527496556845631e-05, + "loss": 0.8394, + "step": 4132 + }, + { + "epoch": 0.3700710728076557, + "grad_norm": 0.938014900646232, + "learning_rate": 1.4524910359834563e-05, + "loss": 0.8941, + "step": 4133 + }, + { + "epoch": 0.37016061335273376, + "grad_norm": 0.9279658248917745, + "learning_rate": 1.4522323782202783e-05, + "loss": 0.8607, + "step": 4134 + }, + { + "epoch": 0.37025015389781185, + "grad_norm": 0.9044983000499031, + "learning_rate": 1.451973682416786e-05, + "loss": 0.8586, + "step": 4135 + }, + { + "epoch": 0.37033969444288994, + "grad_norm": 0.9258374683090905, + "learning_rate": 1.4517149485947409e-05, + "loss": 0.8179, + "step": 4136 + }, + { + "epoch": 0.370429234987968, + "grad_norm": 0.9328437117047843, + "learning_rate": 1.4514561767759059e-05, + "loss": 0.8712, + "step": 4137 + }, + { + "epoch": 0.3705187755330461, + "grad_norm": 0.9843834075522936, + "learning_rate": 1.4511973669820487e-05, + "loss": 0.8098, + "step": 4138 + }, + { + "epoch": 0.3706083160781241, + "grad_norm": 0.9373994711582793, + "learning_rate": 1.4509385192349393e-05, + "loss": 0.8908, + "step": 4139 + }, + { + "epoch": 0.3706978566232022, + "grad_norm": 0.9483480264780919, + "learning_rate": 1.450679633556351e-05, + "loss": 0.8888, + "step": 4140 + }, + { + "epoch": 0.37078739716828024, + "grad_norm": 0.9726878435845129, + "learning_rate": 1.4504207099680607e-05, + "loss": 0.9089, + "step": 4141 + }, + { + "epoch": 0.37087693771335833, + "grad_norm": 0.9591857220650409, + "learning_rate": 1.450161748491848e-05, + "loss": 0.8324, + "step": 4142 + }, + { + "epoch": 0.37096647825843637, + "grad_norm": 0.9260482342200291, + "learning_rate": 1.449902749149496e-05, + "loss": 0.9035, + "step": 4143 + }, + { + "epoch": 0.37105601880351446, + "grad_norm": 0.901350748863898, + "learning_rate": 1.4496437119627907e-05, + "loss": 0.8726, + "step": 4144 + }, + { + "epoch": 0.37114555934859256, + "grad_norm": 0.8669579378283601, + "learning_rate": 1.4493846369535219e-05, + "loss": 0.84, + "step": 4145 + }, + { + "epoch": 0.3712350998936706, + "grad_norm": 0.8750001983119764, + "learning_rate": 1.4491255241434817e-05, + "loss": 0.8034, + "step": 4146 + }, + { + "epoch": 0.3713246404387487, + "grad_norm": 0.8975750934615734, + "learning_rate": 1.4488663735544658e-05, + "loss": 0.8336, + "step": 4147 + }, + { + "epoch": 0.3714141809838267, + "grad_norm": 0.8685969831656057, + "learning_rate": 1.4486071852082733e-05, + "loss": 0.8607, + "step": 4148 + }, + { + "epoch": 0.3715037215289048, + "grad_norm": 0.9830188299775098, + "learning_rate": 1.4483479591267067e-05, + "loss": 0.8609, + "step": 4149 + }, + { + "epoch": 0.37159326207398286, + "grad_norm": 0.9743289775855571, + "learning_rate": 1.4480886953315703e-05, + "loss": 0.8616, + "step": 4150 + }, + { + "epoch": 0.37168280261906095, + "grad_norm": 0.9040133995543536, + "learning_rate": 1.4478293938446734e-05, + "loss": 0.8511, + "step": 4151 + }, + { + "epoch": 0.371772343164139, + "grad_norm": 0.9608664745308472, + "learning_rate": 1.447570054687827e-05, + "loss": 0.8687, + "step": 4152 + }, + { + "epoch": 0.3718618837092171, + "grad_norm": 0.8568078994124085, + "learning_rate": 1.4473106778828459e-05, + "loss": 0.8819, + "step": 4153 + }, + { + "epoch": 0.37195142425429517, + "grad_norm": 0.9571225764767383, + "learning_rate": 1.4470512634515489e-05, + "loss": 0.8633, + "step": 4154 + }, + { + "epoch": 0.3720409647993732, + "grad_norm": 0.9347425653078706, + "learning_rate": 1.4467918114157558e-05, + "loss": 0.8157, + "step": 4155 + }, + { + "epoch": 0.3721305053444513, + "grad_norm": 1.03193702636088, + "learning_rate": 1.4465323217972917e-05, + "loss": 0.8546, + "step": 4156 + }, + { + "epoch": 0.37222004588952934, + "grad_norm": 0.945834178468124, + "learning_rate": 1.446272794617984e-05, + "loss": 0.8623, + "step": 4157 + }, + { + "epoch": 0.37230958643460743, + "grad_norm": 0.9050818227267468, + "learning_rate": 1.4460132298996628e-05, + "loss": 0.8793, + "step": 4158 + }, + { + "epoch": 0.37239912697968547, + "grad_norm": 0.8615703755038566, + "learning_rate": 1.4457536276641621e-05, + "loss": 0.8149, + "step": 4159 + }, + { + "epoch": 0.37248866752476356, + "grad_norm": 1.0278482566477132, + "learning_rate": 1.445493987933319e-05, + "loss": 0.8989, + "step": 4160 + }, + { + "epoch": 0.3725782080698416, + "grad_norm": 0.8801070334629719, + "learning_rate": 1.4452343107289733e-05, + "loss": 0.8341, + "step": 4161 + }, + { + "epoch": 0.3726677486149197, + "grad_norm": 1.1238091076363188, + "learning_rate": 1.4449745960729681e-05, + "loss": 0.8735, + "step": 4162 + }, + { + "epoch": 0.3727572891599978, + "grad_norm": 1.1129784660018307, + "learning_rate": 1.4447148439871503e-05, + "loss": 0.8426, + "step": 4163 + }, + { + "epoch": 0.3728468297050758, + "grad_norm": 0.9606956187602632, + "learning_rate": 1.4444550544933687e-05, + "loss": 0.8642, + "step": 4164 + }, + { + "epoch": 0.3729363702501539, + "grad_norm": 1.0006790830059897, + "learning_rate": 1.4441952276134766e-05, + "loss": 0.8109, + "step": 4165 + }, + { + "epoch": 0.37302591079523195, + "grad_norm": 0.9421086824793374, + "learning_rate": 1.4439353633693292e-05, + "loss": 0.8473, + "step": 4166 + }, + { + "epoch": 0.37311545134031004, + "grad_norm": 0.9224093364861758, + "learning_rate": 1.4436754617827857e-05, + "loss": 0.8096, + "step": 4167 + }, + { + "epoch": 0.3732049918853881, + "grad_norm": 0.8791060932886061, + "learning_rate": 1.443415522875708e-05, + "loss": 0.8441, + "step": 4168 + }, + { + "epoch": 0.3732945324304662, + "grad_norm": 0.8971121012311769, + "learning_rate": 1.4431555466699619e-05, + "loss": 0.87, + "step": 4169 + }, + { + "epoch": 0.3733840729755442, + "grad_norm": 0.9583130954477878, + "learning_rate": 1.4428955331874148e-05, + "loss": 0.8241, + "step": 4170 + }, + { + "epoch": 0.3734736135206223, + "grad_norm": 0.919696875065664, + "learning_rate": 1.4426354824499391e-05, + "loss": 0.8561, + "step": 4171 + }, + { + "epoch": 0.3735631540657004, + "grad_norm": 1.049418800107167, + "learning_rate": 1.442375394479409e-05, + "loss": 0.8844, + "step": 4172 + }, + { + "epoch": 0.37365269461077844, + "grad_norm": 1.0046427750498634, + "learning_rate": 1.4421152692977023e-05, + "loss": 0.8387, + "step": 4173 + }, + { + "epoch": 0.37374223515585653, + "grad_norm": 0.9120003435613306, + "learning_rate": 1.4418551069266996e-05, + "loss": 0.8953, + "step": 4174 + }, + { + "epoch": 0.37383177570093457, + "grad_norm": 0.8437144270980298, + "learning_rate": 1.4415949073882853e-05, + "loss": 0.8187, + "step": 4175 + }, + { + "epoch": 0.37392131624601266, + "grad_norm": 1.091793818287057, + "learning_rate": 1.4413346707043467e-05, + "loss": 0.8757, + "step": 4176 + }, + { + "epoch": 0.3740108567910907, + "grad_norm": 0.9206951397598376, + "learning_rate": 1.4410743968967733e-05, + "loss": 0.8749, + "step": 4177 + }, + { + "epoch": 0.3741003973361688, + "grad_norm": 0.9546160798847961, + "learning_rate": 1.4408140859874593e-05, + "loss": 0.8654, + "step": 4178 + }, + { + "epoch": 0.3741899378812468, + "grad_norm": 1.0961819100434245, + "learning_rate": 1.440553737998301e-05, + "loss": 0.9058, + "step": 4179 + }, + { + "epoch": 0.3742794784263249, + "grad_norm": 0.9324401068098676, + "learning_rate": 1.4402933529511975e-05, + "loss": 0.8703, + "step": 4180 + }, + { + "epoch": 0.374369018971403, + "grad_norm": 1.0525022025626931, + "learning_rate": 1.4400329308680523e-05, + "loss": 0.834, + "step": 4181 + }, + { + "epoch": 0.37445855951648105, + "grad_norm": 0.9212509687634383, + "learning_rate": 1.4397724717707708e-05, + "loss": 0.7758, + "step": 4182 + }, + { + "epoch": 0.37454810006155914, + "grad_norm": 1.004164125561591, + "learning_rate": 1.439511975681262e-05, + "loss": 0.842, + "step": 4183 + }, + { + "epoch": 0.3746376406066372, + "grad_norm": 0.9400035806256253, + "learning_rate": 1.4392514426214378e-05, + "loss": 0.8799, + "step": 4184 + }, + { + "epoch": 0.37472718115171527, + "grad_norm": 0.9769589016947828, + "learning_rate": 1.438990872613214e-05, + "loss": 0.8279, + "step": 4185 + }, + { + "epoch": 0.3748167216967933, + "grad_norm": 0.9290654956864182, + "learning_rate": 1.4387302656785084e-05, + "loss": 0.8184, + "step": 4186 + }, + { + "epoch": 0.3749062622418714, + "grad_norm": 1.0151282341113241, + "learning_rate": 1.4384696218392425e-05, + "loss": 0.8779, + "step": 4187 + }, + { + "epoch": 0.37499580278694944, + "grad_norm": 0.9970904254477098, + "learning_rate": 1.438208941117341e-05, + "loss": 0.8706, + "step": 4188 + }, + { + "epoch": 0.37508534333202753, + "grad_norm": 0.9195544511661152, + "learning_rate": 1.4379482235347312e-05, + "loss": 0.8349, + "step": 4189 + }, + { + "epoch": 0.3751748838771056, + "grad_norm": 0.977908981386023, + "learning_rate": 1.437687469113344e-05, + "loss": 0.8228, + "step": 4190 + }, + { + "epoch": 0.37526442442218366, + "grad_norm": 0.930415413540987, + "learning_rate": 1.4374266778751134e-05, + "loss": 0.8446, + "step": 4191 + }, + { + "epoch": 0.37535396496726176, + "grad_norm": 0.9037742540913861, + "learning_rate": 1.4371658498419758e-05, + "loss": 0.8759, + "step": 4192 + }, + { + "epoch": 0.3754435055123398, + "grad_norm": 0.9982318479667434, + "learning_rate": 1.4369049850358717e-05, + "loss": 0.8026, + "step": 4193 + }, + { + "epoch": 0.3755330460574179, + "grad_norm": 1.0936746032381797, + "learning_rate": 1.4366440834787439e-05, + "loss": 0.8281, + "step": 4194 + }, + { + "epoch": 0.3756225866024959, + "grad_norm": 0.9269404334097506, + "learning_rate": 1.4363831451925387e-05, + "loss": 0.8297, + "step": 4195 + }, + { + "epoch": 0.375712127147574, + "grad_norm": 0.8942739386051966, + "learning_rate": 1.4361221701992055e-05, + "loss": 0.8756, + "step": 4196 + }, + { + "epoch": 0.37580166769265205, + "grad_norm": 0.9713827048368489, + "learning_rate": 1.4358611585206962e-05, + "loss": 0.856, + "step": 4197 + }, + { + "epoch": 0.37589120823773015, + "grad_norm": 1.0547917897259143, + "learning_rate": 1.435600110178967e-05, + "loss": 0.9057, + "step": 4198 + }, + { + "epoch": 0.37598074878280824, + "grad_norm": 0.9848118630679092, + "learning_rate": 1.4353390251959759e-05, + "loss": 0.8958, + "step": 4199 + }, + { + "epoch": 0.3760702893278863, + "grad_norm": 0.9233538786336366, + "learning_rate": 1.4350779035936846e-05, + "loss": 0.9064, + "step": 4200 + }, + { + "epoch": 0.37615982987296437, + "grad_norm": 0.9259714612322825, + "learning_rate": 1.4348167453940578e-05, + "loss": 0.8523, + "step": 4201 + }, + { + "epoch": 0.3762493704180424, + "grad_norm": 1.182028723436946, + "learning_rate": 1.4345555506190634e-05, + "loss": 0.8682, + "step": 4202 + }, + { + "epoch": 0.3763389109631205, + "grad_norm": 1.203874149980032, + "learning_rate": 1.4342943192906721e-05, + "loss": 0.8529, + "step": 4203 + }, + { + "epoch": 0.37642845150819854, + "grad_norm": 0.9676937471865007, + "learning_rate": 1.4340330514308578e-05, + "loss": 0.8512, + "step": 4204 + }, + { + "epoch": 0.37651799205327663, + "grad_norm": 0.8816738701483038, + "learning_rate": 1.4337717470615978e-05, + "loss": 0.8653, + "step": 4205 + }, + { + "epoch": 0.37660753259835467, + "grad_norm": 0.9088213012625905, + "learning_rate": 1.4335104062048721e-05, + "loss": 0.8325, + "step": 4206 + }, + { + "epoch": 0.37669707314343276, + "grad_norm": 0.9437175177991065, + "learning_rate": 1.4332490288826632e-05, + "loss": 0.856, + "step": 4207 + }, + { + "epoch": 0.37678661368851085, + "grad_norm": 0.986517210753926, + "learning_rate": 1.4329876151169581e-05, + "loss": 0.8201, + "step": 4208 + }, + { + "epoch": 0.3768761542335889, + "grad_norm": 1.0603461499648112, + "learning_rate": 1.4327261649297462e-05, + "loss": 0.9224, + "step": 4209 + }, + { + "epoch": 0.376965694778667, + "grad_norm": 1.0633569121240445, + "learning_rate": 1.432464678343019e-05, + "loss": 0.8447, + "step": 4210 + }, + { + "epoch": 0.377055235323745, + "grad_norm": 0.9316599917294316, + "learning_rate": 1.4322031553787721e-05, + "loss": 0.8794, + "step": 4211 + }, + { + "epoch": 0.3771447758688231, + "grad_norm": 1.0053573139515422, + "learning_rate": 1.4319415960590046e-05, + "loss": 0.7921, + "step": 4212 + }, + { + "epoch": 0.37723431641390115, + "grad_norm": 1.0106457799594875, + "learning_rate": 1.4316800004057174e-05, + "loss": 0.8578, + "step": 4213 + }, + { + "epoch": 0.37732385695897924, + "grad_norm": 0.9180942866481836, + "learning_rate": 1.4314183684409155e-05, + "loss": 0.8971, + "step": 4214 + }, + { + "epoch": 0.3774133975040573, + "grad_norm": 0.9998943279127191, + "learning_rate": 1.4311567001866063e-05, + "loss": 0.8665, + "step": 4215 + }, + { + "epoch": 0.3775029380491354, + "grad_norm": 0.929882648243161, + "learning_rate": 1.4308949956648005e-05, + "loss": 0.8952, + "step": 4216 + }, + { + "epoch": 0.37759247859421347, + "grad_norm": 1.2465203944895376, + "learning_rate": 1.4306332548975114e-05, + "loss": 0.8817, + "step": 4217 + }, + { + "epoch": 0.3776820191392915, + "grad_norm": 0.9137013259222495, + "learning_rate": 1.4303714779067566e-05, + "loss": 0.8356, + "step": 4218 + }, + { + "epoch": 0.3777715596843696, + "grad_norm": 0.9364230560584578, + "learning_rate": 1.4301096647145554e-05, + "loss": 0.8809, + "step": 4219 + }, + { + "epoch": 0.37786110022944763, + "grad_norm": 0.9140623262134444, + "learning_rate": 1.4298478153429307e-05, + "loss": 0.8144, + "step": 4220 + }, + { + "epoch": 0.3779506407745257, + "grad_norm": 0.8458572510169693, + "learning_rate": 1.4295859298139088e-05, + "loss": 0.795, + "step": 4221 + }, + { + "epoch": 0.37804018131960376, + "grad_norm": 0.9205956467596355, + "learning_rate": 1.4293240081495181e-05, + "loss": 0.8438, + "step": 4222 + }, + { + "epoch": 0.37812972186468186, + "grad_norm": 0.9087354375870077, + "learning_rate": 1.4290620503717912e-05, + "loss": 0.8595, + "step": 4223 + }, + { + "epoch": 0.3782192624097599, + "grad_norm": 0.9854147362150998, + "learning_rate": 1.4288000565027625e-05, + "loss": 0.8169, + "step": 4224 + }, + { + "epoch": 0.378308802954838, + "grad_norm": 0.9424113846040778, + "learning_rate": 1.4285380265644703e-05, + "loss": 0.8106, + "step": 4225 + }, + { + "epoch": 0.3783983434999161, + "grad_norm": 0.9277631633750724, + "learning_rate": 1.4282759605789562e-05, + "loss": 0.8629, + "step": 4226 + }, + { + "epoch": 0.3784878840449941, + "grad_norm": 0.9452038411119786, + "learning_rate": 1.4280138585682637e-05, + "loss": 0.8574, + "step": 4227 + }, + { + "epoch": 0.3785774245900722, + "grad_norm": 1.0633011122398508, + "learning_rate": 1.42775172055444e-05, + "loss": 0.8251, + "step": 4228 + }, + { + "epoch": 0.37866696513515025, + "grad_norm": 1.0455673398406378, + "learning_rate": 1.4274895465595357e-05, + "loss": 0.943, + "step": 4229 + }, + { + "epoch": 0.37875650568022834, + "grad_norm": 0.8950580181599327, + "learning_rate": 1.4272273366056037e-05, + "loss": 0.87, + "step": 4230 + }, + { + "epoch": 0.3788460462253064, + "grad_norm": 0.9961738402803761, + "learning_rate": 1.4269650907147006e-05, + "loss": 0.842, + "step": 4231 + }, + { + "epoch": 0.37893558677038447, + "grad_norm": 0.9869635039736778, + "learning_rate": 1.4267028089088853e-05, + "loss": 0.8965, + "step": 4232 + }, + { + "epoch": 0.3790251273154625, + "grad_norm": 1.057067285420222, + "learning_rate": 1.4264404912102204e-05, + "loss": 0.8274, + "step": 4233 + }, + { + "epoch": 0.3791146678605406, + "grad_norm": 0.9973396331360694, + "learning_rate": 1.4261781376407704e-05, + "loss": 0.8574, + "step": 4234 + }, + { + "epoch": 0.3792042084056187, + "grad_norm": 0.9827946251791934, + "learning_rate": 1.4259157482226046e-05, + "loss": 0.9084, + "step": 4235 + }, + { + "epoch": 0.37929374895069673, + "grad_norm": 0.9374688859696028, + "learning_rate": 1.4256533229777943e-05, + "loss": 0.8723, + "step": 4236 + }, + { + "epoch": 0.3793832894957748, + "grad_norm": 1.0867846742484102, + "learning_rate": 1.4253908619284134e-05, + "loss": 0.9099, + "step": 4237 + }, + { + "epoch": 0.37947283004085286, + "grad_norm": 1.0924294421049032, + "learning_rate": 1.4251283650965388e-05, + "loss": 0.8466, + "step": 4238 + }, + { + "epoch": 0.37956237058593095, + "grad_norm": 1.2073962546243577, + "learning_rate": 1.4248658325042524e-05, + "loss": 0.8249, + "step": 4239 + }, + { + "epoch": 0.379651911131009, + "grad_norm": 0.9163763834459361, + "learning_rate": 1.4246032641736362e-05, + "loss": 0.8104, + "step": 4240 + }, + { + "epoch": 0.3797414516760871, + "grad_norm": 1.0138836305492107, + "learning_rate": 1.4243406601267769e-05, + "loss": 0.8611, + "step": 4241 + }, + { + "epoch": 0.3798309922211651, + "grad_norm": 0.9723552202197642, + "learning_rate": 1.4240780203857645e-05, + "loss": 0.8938, + "step": 4242 + }, + { + "epoch": 0.3799205327662432, + "grad_norm": 0.9205623845181184, + "learning_rate": 1.4238153449726909e-05, + "loss": 0.8354, + "step": 4243 + }, + { + "epoch": 0.3800100733113213, + "grad_norm": 0.9622707725132664, + "learning_rate": 1.4235526339096515e-05, + "loss": 0.7925, + "step": 4244 + }, + { + "epoch": 0.38009961385639934, + "grad_norm": 1.0785892261987198, + "learning_rate": 1.4232898872187446e-05, + "loss": 0.8457, + "step": 4245 + }, + { + "epoch": 0.38018915440147744, + "grad_norm": 0.9164650095794956, + "learning_rate": 1.423027104922072e-05, + "loss": 0.7852, + "step": 4246 + }, + { + "epoch": 0.3802786949465555, + "grad_norm": 0.9069031040102574, + "learning_rate": 1.4227642870417374e-05, + "loss": 0.8368, + "step": 4247 + }, + { + "epoch": 0.38036823549163357, + "grad_norm": 0.9070925847169027, + "learning_rate": 1.4225014335998492e-05, + "loss": 0.8552, + "step": 4248 + }, + { + "epoch": 0.3804577760367116, + "grad_norm": 0.8698162732092911, + "learning_rate": 1.422238544618517e-05, + "loss": 0.8432, + "step": 4249 + }, + { + "epoch": 0.3805473165817897, + "grad_norm": 1.2142724803712692, + "learning_rate": 1.4219756201198545e-05, + "loss": 0.8716, + "step": 4250 + }, + { + "epoch": 0.38063685712686773, + "grad_norm": 0.8889037302068833, + "learning_rate": 1.4217126601259776e-05, + "loss": 0.8465, + "step": 4251 + }, + { + "epoch": 0.3807263976719458, + "grad_norm": 0.9592370205778548, + "learning_rate": 1.4214496646590061e-05, + "loss": 0.8137, + "step": 4252 + }, + { + "epoch": 0.3808159382170239, + "grad_norm": 1.305559081491289, + "learning_rate": 1.4211866337410625e-05, + "loss": 0.8822, + "step": 4253 + }, + { + "epoch": 0.38090547876210196, + "grad_norm": 0.9720683973384823, + "learning_rate": 1.4209235673942713e-05, + "loss": 0.8732, + "step": 4254 + }, + { + "epoch": 0.38099501930718005, + "grad_norm": 0.9324441928406956, + "learning_rate": 1.4206604656407616e-05, + "loss": 0.831, + "step": 4255 + }, + { + "epoch": 0.3810845598522581, + "grad_norm": 0.8102839926839986, + "learning_rate": 1.4203973285026642e-05, + "loss": 0.8386, + "step": 4256 + }, + { + "epoch": 0.3811741003973362, + "grad_norm": 0.8438876096737119, + "learning_rate": 1.4201341560021135e-05, + "loss": 0.8513, + "step": 4257 + }, + { + "epoch": 0.3812636409424142, + "grad_norm": 0.9405831480446842, + "learning_rate": 1.419870948161247e-05, + "loss": 0.8247, + "step": 4258 + }, + { + "epoch": 0.3813531814874923, + "grad_norm": 0.9256323930915015, + "learning_rate": 1.419607705002204e-05, + "loss": 0.8352, + "step": 4259 + }, + { + "epoch": 0.38144272203257035, + "grad_norm": 0.8993235365135677, + "learning_rate": 1.4193444265471285e-05, + "loss": 0.8969, + "step": 4260 + }, + { + "epoch": 0.38153226257764844, + "grad_norm": 1.0203939070077361, + "learning_rate": 1.4190811128181665e-05, + "loss": 0.8908, + "step": 4261 + }, + { + "epoch": 0.38162180312272653, + "grad_norm": 0.8867518837972675, + "learning_rate": 1.418817763837467e-05, + "loss": 0.8217, + "step": 4262 + }, + { + "epoch": 0.38171134366780457, + "grad_norm": 0.9237608056118288, + "learning_rate": 1.4185543796271819e-05, + "loss": 0.8439, + "step": 4263 + }, + { + "epoch": 0.38180088421288266, + "grad_norm": 0.9473744262718337, + "learning_rate": 1.4182909602094664e-05, + "loss": 0.8839, + "step": 4264 + }, + { + "epoch": 0.3818904247579607, + "grad_norm": 0.8690428624385834, + "learning_rate": 1.418027505606478e-05, + "loss": 0.8559, + "step": 4265 + }, + { + "epoch": 0.3819799653030388, + "grad_norm": 1.012377858570929, + "learning_rate": 1.4177640158403785e-05, + "loss": 0.8633, + "step": 4266 + }, + { + "epoch": 0.38206950584811683, + "grad_norm": 0.9725345876329412, + "learning_rate": 1.4175004909333311e-05, + "loss": 0.8827, + "step": 4267 + }, + { + "epoch": 0.3821590463931949, + "grad_norm": 1.1259074248593617, + "learning_rate": 1.417236930907503e-05, + "loss": 0.811, + "step": 4268 + }, + { + "epoch": 0.38224858693827296, + "grad_norm": 0.9520156065350955, + "learning_rate": 1.4169733357850642e-05, + "loss": 0.8008, + "step": 4269 + }, + { + "epoch": 0.38233812748335105, + "grad_norm": 0.9759065697207279, + "learning_rate": 1.416709705588187e-05, + "loss": 0.8191, + "step": 4270 + }, + { + "epoch": 0.38242766802842915, + "grad_norm": 0.9342913048013438, + "learning_rate": 1.4164460403390468e-05, + "loss": 0.8442, + "step": 4271 + }, + { + "epoch": 0.3825172085735072, + "grad_norm": 0.9261386565299685, + "learning_rate": 1.4161823400598234e-05, + "loss": 0.8553, + "step": 4272 + }, + { + "epoch": 0.3826067491185853, + "grad_norm": 1.0639767582168744, + "learning_rate": 1.4159186047726976e-05, + "loss": 0.9142, + "step": 4273 + }, + { + "epoch": 0.3826962896636633, + "grad_norm": 1.072377580166384, + "learning_rate": 1.4156548344998543e-05, + "loss": 0.8776, + "step": 4274 + }, + { + "epoch": 0.3827858302087414, + "grad_norm": 0.8688137771209221, + "learning_rate": 1.4153910292634802e-05, + "loss": 0.8131, + "step": 4275 + }, + { + "epoch": 0.38287537075381944, + "grad_norm": 0.933743373478712, + "learning_rate": 1.415127189085767e-05, + "loss": 0.9066, + "step": 4276 + }, + { + "epoch": 0.38296491129889754, + "grad_norm": 1.106902207972974, + "learning_rate": 1.4148633139889069e-05, + "loss": 0.8045, + "step": 4277 + }, + { + "epoch": 0.3830544518439756, + "grad_norm": 0.8789845383092317, + "learning_rate": 1.4145994039950971e-05, + "loss": 0.846, + "step": 4278 + }, + { + "epoch": 0.38314399238905367, + "grad_norm": 0.9320178752378488, + "learning_rate": 1.4143354591265365e-05, + "loss": 0.8261, + "step": 4279 + }, + { + "epoch": 0.38323353293413176, + "grad_norm": 0.8865757357567181, + "learning_rate": 1.4140714794054274e-05, + "loss": 0.8206, + "step": 4280 + }, + { + "epoch": 0.3833230734792098, + "grad_norm": 0.8553551883354696, + "learning_rate": 1.4138074648539744e-05, + "loss": 0.821, + "step": 4281 + }, + { + "epoch": 0.3834126140242879, + "grad_norm": 0.9559577621983442, + "learning_rate": 1.4135434154943861e-05, + "loss": 0.8635, + "step": 4282 + }, + { + "epoch": 0.3835021545693659, + "grad_norm": 1.095410195525319, + "learning_rate": 1.4132793313488732e-05, + "loss": 0.7741, + "step": 4283 + }, + { + "epoch": 0.383591695114444, + "grad_norm": 0.8698858960107688, + "learning_rate": 1.41301521243965e-05, + "loss": 0.7575, + "step": 4284 + }, + { + "epoch": 0.38368123565952206, + "grad_norm": 0.880629716763362, + "learning_rate": 1.4127510587889328e-05, + "loss": 0.8253, + "step": 4285 + }, + { + "epoch": 0.38377077620460015, + "grad_norm": 0.896855197257339, + "learning_rate": 1.4124868704189416e-05, + "loss": 0.8738, + "step": 4286 + }, + { + "epoch": 0.3838603167496782, + "grad_norm": 0.8536335908044614, + "learning_rate": 1.4122226473518991e-05, + "loss": 0.847, + "step": 4287 + }, + { + "epoch": 0.3839498572947563, + "grad_norm": 1.1513467011902712, + "learning_rate": 1.4119583896100309e-05, + "loss": 0.818, + "step": 4288 + }, + { + "epoch": 0.3840393978398344, + "grad_norm": 0.9732392592290227, + "learning_rate": 1.4116940972155651e-05, + "loss": 0.8287, + "step": 4289 + }, + { + "epoch": 0.3841289383849124, + "grad_norm": 0.9428344607202426, + "learning_rate": 1.4114297701907336e-05, + "loss": 0.9013, + "step": 4290 + }, + { + "epoch": 0.3842184789299905, + "grad_norm": 1.001595853243546, + "learning_rate": 1.4111654085577709e-05, + "loss": 0.8271, + "step": 4291 + }, + { + "epoch": 0.38430801947506854, + "grad_norm": 1.0327373690973063, + "learning_rate": 1.4109010123389133e-05, + "loss": 0.8524, + "step": 4292 + }, + { + "epoch": 0.38439756002014663, + "grad_norm": 0.872689374391715, + "learning_rate": 1.410636581556402e-05, + "loss": 0.826, + "step": 4293 + }, + { + "epoch": 0.38448710056522467, + "grad_norm": 0.9405576608820454, + "learning_rate": 1.4103721162324795e-05, + "loss": 0.8167, + "step": 4294 + }, + { + "epoch": 0.38457664111030276, + "grad_norm": 0.958985046725877, + "learning_rate": 1.4101076163893915e-05, + "loss": 0.8764, + "step": 4295 + }, + { + "epoch": 0.3846661816553808, + "grad_norm": 1.071263056616227, + "learning_rate": 1.4098430820493878e-05, + "loss": 0.8892, + "step": 4296 + }, + { + "epoch": 0.3847557222004589, + "grad_norm": 0.9300828484513695, + "learning_rate": 1.409578513234719e-05, + "loss": 0.8696, + "step": 4297 + }, + { + "epoch": 0.384845262745537, + "grad_norm": 0.9437021221337074, + "learning_rate": 1.4093139099676407e-05, + "loss": 0.8255, + "step": 4298 + }, + { + "epoch": 0.384934803290615, + "grad_norm": 0.9960229291129784, + "learning_rate": 1.4090492722704103e-05, + "loss": 0.8686, + "step": 4299 + }, + { + "epoch": 0.3850243438356931, + "grad_norm": 0.8979512275750243, + "learning_rate": 1.4087846001652878e-05, + "loss": 0.8228, + "step": 4300 + }, + { + "epoch": 0.38511388438077115, + "grad_norm": 0.9178256480161378, + "learning_rate": 1.4085198936745368e-05, + "loss": 0.864, + "step": 4301 + }, + { + "epoch": 0.38520342492584925, + "grad_norm": 1.0044870989634411, + "learning_rate": 1.4082551528204237e-05, + "loss": 0.8065, + "step": 4302 + }, + { + "epoch": 0.3852929654709273, + "grad_norm": 0.9617772172822552, + "learning_rate": 1.4079903776252178e-05, + "loss": 0.8585, + "step": 4303 + }, + { + "epoch": 0.3853825060160054, + "grad_norm": 0.9673509706484636, + "learning_rate": 1.4077255681111905e-05, + "loss": 0.9104, + "step": 4304 + }, + { + "epoch": 0.3854720465610834, + "grad_norm": 0.9823270335554953, + "learning_rate": 1.4074607243006171e-05, + "loss": 0.9083, + "step": 4305 + }, + { + "epoch": 0.3855615871061615, + "grad_norm": 0.9333533835196084, + "learning_rate": 1.4071958462157756e-05, + "loss": 0.8777, + "step": 4306 + }, + { + "epoch": 0.3856511276512396, + "grad_norm": 0.9197493221909131, + "learning_rate": 1.4069309338789461e-05, + "loss": 0.8118, + "step": 4307 + }, + { + "epoch": 0.38574066819631764, + "grad_norm": 0.9412536228405011, + "learning_rate": 1.4066659873124127e-05, + "loss": 0.832, + "step": 4308 + }, + { + "epoch": 0.38583020874139573, + "grad_norm": 0.8900960298494255, + "learning_rate": 1.4064010065384616e-05, + "loss": 0.8415, + "step": 4309 + }, + { + "epoch": 0.38591974928647377, + "grad_norm": 0.9574022279263648, + "learning_rate": 1.4061359915793822e-05, + "loss": 0.9219, + "step": 4310 + }, + { + "epoch": 0.38600928983155186, + "grad_norm": 0.8803996126541075, + "learning_rate": 1.4058709424574668e-05, + "loss": 0.9162, + "step": 4311 + }, + { + "epoch": 0.3860988303766299, + "grad_norm": 0.9820062178464307, + "learning_rate": 1.4056058591950101e-05, + "loss": 0.8322, + "step": 4312 + }, + { + "epoch": 0.386188370921708, + "grad_norm": 1.0867289654869534, + "learning_rate": 1.4053407418143104e-05, + "loss": 0.8483, + "step": 4313 + }, + { + "epoch": 0.38627791146678603, + "grad_norm": 1.0406821788831242, + "learning_rate": 1.4050755903376682e-05, + "loss": 0.8885, + "step": 4314 + }, + { + "epoch": 0.3863674520118641, + "grad_norm": 0.8786489512235386, + "learning_rate": 1.4048104047873876e-05, + "loss": 0.8532, + "step": 4315 + }, + { + "epoch": 0.3864569925569422, + "grad_norm": 0.9068648804136524, + "learning_rate": 1.4045451851857749e-05, + "loss": 0.8612, + "step": 4316 + }, + { + "epoch": 0.38654653310202025, + "grad_norm": 0.9020771941862551, + "learning_rate": 1.4042799315551394e-05, + "loss": 0.8507, + "step": 4317 + }, + { + "epoch": 0.38663607364709834, + "grad_norm": 0.8767583290432911, + "learning_rate": 1.4040146439177937e-05, + "loss": 0.8406, + "step": 4318 + }, + { + "epoch": 0.3867256141921764, + "grad_norm": 1.0022282165748737, + "learning_rate": 1.4037493222960525e-05, + "loss": 0.91, + "step": 4319 + }, + { + "epoch": 0.3868151547372545, + "grad_norm": 0.9041341302018024, + "learning_rate": 1.403483966712234e-05, + "loss": 0.8592, + "step": 4320 + }, + { + "epoch": 0.3869046952823325, + "grad_norm": 0.9593574254787363, + "learning_rate": 1.4032185771886593e-05, + "loss": 0.8579, + "step": 4321 + }, + { + "epoch": 0.3869942358274106, + "grad_norm": 0.9157039629303706, + "learning_rate": 1.4029531537476515e-05, + "loss": 0.8451, + "step": 4322 + }, + { + "epoch": 0.38708377637248864, + "grad_norm": 0.9400030550174615, + "learning_rate": 1.402687696411538e-05, + "loss": 0.9032, + "step": 4323 + }, + { + "epoch": 0.38717331691756673, + "grad_norm": 0.9987093123835726, + "learning_rate": 1.4024222052026473e-05, + "loss": 0.7824, + "step": 4324 + }, + { + "epoch": 0.3872628574626448, + "grad_norm": 0.8485699986713621, + "learning_rate": 1.402156680143312e-05, + "loss": 0.7973, + "step": 4325 + }, + { + "epoch": 0.38735239800772286, + "grad_norm": 1.02578180214162, + "learning_rate": 1.4018911212558677e-05, + "loss": 0.846, + "step": 4326 + }, + { + "epoch": 0.38744193855280096, + "grad_norm": 0.950263862498733, + "learning_rate": 1.4016255285626517e-05, + "loss": 0.8878, + "step": 4327 + }, + { + "epoch": 0.387531479097879, + "grad_norm": 0.916345684872174, + "learning_rate": 1.4013599020860046e-05, + "loss": 0.8389, + "step": 4328 + }, + { + "epoch": 0.3876210196429571, + "grad_norm": 1.0249819283264308, + "learning_rate": 1.401094241848271e-05, + "loss": 0.8613, + "step": 4329 + }, + { + "epoch": 0.3877105601880351, + "grad_norm": 0.8885072102604518, + "learning_rate": 1.4008285478717967e-05, + "loss": 0.8822, + "step": 4330 + }, + { + "epoch": 0.3878001007331132, + "grad_norm": 0.9633357056027243, + "learning_rate": 1.400562820178931e-05, + "loss": 0.8726, + "step": 4331 + }, + { + "epoch": 0.38788964127819126, + "grad_norm": 1.2694737301866863, + "learning_rate": 1.4002970587920264e-05, + "loss": 0.824, + "step": 4332 + }, + { + "epoch": 0.38797918182326935, + "grad_norm": 0.9316470266952813, + "learning_rate": 1.4000312637334376e-05, + "loss": 0.8456, + "step": 4333 + }, + { + "epoch": 0.38806872236834744, + "grad_norm": 0.981039211722298, + "learning_rate": 1.3997654350255223e-05, + "loss": 0.8727, + "step": 4334 + }, + { + "epoch": 0.3881582629134255, + "grad_norm": 1.106531448032237, + "learning_rate": 1.3994995726906415e-05, + "loss": 0.8553, + "step": 4335 + }, + { + "epoch": 0.38824780345850357, + "grad_norm": 0.9499351717802188, + "learning_rate": 1.3992336767511585e-05, + "loss": 0.8058, + "step": 4336 + }, + { + "epoch": 0.3883373440035816, + "grad_norm": 0.8974496379060156, + "learning_rate": 1.3989677472294397e-05, + "loss": 0.8684, + "step": 4337 + }, + { + "epoch": 0.3884268845486597, + "grad_norm": 0.9797572117318515, + "learning_rate": 1.3987017841478539e-05, + "loss": 0.8323, + "step": 4338 + }, + { + "epoch": 0.38851642509373774, + "grad_norm": 1.0102729822760879, + "learning_rate": 1.398435787528773e-05, + "loss": 0.9084, + "step": 4339 + }, + { + "epoch": 0.38860596563881583, + "grad_norm": 0.9183288231872694, + "learning_rate": 1.3981697573945726e-05, + "loss": 0.7844, + "step": 4340 + }, + { + "epoch": 0.38869550618389387, + "grad_norm": 0.9769498120870611, + "learning_rate": 1.3979036937676294e-05, + "loss": 0.8098, + "step": 4341 + }, + { + "epoch": 0.38878504672897196, + "grad_norm": 1.0167669718911116, + "learning_rate": 1.3976375966703241e-05, + "loss": 0.787, + "step": 4342 + }, + { + "epoch": 0.38887458727405005, + "grad_norm": 0.9812453696310841, + "learning_rate": 1.3973714661250402e-05, + "loss": 0.8939, + "step": 4343 + }, + { + "epoch": 0.3889641278191281, + "grad_norm": 0.916553348073219, + "learning_rate": 1.3971053021541634e-05, + "loss": 0.8382, + "step": 4344 + }, + { + "epoch": 0.3890536683642062, + "grad_norm": 1.031731947140006, + "learning_rate": 1.3968391047800827e-05, + "loss": 0.8513, + "step": 4345 + }, + { + "epoch": 0.3891432089092842, + "grad_norm": 0.8753378447057569, + "learning_rate": 1.3965728740251894e-05, + "loss": 0.7696, + "step": 4346 + }, + { + "epoch": 0.3892327494543623, + "grad_norm": 0.9375260404746948, + "learning_rate": 1.3963066099118785e-05, + "loss": 0.8099, + "step": 4347 + }, + { + "epoch": 0.38932228999944035, + "grad_norm": 1.1677852058642593, + "learning_rate": 1.396040312462547e-05, + "loss": 0.8603, + "step": 4348 + }, + { + "epoch": 0.38941183054451844, + "grad_norm": 1.0118260464213775, + "learning_rate": 1.3957739816995948e-05, + "loss": 0.8508, + "step": 4349 + }, + { + "epoch": 0.3895013710895965, + "grad_norm": 0.9669125945422604, + "learning_rate": 1.395507617645425e-05, + "loss": 0.8371, + "step": 4350 + }, + { + "epoch": 0.3895909116346746, + "grad_norm": 1.08540787302438, + "learning_rate": 1.3952412203224437e-05, + "loss": 0.846, + "step": 4351 + }, + { + "epoch": 0.38968045217975267, + "grad_norm": 0.8946888088373711, + "learning_rate": 1.3949747897530583e-05, + "loss": 0.8598, + "step": 4352 + }, + { + "epoch": 0.3897699927248307, + "grad_norm": 0.9139977317401248, + "learning_rate": 1.3947083259596812e-05, + "loss": 0.8429, + "step": 4353 + }, + { + "epoch": 0.3898595332699088, + "grad_norm": 1.11661369917112, + "learning_rate": 1.3944418289647257e-05, + "loss": 0.8391, + "step": 4354 + }, + { + "epoch": 0.38994907381498684, + "grad_norm": 1.0448964070492612, + "learning_rate": 1.3941752987906088e-05, + "loss": 0.8582, + "step": 4355 + }, + { + "epoch": 0.39003861436006493, + "grad_norm": 0.9607039448516149, + "learning_rate": 1.3939087354597507e-05, + "loss": 0.8943, + "step": 4356 + }, + { + "epoch": 0.39012815490514297, + "grad_norm": 2.316024328723829, + "learning_rate": 1.3936421389945729e-05, + "loss": 0.903, + "step": 4357 + }, + { + "epoch": 0.39021769545022106, + "grad_norm": 1.0268005530301259, + "learning_rate": 1.3933755094175013e-05, + "loss": 0.8914, + "step": 4358 + }, + { + "epoch": 0.3903072359952991, + "grad_norm": 0.866225061105971, + "learning_rate": 1.3931088467509639e-05, + "loss": 0.7966, + "step": 4359 + }, + { + "epoch": 0.3903967765403772, + "grad_norm": 0.9234187978297268, + "learning_rate": 1.3928421510173913e-05, + "loss": 0.8326, + "step": 4360 + }, + { + "epoch": 0.3904863170854553, + "grad_norm": 0.9186714463958888, + "learning_rate": 1.3925754222392167e-05, + "loss": 0.822, + "step": 4361 + }, + { + "epoch": 0.3905758576305333, + "grad_norm": 0.8825929864338079, + "learning_rate": 1.3923086604388774e-05, + "loss": 0.8995, + "step": 4362 + }, + { + "epoch": 0.3906653981756114, + "grad_norm": 0.9601314627873958, + "learning_rate": 1.3920418656388117e-05, + "loss": 0.8289, + "step": 4363 + }, + { + "epoch": 0.39075493872068945, + "grad_norm": 0.8399128029083268, + "learning_rate": 1.391775037861462e-05, + "loss": 0.813, + "step": 4364 + }, + { + "epoch": 0.39084447926576754, + "grad_norm": 0.9038736268327304, + "learning_rate": 1.3915081771292726e-05, + "loss": 0.8495, + "step": 4365 + }, + { + "epoch": 0.3909340198108456, + "grad_norm": 0.9654302051689361, + "learning_rate": 1.3912412834646914e-05, + "loss": 0.8103, + "step": 4366 + }, + { + "epoch": 0.39102356035592367, + "grad_norm": 0.8875386590279613, + "learning_rate": 1.390974356890168e-05, + "loss": 0.8575, + "step": 4367 + }, + { + "epoch": 0.3911131009010017, + "grad_norm": 0.8735904239846528, + "learning_rate": 1.3907073974281562e-05, + "loss": 0.7866, + "step": 4368 + }, + { + "epoch": 0.3912026414460798, + "grad_norm": 0.9361460247292266, + "learning_rate": 1.390440405101111e-05, + "loss": 0.8428, + "step": 4369 + }, + { + "epoch": 0.3912921819911579, + "grad_norm": 0.9201267894732166, + "learning_rate": 1.3901733799314916e-05, + "loss": 0.8224, + "step": 4370 + }, + { + "epoch": 0.39138172253623593, + "grad_norm": 0.9690148023612849, + "learning_rate": 1.3899063219417586e-05, + "loss": 0.87, + "step": 4371 + }, + { + "epoch": 0.391471263081314, + "grad_norm": 1.0052688165934114, + "learning_rate": 1.3896392311543766e-05, + "loss": 0.8471, + "step": 4372 + }, + { + "epoch": 0.39156080362639206, + "grad_norm": 0.9096339062435472, + "learning_rate": 1.3893721075918121e-05, + "loss": 0.8962, + "step": 4373 + }, + { + "epoch": 0.39165034417147015, + "grad_norm": 0.9481615439397594, + "learning_rate": 1.3891049512765347e-05, + "loss": 0.8133, + "step": 4374 + }, + { + "epoch": 0.3917398847165482, + "grad_norm": 1.0622202445862254, + "learning_rate": 1.3888377622310173e-05, + "loss": 0.8691, + "step": 4375 + }, + { + "epoch": 0.3918294252616263, + "grad_norm": 0.9104192920270602, + "learning_rate": 1.3885705404777334e-05, + "loss": 0.8119, + "step": 4376 + }, + { + "epoch": 0.3919189658067043, + "grad_norm": 1.0730988714446843, + "learning_rate": 1.3883032860391626e-05, + "loss": 0.8347, + "step": 4377 + }, + { + "epoch": 0.3920085063517824, + "grad_norm": 0.8796530338796501, + "learning_rate": 1.3880359989377847e-05, + "loss": 0.8223, + "step": 4378 + }, + { + "epoch": 0.3920980468968605, + "grad_norm": 0.9231030151116769, + "learning_rate": 1.387768679196083e-05, + "loss": 0.8167, + "step": 4379 + }, + { + "epoch": 0.39218758744193855, + "grad_norm": 0.9894131240123671, + "learning_rate": 1.3875013268365436e-05, + "loss": 0.8041, + "step": 4380 + }, + { + "epoch": 0.39227712798701664, + "grad_norm": 0.9266938072541895, + "learning_rate": 1.3872339418816553e-05, + "loss": 0.8155, + "step": 4381 + }, + { + "epoch": 0.3923666685320947, + "grad_norm": 0.9612890433504183, + "learning_rate": 1.3869665243539097e-05, + "loss": 0.8742, + "step": 4382 + }, + { + "epoch": 0.39245620907717277, + "grad_norm": 0.8874424793831853, + "learning_rate": 1.3866990742758013e-05, + "loss": 0.8519, + "step": 4383 + }, + { + "epoch": 0.3925457496222508, + "grad_norm": 1.0600835428736393, + "learning_rate": 1.3864315916698266e-05, + "loss": 0.8348, + "step": 4384 + }, + { + "epoch": 0.3926352901673289, + "grad_norm": 1.1778071593422073, + "learning_rate": 1.3861640765584857e-05, + "loss": 0.84, + "step": 4385 + }, + { + "epoch": 0.39272483071240694, + "grad_norm": 0.9280436112107391, + "learning_rate": 1.3858965289642811e-05, + "loss": 0.829, + "step": 4386 + }, + { + "epoch": 0.39281437125748503, + "grad_norm": 0.889346521185196, + "learning_rate": 1.3856289489097181e-05, + "loss": 0.8652, + "step": 4387 + }, + { + "epoch": 0.3929039118025631, + "grad_norm": 0.9022687799347335, + "learning_rate": 1.3853613364173043e-05, + "loss": 0.8345, + "step": 4388 + }, + { + "epoch": 0.39299345234764116, + "grad_norm": 0.9615885614981415, + "learning_rate": 1.3850936915095512e-05, + "loss": 0.8095, + "step": 4389 + }, + { + "epoch": 0.39308299289271925, + "grad_norm": 0.9280503788569006, + "learning_rate": 1.3848260142089714e-05, + "loss": 0.8492, + "step": 4390 + }, + { + "epoch": 0.3931725334377973, + "grad_norm": 0.9217216270985268, + "learning_rate": 1.384558304538081e-05, + "loss": 0.8331, + "step": 4391 + }, + { + "epoch": 0.3932620739828754, + "grad_norm": 0.957404776947905, + "learning_rate": 1.3842905625193998e-05, + "loss": 0.8187, + "step": 4392 + }, + { + "epoch": 0.3933516145279534, + "grad_norm": 0.8992985649268581, + "learning_rate": 1.3840227881754485e-05, + "loss": 0.8328, + "step": 4393 + }, + { + "epoch": 0.3934411550730315, + "grad_norm": 0.8470041329119131, + "learning_rate": 1.3837549815287514e-05, + "loss": 0.7872, + "step": 4394 + }, + { + "epoch": 0.39353069561810955, + "grad_norm": 0.9601284425157596, + "learning_rate": 1.3834871426018361e-05, + "loss": 0.8098, + "step": 4395 + }, + { + "epoch": 0.39362023616318764, + "grad_norm": 1.0320052277868255, + "learning_rate": 1.3832192714172319e-05, + "loss": 0.9062, + "step": 4396 + }, + { + "epoch": 0.39370977670826574, + "grad_norm": 1.01664736854573, + "learning_rate": 1.3829513679974715e-05, + "loss": 0.8821, + "step": 4397 + }, + { + "epoch": 0.3937993172533438, + "grad_norm": 0.9509103921756694, + "learning_rate": 1.3826834323650899e-05, + "loss": 0.8796, + "step": 4398 + }, + { + "epoch": 0.39388885779842187, + "grad_norm": 0.8759599557938503, + "learning_rate": 1.3824154645426251e-05, + "loss": 0.8722, + "step": 4399 + }, + { + "epoch": 0.3939783983434999, + "grad_norm": 0.9197583012357854, + "learning_rate": 1.3821474645526174e-05, + "loss": 0.8332, + "step": 4400 + }, + { + "epoch": 0.394067938888578, + "grad_norm": 1.234147526389074, + "learning_rate": 1.3818794324176103e-05, + "loss": 0.808, + "step": 4401 + }, + { + "epoch": 0.39415747943365603, + "grad_norm": 0.8734731885833076, + "learning_rate": 1.3816113681601499e-05, + "loss": 0.8576, + "step": 4402 + }, + { + "epoch": 0.3942470199787341, + "grad_norm": 0.9597112028837594, + "learning_rate": 1.3813432718027849e-05, + "loss": 0.8413, + "step": 4403 + }, + { + "epoch": 0.39433656052381216, + "grad_norm": 0.925958937771262, + "learning_rate": 1.3810751433680665e-05, + "loss": 0.8676, + "step": 4404 + }, + { + "epoch": 0.39442610106889026, + "grad_norm": 0.9322276327961405, + "learning_rate": 1.3808069828785489e-05, + "loss": 0.8842, + "step": 4405 + }, + { + "epoch": 0.39451564161396835, + "grad_norm": 0.8383103932605624, + "learning_rate": 1.3805387903567885e-05, + "loss": 0.8413, + "step": 4406 + }, + { + "epoch": 0.3946051821590464, + "grad_norm": 0.92133066760104, + "learning_rate": 1.3802705658253452e-05, + "loss": 0.7347, + "step": 4407 + }, + { + "epoch": 0.3946947227041245, + "grad_norm": 0.9135407525122693, + "learning_rate": 1.3800023093067814e-05, + "loss": 0.8004, + "step": 4408 + }, + { + "epoch": 0.3947842632492025, + "grad_norm": 1.0322266056492955, + "learning_rate": 1.3797340208236611e-05, + "loss": 0.9178, + "step": 4409 + }, + { + "epoch": 0.3948738037942806, + "grad_norm": 0.9330819964109333, + "learning_rate": 1.379465700398553e-05, + "loss": 0.8556, + "step": 4410 + }, + { + "epoch": 0.39496334433935865, + "grad_norm": 0.9589600499774461, + "learning_rate": 1.3791973480540265e-05, + "loss": 0.8337, + "step": 4411 + }, + { + "epoch": 0.39505288488443674, + "grad_norm": 0.8145779145985143, + "learning_rate": 1.3789289638126549e-05, + "loss": 0.8886, + "step": 4412 + }, + { + "epoch": 0.3951424254295148, + "grad_norm": 0.9368340917103307, + "learning_rate": 1.3786605476970134e-05, + "loss": 0.8379, + "step": 4413 + }, + { + "epoch": 0.39523196597459287, + "grad_norm": 0.9665018786877776, + "learning_rate": 1.3783920997296809e-05, + "loss": 0.903, + "step": 4414 + }, + { + "epoch": 0.39532150651967096, + "grad_norm": 0.9744554511080462, + "learning_rate": 1.3781236199332377e-05, + "loss": 0.8193, + "step": 4415 + }, + { + "epoch": 0.395411047064749, + "grad_norm": 0.9984648646470298, + "learning_rate": 1.3778551083302683e-05, + "loss": 0.9238, + "step": 4416 + }, + { + "epoch": 0.3955005876098271, + "grad_norm": 1.8587189012509444, + "learning_rate": 1.377586564943358e-05, + "loss": 0.8597, + "step": 4417 + }, + { + "epoch": 0.39559012815490513, + "grad_norm": 0.9820593197200812, + "learning_rate": 1.3773179897950964e-05, + "loss": 0.9142, + "step": 4418 + }, + { + "epoch": 0.3956796686999832, + "grad_norm": 1.0023579986949207, + "learning_rate": 1.3770493829080754e-05, + "loss": 0.8597, + "step": 4419 + }, + { + "epoch": 0.39576920924506126, + "grad_norm": 1.001339650346833, + "learning_rate": 1.3767807443048885e-05, + "loss": 0.8808, + "step": 4420 + }, + { + "epoch": 0.39585874979013935, + "grad_norm": 0.9960995115179302, + "learning_rate": 1.3765120740081332e-05, + "loss": 0.8509, + "step": 4421 + }, + { + "epoch": 0.3959482903352174, + "grad_norm": 0.9416600730312418, + "learning_rate": 1.3762433720404097e-05, + "loss": 0.7846, + "step": 4422 + }, + { + "epoch": 0.3960378308802955, + "grad_norm": 0.9859649192647081, + "learning_rate": 1.3759746384243195e-05, + "loss": 0.8857, + "step": 4423 + }, + { + "epoch": 0.3961273714253736, + "grad_norm": 0.9308342581251277, + "learning_rate": 1.375705873182468e-05, + "loss": 0.8947, + "step": 4424 + }, + { + "epoch": 0.3962169119704516, + "grad_norm": 0.946731604520498, + "learning_rate": 1.3754370763374626e-05, + "loss": 0.762, + "step": 4425 + }, + { + "epoch": 0.3963064525155297, + "grad_norm": 0.9719468692547852, + "learning_rate": 1.375168247911914e-05, + "loss": 0.8205, + "step": 4426 + }, + { + "epoch": 0.39639599306060774, + "grad_norm": 1.0073513431991896, + "learning_rate": 1.374899387928435e-05, + "loss": 0.8699, + "step": 4427 + }, + { + "epoch": 0.39648553360568584, + "grad_norm": 0.9252415956914926, + "learning_rate": 1.3746304964096409e-05, + "loss": 0.8642, + "step": 4428 + }, + { + "epoch": 0.3965750741507639, + "grad_norm": 0.97873111542137, + "learning_rate": 1.3743615733781504e-05, + "loss": 0.8551, + "step": 4429 + }, + { + "epoch": 0.39666461469584197, + "grad_norm": 0.9806292018994187, + "learning_rate": 1.374092618856584e-05, + "loss": 0.8092, + "step": 4430 + }, + { + "epoch": 0.39675415524092, + "grad_norm": 0.9556317038521843, + "learning_rate": 1.3738236328675658e-05, + "loss": 0.9211, + "step": 4431 + }, + { + "epoch": 0.3968436957859981, + "grad_norm": 0.9648291637022697, + "learning_rate": 1.3735546154337218e-05, + "loss": 0.8615, + "step": 4432 + }, + { + "epoch": 0.3969332363310762, + "grad_norm": 1.0397258488292191, + "learning_rate": 1.3732855665776808e-05, + "loss": 0.8947, + "step": 4433 + }, + { + "epoch": 0.3970227768761542, + "grad_norm": 0.9396599887989061, + "learning_rate": 1.3730164863220746e-05, + "loss": 0.8248, + "step": 4434 + }, + { + "epoch": 0.3971123174212323, + "grad_norm": 1.0203642860131545, + "learning_rate": 1.372747374689537e-05, + "loss": 0.8899, + "step": 4435 + }, + { + "epoch": 0.39720185796631036, + "grad_norm": 1.1881706247539423, + "learning_rate": 1.3724782317027046e-05, + "loss": 0.9191, + "step": 4436 + }, + { + "epoch": 0.39729139851138845, + "grad_norm": 1.0388388313209214, + "learning_rate": 1.3722090573842173e-05, + "loss": 0.824, + "step": 4437 + }, + { + "epoch": 0.3973809390564665, + "grad_norm": 0.9065276285889443, + "learning_rate": 1.3719398517567172e-05, + "loss": 0.8877, + "step": 4438 + }, + { + "epoch": 0.3974704796015446, + "grad_norm": 0.8763718611180635, + "learning_rate": 1.3716706148428487e-05, + "loss": 0.8254, + "step": 4439 + }, + { + "epoch": 0.3975600201466226, + "grad_norm": 0.8778965272462631, + "learning_rate": 1.3714013466652592e-05, + "loss": 0.8322, + "step": 4440 + }, + { + "epoch": 0.3976495606917007, + "grad_norm": 0.9922961405589652, + "learning_rate": 1.371132047246599e-05, + "loss": 0.8868, + "step": 4441 + }, + { + "epoch": 0.3977391012367788, + "grad_norm": 0.8849921930041346, + "learning_rate": 1.3708627166095199e-05, + "loss": 0.8582, + "step": 4442 + }, + { + "epoch": 0.39782864178185684, + "grad_norm": 0.93941497167276, + "learning_rate": 1.3705933547766778e-05, + "loss": 0.8467, + "step": 4443 + }, + { + "epoch": 0.39791818232693493, + "grad_norm": 0.9096076321095928, + "learning_rate": 1.3703239617707308e-05, + "loss": 0.8577, + "step": 4444 + }, + { + "epoch": 0.39800772287201297, + "grad_norm": 0.9775998871123823, + "learning_rate": 1.3700545376143381e-05, + "loss": 0.8474, + "step": 4445 + }, + { + "epoch": 0.39809726341709106, + "grad_norm": 0.9346929989107483, + "learning_rate": 1.3697850823301642e-05, + "loss": 0.8315, + "step": 4446 + }, + { + "epoch": 0.3981868039621691, + "grad_norm": 0.9177284749382002, + "learning_rate": 1.369515595940874e-05, + "loss": 0.8688, + "step": 4447 + }, + { + "epoch": 0.3982763445072472, + "grad_norm": 0.9034819967760698, + "learning_rate": 1.3692460784691357e-05, + "loss": 0.8497, + "step": 4448 + }, + { + "epoch": 0.39836588505232523, + "grad_norm": 0.8559289759829627, + "learning_rate": 1.3689765299376212e-05, + "loss": 0.8378, + "step": 4449 + }, + { + "epoch": 0.3984554255974033, + "grad_norm": 0.9252137252384982, + "learning_rate": 1.368706950369003e-05, + "loss": 0.8855, + "step": 4450 + }, + { + "epoch": 0.3985449661424814, + "grad_norm": 0.8905599303696533, + "learning_rate": 1.3684373397859573e-05, + "loss": 0.8159, + "step": 4451 + }, + { + "epoch": 0.39863450668755945, + "grad_norm": 0.9361216357755833, + "learning_rate": 1.368167698211164e-05, + "loss": 0.8894, + "step": 4452 + }, + { + "epoch": 0.39872404723263755, + "grad_norm": 1.1497370561760702, + "learning_rate": 1.3678980256673034e-05, + "loss": 0.8494, + "step": 4453 + }, + { + "epoch": 0.3988135877777156, + "grad_norm": 1.1331748858027035, + "learning_rate": 1.3676283221770595e-05, + "loss": 0.8342, + "step": 4454 + }, + { + "epoch": 0.3989031283227937, + "grad_norm": 0.9742609324623751, + "learning_rate": 1.3673585877631192e-05, + "loss": 0.8908, + "step": 4455 + }, + { + "epoch": 0.3989926688678717, + "grad_norm": 1.0649250636549026, + "learning_rate": 1.3670888224481717e-05, + "loss": 0.7885, + "step": 4456 + }, + { + "epoch": 0.3990822094129498, + "grad_norm": 0.9202688598092882, + "learning_rate": 1.3668190262549085e-05, + "loss": 0.8778, + "step": 4457 + }, + { + "epoch": 0.39917174995802784, + "grad_norm": 0.8926703013115901, + "learning_rate": 1.3665491992060243e-05, + "loss": 0.7983, + "step": 4458 + }, + { + "epoch": 0.39926129050310594, + "grad_norm": 0.9393187929328782, + "learning_rate": 1.3662793413242162e-05, + "loss": 0.8602, + "step": 4459 + }, + { + "epoch": 0.39935083104818403, + "grad_norm": 0.9965123964980215, + "learning_rate": 1.366009452632183e-05, + "loss": 0.8583, + "step": 4460 + }, + { + "epoch": 0.39944037159326207, + "grad_norm": 0.9652940414311767, + "learning_rate": 1.3657395331526277e-05, + "loss": 0.8192, + "step": 4461 + }, + { + "epoch": 0.39952991213834016, + "grad_norm": 1.000579874071736, + "learning_rate": 1.3654695829082547e-05, + "loss": 0.8194, + "step": 4462 + }, + { + "epoch": 0.3996194526834182, + "grad_norm": 0.9214729686800737, + "learning_rate": 1.3651996019217712e-05, + "loss": 0.7846, + "step": 4463 + }, + { + "epoch": 0.3997089932284963, + "grad_norm": 0.964798851799019, + "learning_rate": 1.3649295902158874e-05, + "loss": 0.8574, + "step": 4464 + }, + { + "epoch": 0.3997985337735743, + "grad_norm": 0.9072131773093552, + "learning_rate": 1.3646595478133158e-05, + "loss": 0.8706, + "step": 4465 + }, + { + "epoch": 0.3998880743186524, + "grad_norm": 0.9343619815846401, + "learning_rate": 1.364389474736771e-05, + "loss": 0.8946, + "step": 4466 + }, + { + "epoch": 0.39997761486373046, + "grad_norm": 0.888477664457081, + "learning_rate": 1.364119371008971e-05, + "loss": 0.8321, + "step": 4467 + }, + { + "epoch": 0.40006715540880855, + "grad_norm": 1.1271464424441613, + "learning_rate": 1.3638492366526364e-05, + "loss": 0.8734, + "step": 4468 + }, + { + "epoch": 0.40015669595388664, + "grad_norm": 0.9485863184681835, + "learning_rate": 1.3635790716904894e-05, + "loss": 0.8738, + "step": 4469 + }, + { + "epoch": 0.4002462364989647, + "grad_norm": 1.0452633444698731, + "learning_rate": 1.3633088761452557e-05, + "loss": 0.9401, + "step": 4470 + }, + { + "epoch": 0.4003357770440428, + "grad_norm": 0.9661636635651168, + "learning_rate": 1.3630386500396637e-05, + "loss": 0.862, + "step": 4471 + }, + { + "epoch": 0.4004253175891208, + "grad_norm": 0.8936469353949354, + "learning_rate": 1.362768393396443e-05, + "loss": 0.8304, + "step": 4472 + }, + { + "epoch": 0.4005148581341989, + "grad_norm": 0.8816972531088852, + "learning_rate": 1.3624981062383274e-05, + "loss": 0.8338, + "step": 4473 + }, + { + "epoch": 0.40060439867927694, + "grad_norm": 0.8761735847969794, + "learning_rate": 1.3622277885880526e-05, + "loss": 0.8677, + "step": 4474 + }, + { + "epoch": 0.40069393922435503, + "grad_norm": 0.8935426172795219, + "learning_rate": 1.361957440468356e-05, + "loss": 0.8396, + "step": 4475 + }, + { + "epoch": 0.40078347976943307, + "grad_norm": 0.8787888345569079, + "learning_rate": 1.3616870619019795e-05, + "loss": 0.867, + "step": 4476 + }, + { + "epoch": 0.40087302031451116, + "grad_norm": 0.965390833492568, + "learning_rate": 1.3614166529116659e-05, + "loss": 0.8572, + "step": 4477 + }, + { + "epoch": 0.40096256085958926, + "grad_norm": 0.9740971215939589, + "learning_rate": 1.361146213520161e-05, + "loss": 0.8385, + "step": 4478 + }, + { + "epoch": 0.4010521014046673, + "grad_norm": 0.9025120988745962, + "learning_rate": 1.360875743750214e-05, + "loss": 0.8655, + "step": 4479 + }, + { + "epoch": 0.4011416419497454, + "grad_norm": 1.0186064649949762, + "learning_rate": 1.360605243624575e-05, + "loss": 0.8553, + "step": 4480 + }, + { + "epoch": 0.4012311824948234, + "grad_norm": 0.9250276269164744, + "learning_rate": 1.360334713165998e-05, + "loss": 0.8044, + "step": 4481 + }, + { + "epoch": 0.4013207230399015, + "grad_norm": 0.9322636939402259, + "learning_rate": 1.3600641523972393e-05, + "loss": 0.8432, + "step": 4482 + }, + { + "epoch": 0.40141026358497955, + "grad_norm": 0.8996558050061848, + "learning_rate": 1.3597935613410576e-05, + "loss": 0.8471, + "step": 4483 + }, + { + "epoch": 0.40149980413005765, + "grad_norm": 2.326977929397955, + "learning_rate": 1.3595229400202137e-05, + "loss": 0.9359, + "step": 4484 + }, + { + "epoch": 0.4015893446751357, + "grad_norm": 0.9927075276244369, + "learning_rate": 1.3592522884574717e-05, + "loss": 0.8261, + "step": 4485 + }, + { + "epoch": 0.4016788852202138, + "grad_norm": 0.877379387454843, + "learning_rate": 1.3589816066755978e-05, + "loss": 0.8186, + "step": 4486 + }, + { + "epoch": 0.40176842576529187, + "grad_norm": 0.9581301362758288, + "learning_rate": 1.358710894697361e-05, + "loss": 0.8924, + "step": 4487 + }, + { + "epoch": 0.4018579663103699, + "grad_norm": 0.9075046332936687, + "learning_rate": 1.3584401525455331e-05, + "loss": 0.8715, + "step": 4488 + }, + { + "epoch": 0.401947506855448, + "grad_norm": 0.9302898791311506, + "learning_rate": 1.3581693802428873e-05, + "loss": 0.8113, + "step": 4489 + }, + { + "epoch": 0.40203704740052604, + "grad_norm": 0.9670470035990554, + "learning_rate": 1.3578985778122003e-05, + "loss": 0.8533, + "step": 4490 + }, + { + "epoch": 0.40212658794560413, + "grad_norm": 0.9360660088757257, + "learning_rate": 1.3576277452762512e-05, + "loss": 0.8995, + "step": 4491 + }, + { + "epoch": 0.40221612849068217, + "grad_norm": 0.942163854335068, + "learning_rate": 1.3573568826578215e-05, + "loss": 0.8759, + "step": 4492 + }, + { + "epoch": 0.40230566903576026, + "grad_norm": 1.0234700830736927, + "learning_rate": 1.3570859899796957e-05, + "loss": 0.8278, + "step": 4493 + }, + { + "epoch": 0.4023952095808383, + "grad_norm": 0.9692503125331849, + "learning_rate": 1.3568150672646598e-05, + "loss": 0.8607, + "step": 4494 + }, + { + "epoch": 0.4024847501259164, + "grad_norm": 0.9325685504847488, + "learning_rate": 1.3565441145355036e-05, + "loss": 0.8778, + "step": 4495 + }, + { + "epoch": 0.4025742906709945, + "grad_norm": 0.8801075544714826, + "learning_rate": 1.3562731318150177e-05, + "loss": 0.8094, + "step": 4496 + }, + { + "epoch": 0.4026638312160725, + "grad_norm": 1.0693582860488853, + "learning_rate": 1.3560021191259973e-05, + "loss": 0.8769, + "step": 4497 + }, + { + "epoch": 0.4027533717611506, + "grad_norm": 1.1543768107375647, + "learning_rate": 1.355731076491239e-05, + "loss": 0.8391, + "step": 4498 + }, + { + "epoch": 0.40284291230622865, + "grad_norm": 1.1614143836238247, + "learning_rate": 1.3554600039335413e-05, + "loss": 0.8868, + "step": 4499 + }, + { + "epoch": 0.40293245285130674, + "grad_norm": 0.96024822484628, + "learning_rate": 1.3551889014757067e-05, + "loss": 0.8048, + "step": 4500 + }, + { + "epoch": 0.4030219933963848, + "grad_norm": 1.2757267786068034, + "learning_rate": 1.3549177691405391e-05, + "loss": 0.8522, + "step": 4501 + }, + { + "epoch": 0.4031115339414629, + "grad_norm": 0.9952925269442845, + "learning_rate": 1.354646606950845e-05, + "loss": 0.9318, + "step": 4502 + }, + { + "epoch": 0.4032010744865409, + "grad_norm": 1.134944826076881, + "learning_rate": 1.3543754149294344e-05, + "loss": 0.8511, + "step": 4503 + }, + { + "epoch": 0.403290615031619, + "grad_norm": 0.9015969479082923, + "learning_rate": 1.3541041930991189e-05, + "loss": 0.8202, + "step": 4504 + }, + { + "epoch": 0.4033801555766971, + "grad_norm": 0.936302782037889, + "learning_rate": 1.353832941482712e-05, + "loss": 0.8217, + "step": 4505 + }, + { + "epoch": 0.40346969612177513, + "grad_norm": 0.8761864219275303, + "learning_rate": 1.3535616601030317e-05, + "loss": 0.8941, + "step": 4506 + }, + { + "epoch": 0.4035592366668532, + "grad_norm": 0.8444784263369487, + "learning_rate": 1.3532903489828964e-05, + "loss": 0.8162, + "step": 4507 + }, + { + "epoch": 0.40364877721193126, + "grad_norm": 0.9510293773266176, + "learning_rate": 1.3530190081451282e-05, + "loss": 0.8222, + "step": 4508 + }, + { + "epoch": 0.40373831775700936, + "grad_norm": 1.2659201022040512, + "learning_rate": 1.3527476376125515e-05, + "loss": 0.8264, + "step": 4509 + }, + { + "epoch": 0.4038278583020874, + "grad_norm": 1.0595297337418874, + "learning_rate": 1.352476237407993e-05, + "loss": 0.8595, + "step": 4510 + }, + { + "epoch": 0.4039173988471655, + "grad_norm": 1.0403890973811447, + "learning_rate": 1.3522048075542818e-05, + "loss": 0.8329, + "step": 4511 + }, + { + "epoch": 0.4040069393922435, + "grad_norm": 1.145333383524234, + "learning_rate": 1.3519333480742502e-05, + "loss": 0.9007, + "step": 4512 + }, + { + "epoch": 0.4040964799373216, + "grad_norm": 0.9484488113446747, + "learning_rate": 1.351661858990732e-05, + "loss": 0.7972, + "step": 4513 + }, + { + "epoch": 0.4041860204823997, + "grad_norm": 0.9580461484275042, + "learning_rate": 1.3513903403265643e-05, + "loss": 0.8539, + "step": 4514 + }, + { + "epoch": 0.40427556102747775, + "grad_norm": 0.9767206623843067, + "learning_rate": 1.3511187921045863e-05, + "loss": 0.8401, + "step": 4515 + }, + { + "epoch": 0.40436510157255584, + "grad_norm": 0.887666835612042, + "learning_rate": 1.3508472143476397e-05, + "loss": 0.8147, + "step": 4516 + }, + { + "epoch": 0.4044546421176339, + "grad_norm": 0.8704146018612282, + "learning_rate": 1.3505756070785684e-05, + "loss": 0.8208, + "step": 4517 + }, + { + "epoch": 0.40454418266271197, + "grad_norm": 0.9620386661415793, + "learning_rate": 1.35030397032022e-05, + "loss": 0.8489, + "step": 4518 + }, + { + "epoch": 0.40463372320779, + "grad_norm": 1.0808081832604142, + "learning_rate": 1.3500323040954429e-05, + "loss": 0.8613, + "step": 4519 + }, + { + "epoch": 0.4047232637528681, + "grad_norm": 1.010232512801896, + "learning_rate": 1.3497606084270889e-05, + "loss": 0.8954, + "step": 4520 + }, + { + "epoch": 0.40481280429794614, + "grad_norm": 0.970985652683431, + "learning_rate": 1.3494888833380124e-05, + "loss": 0.8374, + "step": 4521 + }, + { + "epoch": 0.40490234484302423, + "grad_norm": 0.9341418442078511, + "learning_rate": 1.3492171288510701e-05, + "loss": 0.8727, + "step": 4522 + }, + { + "epoch": 0.4049918853881023, + "grad_norm": 0.9081627155438473, + "learning_rate": 1.3489453449891206e-05, + "loss": 0.8017, + "step": 4523 + }, + { + "epoch": 0.40508142593318036, + "grad_norm": 0.8474542247164016, + "learning_rate": 1.348673531775026e-05, + "loss": 0.8112, + "step": 4524 + }, + { + "epoch": 0.40517096647825845, + "grad_norm": 0.9412260054466648, + "learning_rate": 1.3484016892316503e-05, + "loss": 0.8917, + "step": 4525 + }, + { + "epoch": 0.4052605070233365, + "grad_norm": 0.9961068539087753, + "learning_rate": 1.3481298173818593e-05, + "loss": 0.8704, + "step": 4526 + }, + { + "epoch": 0.4053500475684146, + "grad_norm": 1.0562341777492048, + "learning_rate": 1.3478579162485228e-05, + "loss": 0.9319, + "step": 4527 + }, + { + "epoch": 0.4054395881134926, + "grad_norm": 0.9851290481217739, + "learning_rate": 1.3475859858545121e-05, + "loss": 0.8612, + "step": 4528 + }, + { + "epoch": 0.4055291286585707, + "grad_norm": 0.93516140191837, + "learning_rate": 1.3473140262227007e-05, + "loss": 0.8564, + "step": 4529 + }, + { + "epoch": 0.40561866920364875, + "grad_norm": 0.9448154886682678, + "learning_rate": 1.3470420373759651e-05, + "loss": 0.8307, + "step": 4530 + }, + { + "epoch": 0.40570820974872684, + "grad_norm": 0.9474729757593683, + "learning_rate": 1.3467700193371848e-05, + "loss": 0.8336, + "step": 4531 + }, + { + "epoch": 0.40579775029380494, + "grad_norm": 0.9814331907833825, + "learning_rate": 1.3464979721292399e-05, + "loss": 0.8943, + "step": 4532 + }, + { + "epoch": 0.405887290838883, + "grad_norm": 0.9619634081070338, + "learning_rate": 1.3462258957750152e-05, + "loss": 0.828, + "step": 4533 + }, + { + "epoch": 0.40597683138396107, + "grad_norm": 0.908827172390751, + "learning_rate": 1.3459537902973963e-05, + "loss": 0.8403, + "step": 4534 + }, + { + "epoch": 0.4060663719290391, + "grad_norm": 0.8560585522376893, + "learning_rate": 1.3456816557192718e-05, + "loss": 0.7777, + "step": 4535 + }, + { + "epoch": 0.4061559124741172, + "grad_norm": 0.9913749254338156, + "learning_rate": 1.3454094920635327e-05, + "loss": 0.8891, + "step": 4536 + }, + { + "epoch": 0.40624545301919524, + "grad_norm": 1.0432003774117335, + "learning_rate": 1.3451372993530729e-05, + "loss": 0.8542, + "step": 4537 + }, + { + "epoch": 0.40633499356427333, + "grad_norm": 0.9223267963715208, + "learning_rate": 1.344865077610788e-05, + "loss": 0.7705, + "step": 4538 + }, + { + "epoch": 0.40642453410935137, + "grad_norm": 0.9908953176945192, + "learning_rate": 1.344592826859577e-05, + "loss": 0.8053, + "step": 4539 + }, + { + "epoch": 0.40651407465442946, + "grad_norm": 0.9678679772787933, + "learning_rate": 1.34432054712234e-05, + "loss": 0.8579, + "step": 4540 + }, + { + "epoch": 0.40660361519950755, + "grad_norm": 1.0174010720322002, + "learning_rate": 1.3440482384219807e-05, + "loss": 0.8598, + "step": 4541 + }, + { + "epoch": 0.4066931557445856, + "grad_norm": 0.8460226462544751, + "learning_rate": 1.3437759007814046e-05, + "loss": 0.8565, + "step": 4542 + }, + { + "epoch": 0.4067826962896637, + "grad_norm": 0.9386144553068516, + "learning_rate": 1.3435035342235204e-05, + "loss": 0.8663, + "step": 4543 + }, + { + "epoch": 0.4068722368347417, + "grad_norm": 0.9692082358969527, + "learning_rate": 1.3432311387712378e-05, + "loss": 0.8616, + "step": 4544 + }, + { + "epoch": 0.4069617773798198, + "grad_norm": 0.9466390515429067, + "learning_rate": 1.3429587144474705e-05, + "loss": 0.8627, + "step": 4545 + }, + { + "epoch": 0.40705131792489785, + "grad_norm": 0.9058342600177697, + "learning_rate": 1.3426862612751336e-05, + "loss": 0.8567, + "step": 4546 + }, + { + "epoch": 0.40714085846997594, + "grad_norm": 1.1423014686710726, + "learning_rate": 1.3424137792771455e-05, + "loss": 0.8851, + "step": 4547 + }, + { + "epoch": 0.407230399015054, + "grad_norm": 0.9226218607379479, + "learning_rate": 1.3421412684764256e-05, + "loss": 0.847, + "step": 4548 + }, + { + "epoch": 0.40731993956013207, + "grad_norm": 0.9774286083690441, + "learning_rate": 1.3418687288958976e-05, + "loss": 0.8142, + "step": 4549 + }, + { + "epoch": 0.40740948010521016, + "grad_norm": 0.9650988238030125, + "learning_rate": 1.3415961605584857e-05, + "loss": 0.8285, + "step": 4550 + }, + { + "epoch": 0.4074990206502882, + "grad_norm": 0.8598830505967154, + "learning_rate": 1.3413235634871185e-05, + "loss": 0.8823, + "step": 4551 + }, + { + "epoch": 0.4075885611953663, + "grad_norm": 0.9101646712023322, + "learning_rate": 1.341050937704725e-05, + "loss": 0.8846, + "step": 4552 + }, + { + "epoch": 0.40767810174044433, + "grad_norm": 0.9030153623726633, + "learning_rate": 1.3407782832342382e-05, + "loss": 0.8575, + "step": 4553 + }, + { + "epoch": 0.4077676422855224, + "grad_norm": 0.8388911890500786, + "learning_rate": 1.3405056000985925e-05, + "loss": 0.8238, + "step": 4554 + }, + { + "epoch": 0.40785718283060046, + "grad_norm": 0.9309588745139172, + "learning_rate": 1.3402328883207257e-05, + "loss": 0.8606, + "step": 4555 + }, + { + "epoch": 0.40794672337567855, + "grad_norm": 0.8762462551837407, + "learning_rate": 1.3399601479235767e-05, + "loss": 0.8824, + "step": 4556 + }, + { + "epoch": 0.4080362639207566, + "grad_norm": 0.8882470096875025, + "learning_rate": 1.3396873789300879e-05, + "loss": 0.7821, + "step": 4557 + }, + { + "epoch": 0.4081258044658347, + "grad_norm": 0.9251347056269427, + "learning_rate": 1.339414581363204e-05, + "loss": 0.8521, + "step": 4558 + }, + { + "epoch": 0.4082153450109128, + "grad_norm": 0.8890298695496572, + "learning_rate": 1.3391417552458712e-05, + "loss": 0.831, + "step": 4559 + }, + { + "epoch": 0.4083048855559908, + "grad_norm": 1.086556456057103, + "learning_rate": 1.3388689006010394e-05, + "loss": 0.8612, + "step": 4560 + }, + { + "epoch": 0.4083944261010689, + "grad_norm": 1.1083473238528658, + "learning_rate": 1.33859601745166e-05, + "loss": 0.796, + "step": 4561 + }, + { + "epoch": 0.40848396664614695, + "grad_norm": 1.0760774860103657, + "learning_rate": 1.3383231058206866e-05, + "loss": 0.8794, + "step": 4562 + }, + { + "epoch": 0.40857350719122504, + "grad_norm": 1.1125398325660019, + "learning_rate": 1.3380501657310763e-05, + "loss": 0.8206, + "step": 4563 + }, + { + "epoch": 0.4086630477363031, + "grad_norm": 0.9563373323066136, + "learning_rate": 1.3377771972057878e-05, + "loss": 0.8118, + "step": 4564 + }, + { + "epoch": 0.40875258828138117, + "grad_norm": 0.9090597504823279, + "learning_rate": 1.337504200267782e-05, + "loss": 0.8911, + "step": 4565 + }, + { + "epoch": 0.4088421288264592, + "grad_norm": 0.9233541598867686, + "learning_rate": 1.3372311749400226e-05, + "loss": 0.8393, + "step": 4566 + }, + { + "epoch": 0.4089316693715373, + "grad_norm": 1.0508909317558797, + "learning_rate": 1.3369581212454758e-05, + "loss": 0.8542, + "step": 4567 + }, + { + "epoch": 0.4090212099166154, + "grad_norm": 0.9278082088264658, + "learning_rate": 1.33668503920711e-05, + "loss": 0.8193, + "step": 4568 + }, + { + "epoch": 0.40911075046169343, + "grad_norm": 0.8397817438730998, + "learning_rate": 1.336411928847896e-05, + "loss": 0.8243, + "step": 4569 + }, + { + "epoch": 0.4092002910067715, + "grad_norm": 0.8466845539832453, + "learning_rate": 1.3361387901908063e-05, + "loss": 0.8304, + "step": 4570 + }, + { + "epoch": 0.40928983155184956, + "grad_norm": 0.9380068231004197, + "learning_rate": 1.3358656232588174e-05, + "loss": 0.8308, + "step": 4571 + }, + { + "epoch": 0.40937937209692765, + "grad_norm": 0.9449251187204846, + "learning_rate": 1.3355924280749065e-05, + "loss": 0.902, + "step": 4572 + }, + { + "epoch": 0.4094689126420057, + "grad_norm": 1.0066540794588783, + "learning_rate": 1.3353192046620542e-05, + "loss": 0.8834, + "step": 4573 + }, + { + "epoch": 0.4095584531870838, + "grad_norm": 0.9492260077501271, + "learning_rate": 1.3350459530432431e-05, + "loss": 0.8426, + "step": 4574 + }, + { + "epoch": 0.4096479937321618, + "grad_norm": 1.0876057747062915, + "learning_rate": 1.3347726732414584e-05, + "loss": 0.8201, + "step": 4575 + }, + { + "epoch": 0.4097375342772399, + "grad_norm": 0.9938192013613967, + "learning_rate": 1.3344993652796872e-05, + "loss": 0.8697, + "step": 4576 + }, + { + "epoch": 0.409827074822318, + "grad_norm": 0.9451712074067705, + "learning_rate": 1.3342260291809194e-05, + "loss": 0.8296, + "step": 4577 + }, + { + "epoch": 0.40991661536739604, + "grad_norm": 0.9699039908276667, + "learning_rate": 1.3339526649681473e-05, + "loss": 0.9037, + "step": 4578 + }, + { + "epoch": 0.41000615591247414, + "grad_norm": 0.9614840372737827, + "learning_rate": 1.3336792726643652e-05, + "loss": 0.861, + "step": 4579 + }, + { + "epoch": 0.4100956964575522, + "grad_norm": 0.9299321911136904, + "learning_rate": 1.3334058522925702e-05, + "loss": 0.8708, + "step": 4580 + }, + { + "epoch": 0.41018523700263027, + "grad_norm": 0.9654633566271076, + "learning_rate": 1.3331324038757612e-05, + "loss": 0.8072, + "step": 4581 + }, + { + "epoch": 0.4102747775477083, + "grad_norm": 0.8878407335900006, + "learning_rate": 1.33285892743694e-05, + "loss": 0.8628, + "step": 4582 + }, + { + "epoch": 0.4103643180927864, + "grad_norm": 0.8908724709174111, + "learning_rate": 1.3325854229991104e-05, + "loss": 0.7846, + "step": 4583 + }, + { + "epoch": 0.41045385863786443, + "grad_norm": 0.9613035862774133, + "learning_rate": 1.332311890585279e-05, + "loss": 0.8256, + "step": 4584 + }, + { + "epoch": 0.4105433991829425, + "grad_norm": 0.9964065110914502, + "learning_rate": 1.3320383302184546e-05, + "loss": 0.8389, + "step": 4585 + }, + { + "epoch": 0.4106329397280206, + "grad_norm": 0.8546655750731609, + "learning_rate": 1.331764741921647e-05, + "loss": 0.8205, + "step": 4586 + }, + { + "epoch": 0.41072248027309866, + "grad_norm": 1.0774639743019896, + "learning_rate": 1.331491125717871e-05, + "loss": 0.8171, + "step": 4587 + }, + { + "epoch": 0.41081202081817675, + "grad_norm": 1.0181628094583761, + "learning_rate": 1.3312174816301418e-05, + "loss": 0.8284, + "step": 4588 + }, + { + "epoch": 0.4109015613632548, + "grad_norm": 0.8855528770972546, + "learning_rate": 1.3309438096814772e-05, + "loss": 0.8531, + "step": 4589 + }, + { + "epoch": 0.4109911019083329, + "grad_norm": 0.8822107077366784, + "learning_rate": 1.3306701098948978e-05, + "loss": 0.8439, + "step": 4590 + }, + { + "epoch": 0.4110806424534109, + "grad_norm": 0.9076855758792197, + "learning_rate": 1.3303963822934264e-05, + "loss": 0.8398, + "step": 4591 + }, + { + "epoch": 0.411170182998489, + "grad_norm": 0.9285593788012148, + "learning_rate": 1.330122626900088e-05, + "loss": 0.833, + "step": 4592 + }, + { + "epoch": 0.41125972354356705, + "grad_norm": 0.9756747490703039, + "learning_rate": 1.3298488437379096e-05, + "loss": 0.8188, + "step": 4593 + }, + { + "epoch": 0.41134926408864514, + "grad_norm": 1.078644547280076, + "learning_rate": 1.3295750328299219e-05, + "loss": 0.8569, + "step": 4594 + }, + { + "epoch": 0.41143880463372323, + "grad_norm": 1.2177247263270485, + "learning_rate": 1.3293011941991561e-05, + "loss": 0.869, + "step": 4595 + }, + { + "epoch": 0.41152834517880127, + "grad_norm": 1.0152014145562078, + "learning_rate": 1.3290273278686469e-05, + "loss": 0.8268, + "step": 4596 + }, + { + "epoch": 0.41161788572387936, + "grad_norm": 1.1074879588961724, + "learning_rate": 1.3287534338614313e-05, + "loss": 0.8107, + "step": 4597 + }, + { + "epoch": 0.4117074262689574, + "grad_norm": 0.8896465682708404, + "learning_rate": 1.328479512200548e-05, + "loss": 0.8534, + "step": 4598 + }, + { + "epoch": 0.4117969668140355, + "grad_norm": 1.073572431591183, + "learning_rate": 1.3282055629090387e-05, + "loss": 0.8695, + "step": 4599 + }, + { + "epoch": 0.41188650735911353, + "grad_norm": 0.881577555602564, + "learning_rate": 1.3279315860099468e-05, + "loss": 0.8473, + "step": 4600 + }, + { + "epoch": 0.4119760479041916, + "grad_norm": 0.982180239266472, + "learning_rate": 1.3276575815263187e-05, + "loss": 0.8528, + "step": 4601 + }, + { + "epoch": 0.41206558844926966, + "grad_norm": 1.0190998905201165, + "learning_rate": 1.3273835494812023e-05, + "loss": 0.9019, + "step": 4602 + }, + { + "epoch": 0.41215512899434775, + "grad_norm": 0.9104134662785992, + "learning_rate": 1.3271094898976488e-05, + "loss": 0.8848, + "step": 4603 + }, + { + "epoch": 0.41224466953942585, + "grad_norm": 0.9998663868670606, + "learning_rate": 1.326835402798711e-05, + "loss": 0.8403, + "step": 4604 + }, + { + "epoch": 0.4123342100845039, + "grad_norm": 1.2477286444590316, + "learning_rate": 1.3265612882074441e-05, + "loss": 0.8272, + "step": 4605 + }, + { + "epoch": 0.412423750629582, + "grad_norm": 0.9250570113061771, + "learning_rate": 1.3262871461469057e-05, + "loss": 0.8207, + "step": 4606 + }, + { + "epoch": 0.41251329117466, + "grad_norm": 0.9329401712882781, + "learning_rate": 1.326012976640156e-05, + "loss": 0.8322, + "step": 4607 + }, + { + "epoch": 0.4126028317197381, + "grad_norm": 0.9489315333930428, + "learning_rate": 1.325738779710257e-05, + "loss": 0.8176, + "step": 4608 + }, + { + "epoch": 0.41269237226481614, + "grad_norm": 0.8273872821029399, + "learning_rate": 1.3254645553802731e-05, + "loss": 0.8147, + "step": 4609 + }, + { + "epoch": 0.41278191280989424, + "grad_norm": 0.8970109030900272, + "learning_rate": 1.3251903036732718e-05, + "loss": 0.8561, + "step": 4610 + }, + { + "epoch": 0.4128714533549723, + "grad_norm": 0.9692401893013974, + "learning_rate": 1.3249160246123216e-05, + "loss": 0.839, + "step": 4611 + }, + { + "epoch": 0.41296099390005037, + "grad_norm": 0.9087791981905572, + "learning_rate": 1.3246417182204944e-05, + "loss": 0.8806, + "step": 4612 + }, + { + "epoch": 0.41305053444512846, + "grad_norm": 0.966237193485273, + "learning_rate": 1.3243673845208638e-05, + "loss": 0.8269, + "step": 4613 + }, + { + "epoch": 0.4131400749902065, + "grad_norm": 0.9287230016236534, + "learning_rate": 1.3240930235365054e-05, + "loss": 0.7945, + "step": 4614 + }, + { + "epoch": 0.4132296155352846, + "grad_norm": 1.0018047332899902, + "learning_rate": 1.3238186352904985e-05, + "loss": 0.8592, + "step": 4615 + }, + { + "epoch": 0.4133191560803626, + "grad_norm": 0.999805643274705, + "learning_rate": 1.3235442198059233e-05, + "loss": 0.7644, + "step": 4616 + }, + { + "epoch": 0.4134086966254407, + "grad_norm": 1.0806087015699573, + "learning_rate": 1.323269777105862e-05, + "loss": 0.8874, + "step": 4617 + }, + { + "epoch": 0.41349823717051876, + "grad_norm": 0.9091031689744161, + "learning_rate": 1.3229953072134012e-05, + "loss": 0.7725, + "step": 4618 + }, + { + "epoch": 0.41358777771559685, + "grad_norm": 1.1672372449111448, + "learning_rate": 1.3227208101516273e-05, + "loss": 0.9022, + "step": 4619 + }, + { + "epoch": 0.4136773182606749, + "grad_norm": 1.1690505655294394, + "learning_rate": 1.3224462859436304e-05, + "loss": 0.8404, + "step": 4620 + }, + { + "epoch": 0.413766858805753, + "grad_norm": 0.925577127704765, + "learning_rate": 1.3221717346125029e-05, + "loss": 0.8088, + "step": 4621 + }, + { + "epoch": 0.4138563993508311, + "grad_norm": 0.8968946873108684, + "learning_rate": 1.321897156181339e-05, + "loss": 0.8215, + "step": 4622 + }, + { + "epoch": 0.4139459398959091, + "grad_norm": 0.9704610813389212, + "learning_rate": 1.321622550673235e-05, + "loss": 0.8222, + "step": 4623 + }, + { + "epoch": 0.4140354804409872, + "grad_norm": 1.020599008603233, + "learning_rate": 1.3213479181112906e-05, + "loss": 0.8546, + "step": 4624 + }, + { + "epoch": 0.41412502098606524, + "grad_norm": 0.954281810589137, + "learning_rate": 1.321073258518606e-05, + "loss": 0.848, + "step": 4625 + }, + { + "epoch": 0.41421456153114333, + "grad_norm": 0.9592509514278127, + "learning_rate": 1.3207985719182857e-05, + "loss": 0.8486, + "step": 4626 + }, + { + "epoch": 0.41430410207622137, + "grad_norm": 0.992927323363761, + "learning_rate": 1.3205238583334343e-05, + "loss": 0.8775, + "step": 4627 + }, + { + "epoch": 0.41439364262129946, + "grad_norm": 0.9194625188139148, + "learning_rate": 1.3202491177871608e-05, + "loss": 0.8847, + "step": 4628 + }, + { + "epoch": 0.4144831831663775, + "grad_norm": 0.9330567672692596, + "learning_rate": 1.3199743503025753e-05, + "loss": 0.8232, + "step": 4629 + }, + { + "epoch": 0.4145727237114556, + "grad_norm": 0.8889707777673176, + "learning_rate": 1.3196995559027897e-05, + "loss": 0.8215, + "step": 4630 + }, + { + "epoch": 0.4146622642565337, + "grad_norm": 0.9061196558934956, + "learning_rate": 1.3194247346109196e-05, + "loss": 0.8732, + "step": 4631 + }, + { + "epoch": 0.4147518048016117, + "grad_norm": 1.1181165079217956, + "learning_rate": 1.3191498864500813e-05, + "loss": 0.7961, + "step": 4632 + }, + { + "epoch": 0.4148413453466898, + "grad_norm": 0.8115127254057263, + "learning_rate": 1.3188750114433951e-05, + "loss": 0.8748, + "step": 4633 + }, + { + "epoch": 0.41493088589176785, + "grad_norm": 0.8769947067715624, + "learning_rate": 1.3186001096139818e-05, + "loss": 0.8615, + "step": 4634 + }, + { + "epoch": 0.41502042643684595, + "grad_norm": 1.1462198331281213, + "learning_rate": 1.3183251809849655e-05, + "loss": 0.7953, + "step": 4635 + }, + { + "epoch": 0.415109966981924, + "grad_norm": 0.8572780827941026, + "learning_rate": 1.3180502255794723e-05, + "loss": 0.8474, + "step": 4636 + }, + { + "epoch": 0.4151995075270021, + "grad_norm": 1.2846869032657486, + "learning_rate": 1.3177752434206305e-05, + "loss": 0.8899, + "step": 4637 + }, + { + "epoch": 0.4152890480720801, + "grad_norm": 0.9821742845977395, + "learning_rate": 1.317500234531571e-05, + "loss": 0.8355, + "step": 4638 + }, + { + "epoch": 0.4153785886171582, + "grad_norm": 0.9373207537928022, + "learning_rate": 1.317225198935426e-05, + "loss": 0.8755, + "step": 4639 + }, + { + "epoch": 0.4154681291622363, + "grad_norm": 0.8308853445502898, + "learning_rate": 1.3169501366553314e-05, + "loss": 0.8288, + "step": 4640 + }, + { + "epoch": 0.41555766970731434, + "grad_norm": 1.1504088516725506, + "learning_rate": 1.3166750477144241e-05, + "loss": 0.8422, + "step": 4641 + }, + { + "epoch": 0.41564721025239243, + "grad_norm": 0.9402836437634677, + "learning_rate": 1.3163999321358436e-05, + "loss": 0.8845, + "step": 4642 + }, + { + "epoch": 0.41573675079747047, + "grad_norm": 0.9623303998465765, + "learning_rate": 1.3161247899427321e-05, + "loss": 0.8155, + "step": 4643 + }, + { + "epoch": 0.41582629134254856, + "grad_norm": 0.9191905321268291, + "learning_rate": 1.315849621158233e-05, + "loss": 0.9001, + "step": 4644 + }, + { + "epoch": 0.4159158318876266, + "grad_norm": 0.9607037118151015, + "learning_rate": 1.3155744258054934e-05, + "loss": 0.7946, + "step": 4645 + }, + { + "epoch": 0.4160053724327047, + "grad_norm": 0.9216694176538363, + "learning_rate": 1.3152992039076616e-05, + "loss": 0.8218, + "step": 4646 + }, + { + "epoch": 0.4160949129777827, + "grad_norm": 0.8871327779806395, + "learning_rate": 1.3150239554878876e-05, + "loss": 0.8622, + "step": 4647 + }, + { + "epoch": 0.4161844535228608, + "grad_norm": 0.9362560430881015, + "learning_rate": 1.3147486805693258e-05, + "loss": 0.8369, + "step": 4648 + }, + { + "epoch": 0.4162739940679389, + "grad_norm": 0.9023815269899874, + "learning_rate": 1.3144733791751301e-05, + "loss": 0.8391, + "step": 4649 + }, + { + "epoch": 0.41636353461301695, + "grad_norm": 0.9831019406426816, + "learning_rate": 1.3141980513284584e-05, + "loss": 0.8839, + "step": 4650 + }, + { + "epoch": 0.41645307515809504, + "grad_norm": 0.8992611897182874, + "learning_rate": 1.313922697052471e-05, + "loss": 0.8316, + "step": 4651 + }, + { + "epoch": 0.4165426157031731, + "grad_norm": 0.9406869452982524, + "learning_rate": 1.3136473163703291e-05, + "loss": 0.8408, + "step": 4652 + }, + { + "epoch": 0.4166321562482512, + "grad_norm": 0.917723487069821, + "learning_rate": 1.3133719093051968e-05, + "loss": 0.8745, + "step": 4653 + }, + { + "epoch": 0.4167216967933292, + "grad_norm": 0.9185868620363086, + "learning_rate": 1.313096475880241e-05, + "loss": 0.7782, + "step": 4654 + }, + { + "epoch": 0.4168112373384073, + "grad_norm": 0.9065162127552399, + "learning_rate": 1.3128210161186299e-05, + "loss": 0.8299, + "step": 4655 + }, + { + "epoch": 0.41690077788348534, + "grad_norm": 0.9124269286174485, + "learning_rate": 1.3125455300435343e-05, + "loss": 0.8715, + "step": 4656 + }, + { + "epoch": 0.41699031842856343, + "grad_norm": 0.9210232868415803, + "learning_rate": 1.312270017678127e-05, + "loss": 0.8163, + "step": 4657 + }, + { + "epoch": 0.4170798589736415, + "grad_norm": 0.8443906039482938, + "learning_rate": 1.3119944790455837e-05, + "loss": 0.8041, + "step": 4658 + }, + { + "epoch": 0.41716939951871956, + "grad_norm": 0.9599377820340842, + "learning_rate": 1.3117189141690815e-05, + "loss": 0.8484, + "step": 4659 + }, + { + "epoch": 0.41725894006379766, + "grad_norm": 0.9297116036913715, + "learning_rate": 1.3114433230717998e-05, + "loss": 0.9055, + "step": 4660 + }, + { + "epoch": 0.4173484806088757, + "grad_norm": 0.8874840704671126, + "learning_rate": 1.3111677057769208e-05, + "loss": 0.8659, + "step": 4661 + }, + { + "epoch": 0.4174380211539538, + "grad_norm": 1.003778061450708, + "learning_rate": 1.3108920623076285e-05, + "loss": 0.8191, + "step": 4662 + }, + { + "epoch": 0.4175275616990318, + "grad_norm": 0.9992249877611448, + "learning_rate": 1.3106163926871087e-05, + "loss": 0.8047, + "step": 4663 + }, + { + "epoch": 0.4176171022441099, + "grad_norm": 0.9560570869517108, + "learning_rate": 1.3103406969385503e-05, + "loss": 0.8683, + "step": 4664 + }, + { + "epoch": 0.41770664278918795, + "grad_norm": 0.9552214078071677, + "learning_rate": 1.310064975085144e-05, + "loss": 0.8257, + "step": 4665 + }, + { + "epoch": 0.41779618333426605, + "grad_norm": 0.9413913920296842, + "learning_rate": 1.3097892271500823e-05, + "loss": 0.8621, + "step": 4666 + }, + { + "epoch": 0.41788572387934414, + "grad_norm": 0.9472586405069346, + "learning_rate": 1.3095134531565603e-05, + "loss": 0.8756, + "step": 4667 + }, + { + "epoch": 0.4179752644244222, + "grad_norm": 0.9577133262185117, + "learning_rate": 1.3092376531277751e-05, + "loss": 0.8494, + "step": 4668 + }, + { + "epoch": 0.41806480496950027, + "grad_norm": 1.014542126188905, + "learning_rate": 1.3089618270869263e-05, + "loss": 0.8829, + "step": 4669 + }, + { + "epoch": 0.4181543455145783, + "grad_norm": 0.8704543576605985, + "learning_rate": 1.3086859750572155e-05, + "loss": 0.8693, + "step": 4670 + }, + { + "epoch": 0.4182438860596564, + "grad_norm": 0.9127430959270818, + "learning_rate": 1.3084100970618463e-05, + "loss": 0.8689, + "step": 4671 + }, + { + "epoch": 0.41833342660473444, + "grad_norm": 0.9068657150194723, + "learning_rate": 1.3081341931240248e-05, + "loss": 0.8043, + "step": 4672 + }, + { + "epoch": 0.41842296714981253, + "grad_norm": 0.9699648071629574, + "learning_rate": 1.3078582632669594e-05, + "loss": 0.881, + "step": 4673 + }, + { + "epoch": 0.41851250769489057, + "grad_norm": 0.963258145354212, + "learning_rate": 1.3075823075138596e-05, + "loss": 0.8292, + "step": 4674 + }, + { + "epoch": 0.41860204823996866, + "grad_norm": 1.0242842037934123, + "learning_rate": 1.3073063258879387e-05, + "loss": 0.8577, + "step": 4675 + }, + { + "epoch": 0.41869158878504675, + "grad_norm": 1.092262611762796, + "learning_rate": 1.3070303184124111e-05, + "loss": 0.8711, + "step": 4676 + }, + { + "epoch": 0.4187811293301248, + "grad_norm": 0.9838270688618203, + "learning_rate": 1.3067542851104933e-05, + "loss": 0.8233, + "step": 4677 + }, + { + "epoch": 0.4188706698752029, + "grad_norm": 0.9203296737606311, + "learning_rate": 1.306478226005405e-05, + "loss": 0.8172, + "step": 4678 + }, + { + "epoch": 0.4189602104202809, + "grad_norm": 0.9616787989563077, + "learning_rate": 1.3062021411203671e-05, + "loss": 0.8599, + "step": 4679 + }, + { + "epoch": 0.419049750965359, + "grad_norm": 0.9613061690080046, + "learning_rate": 1.3059260304786025e-05, + "loss": 0.8276, + "step": 4680 + }, + { + "epoch": 0.41913929151043705, + "grad_norm": 0.8375156033115455, + "learning_rate": 1.3056498941033375e-05, + "loss": 0.7958, + "step": 4681 + }, + { + "epoch": 0.41922883205551514, + "grad_norm": 1.1478593726725939, + "learning_rate": 1.3053737320177995e-05, + "loss": 0.8488, + "step": 4682 + }, + { + "epoch": 0.4193183726005932, + "grad_norm": 0.9092129667055416, + "learning_rate": 1.3050975442452179e-05, + "loss": 0.8679, + "step": 4683 + }, + { + "epoch": 0.4194079131456713, + "grad_norm": 0.982886630540918, + "learning_rate": 1.3048213308088253e-05, + "loss": 0.8845, + "step": 4684 + }, + { + "epoch": 0.41949745369074937, + "grad_norm": 0.9913852260384906, + "learning_rate": 1.3045450917318558e-05, + "loss": 0.8002, + "step": 4685 + }, + { + "epoch": 0.4195869942358274, + "grad_norm": 1.0569129500700625, + "learning_rate": 1.3042688270375456e-05, + "loss": 0.8956, + "step": 4686 + }, + { + "epoch": 0.4196765347809055, + "grad_norm": 0.8801706474732551, + "learning_rate": 1.3039925367491331e-05, + "loss": 0.8812, + "step": 4687 + }, + { + "epoch": 0.41976607532598353, + "grad_norm": 1.2044954002253259, + "learning_rate": 1.303716220889859e-05, + "loss": 0.9146, + "step": 4688 + }, + { + "epoch": 0.4198556158710616, + "grad_norm": 1.0281304338884343, + "learning_rate": 1.3034398794829661e-05, + "loss": 0.8599, + "step": 4689 + }, + { + "epoch": 0.41994515641613966, + "grad_norm": 0.8643529163147792, + "learning_rate": 1.3031635125516994e-05, + "loss": 0.7747, + "step": 4690 + }, + { + "epoch": 0.42003469696121776, + "grad_norm": 0.9820525966487977, + "learning_rate": 1.3028871201193058e-05, + "loss": 0.861, + "step": 4691 + }, + { + "epoch": 0.4201242375062958, + "grad_norm": 0.9372381839014928, + "learning_rate": 1.3026107022090351e-05, + "loss": 0.8248, + "step": 4692 + }, + { + "epoch": 0.4202137780513739, + "grad_norm": 0.8919571994048802, + "learning_rate": 1.3023342588441379e-05, + "loss": 0.8853, + "step": 4693 + }, + { + "epoch": 0.420303318596452, + "grad_norm": 0.9153850318594442, + "learning_rate": 1.3020577900478682e-05, + "loss": 0.8676, + "step": 4694 + }, + { + "epoch": 0.42039285914153, + "grad_norm": 0.9430614114038058, + "learning_rate": 1.3017812958434812e-05, + "loss": 0.8321, + "step": 4695 + }, + { + "epoch": 0.4204823996866081, + "grad_norm": 0.9332423052638498, + "learning_rate": 1.3015047762542353e-05, + "loss": 0.8643, + "step": 4696 + }, + { + "epoch": 0.42057194023168615, + "grad_norm": 0.9722117021221077, + "learning_rate": 1.3012282313033904e-05, + "loss": 0.885, + "step": 4697 + }, + { + "epoch": 0.42066148077676424, + "grad_norm": 0.9412990551681779, + "learning_rate": 1.3009516610142076e-05, + "loss": 0.8553, + "step": 4698 + }, + { + "epoch": 0.4207510213218423, + "grad_norm": 0.9931320570131007, + "learning_rate": 1.3006750654099522e-05, + "loss": 0.8645, + "step": 4699 + }, + { + "epoch": 0.42084056186692037, + "grad_norm": 0.8885940695753026, + "learning_rate": 1.3003984445138905e-05, + "loss": 0.8886, + "step": 4700 + }, + { + "epoch": 0.4209301024119984, + "grad_norm": 0.9826481640600054, + "learning_rate": 1.3001217983492898e-05, + "loss": 0.8198, + "step": 4701 + }, + { + "epoch": 0.4210196429570765, + "grad_norm": 1.1667617963905261, + "learning_rate": 1.2998451269394216e-05, + "loss": 0.8006, + "step": 4702 + }, + { + "epoch": 0.4211091835021546, + "grad_norm": 0.9579931360581966, + "learning_rate": 1.2995684303075591e-05, + "loss": 0.8363, + "step": 4703 + }, + { + "epoch": 0.42119872404723263, + "grad_norm": 1.1073316128782695, + "learning_rate": 1.2992917084769757e-05, + "loss": 0.8684, + "step": 4704 + }, + { + "epoch": 0.4212882645923107, + "grad_norm": 0.9806731566472836, + "learning_rate": 1.2990149614709493e-05, + "loss": 0.8486, + "step": 4705 + }, + { + "epoch": 0.42137780513738876, + "grad_norm": 0.9035359947952818, + "learning_rate": 1.2987381893127591e-05, + "loss": 0.8092, + "step": 4706 + }, + { + "epoch": 0.42146734568246685, + "grad_norm": 0.9753732270507935, + "learning_rate": 1.2984613920256852e-05, + "loss": 0.8637, + "step": 4707 + }, + { + "epoch": 0.4215568862275449, + "grad_norm": 0.9167516545821977, + "learning_rate": 1.2981845696330122e-05, + "loss": 0.884, + "step": 4708 + }, + { + "epoch": 0.421646426772623, + "grad_norm": 0.8722929779588924, + "learning_rate": 1.2979077221580247e-05, + "loss": 0.8222, + "step": 4709 + }, + { + "epoch": 0.421735967317701, + "grad_norm": 0.9808933749379851, + "learning_rate": 1.2976308496240102e-05, + "loss": 0.874, + "step": 4710 + }, + { + "epoch": 0.4218255078627791, + "grad_norm": 0.896217722491882, + "learning_rate": 1.2973539520542589e-05, + "loss": 0.8845, + "step": 4711 + }, + { + "epoch": 0.4219150484078572, + "grad_norm": 0.9967614285525078, + "learning_rate": 1.297077029472062e-05, + "loss": 0.8759, + "step": 4712 + }, + { + "epoch": 0.42200458895293524, + "grad_norm": 0.9951832322325717, + "learning_rate": 1.2968000819007131e-05, + "loss": 0.8939, + "step": 4713 + }, + { + "epoch": 0.42209412949801334, + "grad_norm": 0.9403580223141892, + "learning_rate": 1.2965231093635092e-05, + "loss": 0.892, + "step": 4714 + }, + { + "epoch": 0.4221836700430914, + "grad_norm": 0.9695860500395811, + "learning_rate": 1.2962461118837472e-05, + "loss": 0.8509, + "step": 4715 + }, + { + "epoch": 0.42227321058816947, + "grad_norm": 0.9387882227536882, + "learning_rate": 1.2959690894847274e-05, + "loss": 0.8307, + "step": 4716 + }, + { + "epoch": 0.4223627511332475, + "grad_norm": 0.8952646394499433, + "learning_rate": 1.2956920421897527e-05, + "loss": 0.8139, + "step": 4717 + }, + { + "epoch": 0.4224522916783256, + "grad_norm": 0.9156342739196973, + "learning_rate": 1.2954149700221271e-05, + "loss": 0.8613, + "step": 4718 + }, + { + "epoch": 0.42254183222340364, + "grad_norm": 0.9192123322657759, + "learning_rate": 1.2951378730051566e-05, + "loss": 0.8275, + "step": 4719 + }, + { + "epoch": 0.42263137276848173, + "grad_norm": 0.9319667696245016, + "learning_rate": 1.2948607511621498e-05, + "loss": 0.8342, + "step": 4720 + }, + { + "epoch": 0.4227209133135598, + "grad_norm": 0.9367606521278115, + "learning_rate": 1.2945836045164177e-05, + "loss": 0.8066, + "step": 4721 + }, + { + "epoch": 0.42281045385863786, + "grad_norm": 0.920752247593063, + "learning_rate": 1.294306433091273e-05, + "loss": 0.8216, + "step": 4722 + }, + { + "epoch": 0.42289999440371595, + "grad_norm": 0.9868429618607599, + "learning_rate": 1.2940292369100297e-05, + "loss": 0.9433, + "step": 4723 + }, + { + "epoch": 0.422989534948794, + "grad_norm": 1.0015056418035166, + "learning_rate": 1.2937520159960055e-05, + "loss": 0.9041, + "step": 4724 + }, + { + "epoch": 0.4230790754938721, + "grad_norm": 0.9663577835711813, + "learning_rate": 1.2934747703725188e-05, + "loss": 0.7973, + "step": 4725 + }, + { + "epoch": 0.4231686160389501, + "grad_norm": 1.0069102472883023, + "learning_rate": 1.293197500062891e-05, + "loss": 0.8155, + "step": 4726 + }, + { + "epoch": 0.4232581565840282, + "grad_norm": 0.946504808793655, + "learning_rate": 1.2929202050904448e-05, + "loss": 0.8697, + "step": 4727 + }, + { + "epoch": 0.42334769712910625, + "grad_norm": 0.9652805094817695, + "learning_rate": 1.292642885478505e-05, + "loss": 0.9012, + "step": 4728 + }, + { + "epoch": 0.42343723767418434, + "grad_norm": 0.9300322169650518, + "learning_rate": 1.2923655412504e-05, + "loss": 0.8533, + "step": 4729 + }, + { + "epoch": 0.42352677821926243, + "grad_norm": 0.934481759423368, + "learning_rate": 1.2920881724294585e-05, + "loss": 0.8746, + "step": 4730 + }, + { + "epoch": 0.42361631876434047, + "grad_norm": 0.9544057259344606, + "learning_rate": 1.2918107790390111e-05, + "loss": 0.8012, + "step": 4731 + }, + { + "epoch": 0.42370585930941856, + "grad_norm": 0.9059359668812877, + "learning_rate": 1.2915333611023923e-05, + "loss": 0.8878, + "step": 4732 + }, + { + "epoch": 0.4237953998544966, + "grad_norm": 1.0493015692935304, + "learning_rate": 1.2912559186429372e-05, + "loss": 0.9328, + "step": 4733 + }, + { + "epoch": 0.4238849403995747, + "grad_norm": 0.8678960884162599, + "learning_rate": 1.2909784516839832e-05, + "loss": 0.8177, + "step": 4734 + }, + { + "epoch": 0.42397448094465273, + "grad_norm": 0.8443960331048497, + "learning_rate": 1.2907009602488701e-05, + "loss": 0.8822, + "step": 4735 + }, + { + "epoch": 0.4240640214897308, + "grad_norm": 0.9967353630763351, + "learning_rate": 1.2904234443609395e-05, + "loss": 0.9215, + "step": 4736 + }, + { + "epoch": 0.42415356203480886, + "grad_norm": 0.9609524307596268, + "learning_rate": 1.2901459040435352e-05, + "loss": 0.8496, + "step": 4737 + }, + { + "epoch": 0.42424310257988695, + "grad_norm": 0.9394560590312089, + "learning_rate": 1.289868339320003e-05, + "loss": 0.8724, + "step": 4738 + }, + { + "epoch": 0.42433264312496505, + "grad_norm": 0.9842980274260325, + "learning_rate": 1.2895907502136908e-05, + "loss": 0.8831, + "step": 4739 + }, + { + "epoch": 0.4244221836700431, + "grad_norm": 0.9547615978521125, + "learning_rate": 1.289313136747948e-05, + "loss": 0.8291, + "step": 4740 + }, + { + "epoch": 0.4245117242151212, + "grad_norm": 0.8946177388542212, + "learning_rate": 1.2890354989461273e-05, + "loss": 0.8072, + "step": 4741 + }, + { + "epoch": 0.4246012647601992, + "grad_norm": 0.8951148884280952, + "learning_rate": 1.288757836831582e-05, + "loss": 0.7793, + "step": 4742 + }, + { + "epoch": 0.4246908053052773, + "grad_norm": 0.9616023408383729, + "learning_rate": 1.2884801504276684e-05, + "loss": 0.7799, + "step": 4743 + }, + { + "epoch": 0.42478034585035535, + "grad_norm": 0.870720014309664, + "learning_rate": 1.288202439757745e-05, + "loss": 0.8209, + "step": 4744 + }, + { + "epoch": 0.42486988639543344, + "grad_norm": 1.0635366073884072, + "learning_rate": 1.2879247048451715e-05, + "loss": 0.8556, + "step": 4745 + }, + { + "epoch": 0.4249594269405115, + "grad_norm": 1.0119358795930222, + "learning_rate": 1.2876469457133097e-05, + "loss": 0.8674, + "step": 4746 + }, + { + "epoch": 0.42504896748558957, + "grad_norm": 0.9331042827489495, + "learning_rate": 1.2873691623855247e-05, + "loss": 0.8266, + "step": 4747 + }, + { + "epoch": 0.42513850803066766, + "grad_norm": 1.099966397829452, + "learning_rate": 1.287091354885182e-05, + "loss": 0.8358, + "step": 4748 + }, + { + "epoch": 0.4252280485757457, + "grad_norm": 0.9196868924358731, + "learning_rate": 1.28681352323565e-05, + "loss": 0.916, + "step": 4749 + }, + { + "epoch": 0.4253175891208238, + "grad_norm": 0.9279223906877845, + "learning_rate": 1.2865356674602989e-05, + "loss": 0.8443, + "step": 4750 + }, + { + "epoch": 0.42540712966590183, + "grad_norm": 1.0760275318520804, + "learning_rate": 1.2862577875825015e-05, + "loss": 0.797, + "step": 4751 + }, + { + "epoch": 0.4254966702109799, + "grad_norm": 0.9610514551418874, + "learning_rate": 1.2859798836256316e-05, + "loss": 0.799, + "step": 4752 + }, + { + "epoch": 0.42558621075605796, + "grad_norm": 0.9695438381709975, + "learning_rate": 1.2857019556130658e-05, + "loss": 0.8397, + "step": 4753 + }, + { + "epoch": 0.42567575130113605, + "grad_norm": 1.0024527775482661, + "learning_rate": 1.2854240035681826e-05, + "loss": 0.8188, + "step": 4754 + }, + { + "epoch": 0.4257652918462141, + "grad_norm": 0.9561709543887179, + "learning_rate": 1.2851460275143626e-05, + "loss": 0.8084, + "step": 4755 + }, + { + "epoch": 0.4258548323912922, + "grad_norm": 0.8828706487400473, + "learning_rate": 1.2848680274749876e-05, + "loss": 0.8599, + "step": 4756 + }, + { + "epoch": 0.4259443729363703, + "grad_norm": 1.1928364760984327, + "learning_rate": 1.284590003473443e-05, + "loss": 0.8171, + "step": 4757 + }, + { + "epoch": 0.4260339134814483, + "grad_norm": 0.9530531000329019, + "learning_rate": 1.2843119555331139e-05, + "loss": 0.8824, + "step": 4758 + }, + { + "epoch": 0.4261234540265264, + "grad_norm": 1.0290543939752066, + "learning_rate": 1.28403388367739e-05, + "loss": 0.8365, + "step": 4759 + }, + { + "epoch": 0.42621299457160444, + "grad_norm": 0.9407487476072213, + "learning_rate": 1.2837557879296613e-05, + "loss": 0.9077, + "step": 4760 + }, + { + "epoch": 0.42630253511668253, + "grad_norm": 0.8534524626006078, + "learning_rate": 1.2834776683133202e-05, + "loss": 0.827, + "step": 4761 + }, + { + "epoch": 0.4263920756617606, + "grad_norm": 1.037699087004459, + "learning_rate": 1.283199524851762e-05, + "loss": 0.8657, + "step": 4762 + }, + { + "epoch": 0.42648161620683867, + "grad_norm": 0.9486358800844373, + "learning_rate": 1.2829213575683823e-05, + "loss": 0.832, + "step": 4763 + }, + { + "epoch": 0.4265711567519167, + "grad_norm": 0.9472139926666191, + "learning_rate": 1.2826431664865797e-05, + "loss": 0.8794, + "step": 4764 + }, + { + "epoch": 0.4266606972969948, + "grad_norm": 0.8049144071365216, + "learning_rate": 1.2823649516297552e-05, + "loss": 0.811, + "step": 4765 + }, + { + "epoch": 0.4267502378420729, + "grad_norm": 0.9966447106517308, + "learning_rate": 1.2820867130213116e-05, + "loss": 0.7944, + "step": 4766 + }, + { + "epoch": 0.4268397783871509, + "grad_norm": 0.9851354625173271, + "learning_rate": 1.281808450684652e-05, + "loss": 0.8238, + "step": 4767 + }, + { + "epoch": 0.426929318932229, + "grad_norm": 0.9530873972647405, + "learning_rate": 1.2815301646431846e-05, + "loss": 0.8373, + "step": 4768 + }, + { + "epoch": 0.42701885947730706, + "grad_norm": 0.99876390216737, + "learning_rate": 1.2812518549203168e-05, + "loss": 0.8574, + "step": 4769 + }, + { + "epoch": 0.42710840002238515, + "grad_norm": 0.8849457849970673, + "learning_rate": 1.2809735215394594e-05, + "loss": 0.8178, + "step": 4770 + }, + { + "epoch": 0.4271979405674632, + "grad_norm": 0.9821755595379084, + "learning_rate": 1.2806951645240253e-05, + "loss": 0.8326, + "step": 4771 + }, + { + "epoch": 0.4272874811125413, + "grad_norm": 0.8855626146210521, + "learning_rate": 1.2804167838974286e-05, + "loss": 0.8498, + "step": 4772 + }, + { + "epoch": 0.4273770216576193, + "grad_norm": 0.9593581366544753, + "learning_rate": 1.2801383796830856e-05, + "loss": 0.8259, + "step": 4773 + }, + { + "epoch": 0.4274665622026974, + "grad_norm": 0.9956563200185977, + "learning_rate": 1.2798599519044152e-05, + "loss": 0.8627, + "step": 4774 + }, + { + "epoch": 0.4275561027477755, + "grad_norm": 0.8894698609544399, + "learning_rate": 1.2795815005848378e-05, + "loss": 0.7775, + "step": 4775 + }, + { + "epoch": 0.42764564329285354, + "grad_norm": 0.8751912418748008, + "learning_rate": 1.2793030257477751e-05, + "loss": 0.7641, + "step": 4776 + }, + { + "epoch": 0.42773518383793163, + "grad_norm": 0.8747698294072767, + "learning_rate": 1.2790245274166526e-05, + "loss": 0.8426, + "step": 4777 + }, + { + "epoch": 0.42782472438300967, + "grad_norm": 1.170275714882787, + "learning_rate": 1.2787460056148957e-05, + "loss": 0.8104, + "step": 4778 + }, + { + "epoch": 0.42791426492808776, + "grad_norm": 0.8466957303278845, + "learning_rate": 1.2784674603659335e-05, + "loss": 0.8069, + "step": 4779 + }, + { + "epoch": 0.4280038054731658, + "grad_norm": 0.9710348946666589, + "learning_rate": 1.2781888916931957e-05, + "loss": 0.9052, + "step": 4780 + }, + { + "epoch": 0.4280933460182439, + "grad_norm": 0.8892971225807514, + "learning_rate": 1.277910299620115e-05, + "loss": 0.8303, + "step": 4781 + }, + { + "epoch": 0.42818288656332193, + "grad_norm": 0.9745266973023328, + "learning_rate": 1.2776316841701255e-05, + "loss": 0.8228, + "step": 4782 + }, + { + "epoch": 0.4282724271084, + "grad_norm": 0.9101436527507242, + "learning_rate": 1.2773530453666634e-05, + "loss": 0.7861, + "step": 4783 + }, + { + "epoch": 0.4283619676534781, + "grad_norm": 0.8603459675524968, + "learning_rate": 1.277074383233167e-05, + "loss": 0.8688, + "step": 4784 + }, + { + "epoch": 0.42845150819855615, + "grad_norm": 0.8910546863910951, + "learning_rate": 1.2767956977930764e-05, + "loss": 0.8444, + "step": 4785 + }, + { + "epoch": 0.42854104874363425, + "grad_norm": 1.013042514508105, + "learning_rate": 1.2765169890698337e-05, + "loss": 0.8599, + "step": 4786 + }, + { + "epoch": 0.4286305892887123, + "grad_norm": 1.0814816004979944, + "learning_rate": 1.2762382570868828e-05, + "loss": 0.844, + "step": 4787 + }, + { + "epoch": 0.4287201298337904, + "grad_norm": 0.8935973255675718, + "learning_rate": 1.27595950186767e-05, + "loss": 0.8274, + "step": 4788 + }, + { + "epoch": 0.4288096703788684, + "grad_norm": 0.9223805769304506, + "learning_rate": 1.2756807234356432e-05, + "loss": 0.8816, + "step": 4789 + }, + { + "epoch": 0.4288992109239465, + "grad_norm": 0.9805609392151479, + "learning_rate": 1.2754019218142526e-05, + "loss": 0.7898, + "step": 4790 + }, + { + "epoch": 0.42898875146902454, + "grad_norm": 0.9036644494990118, + "learning_rate": 1.2751230970269493e-05, + "loss": 0.8268, + "step": 4791 + }, + { + "epoch": 0.42907829201410264, + "grad_norm": 0.8883477760436611, + "learning_rate": 1.2748442490971877e-05, + "loss": 0.7894, + "step": 4792 + }, + { + "epoch": 0.42916783255918073, + "grad_norm": 1.0228154556689883, + "learning_rate": 1.2745653780484239e-05, + "loss": 0.8773, + "step": 4793 + }, + { + "epoch": 0.42925737310425877, + "grad_norm": 0.9972554405599129, + "learning_rate": 1.2742864839041147e-05, + "loss": 0.8656, + "step": 4794 + }, + { + "epoch": 0.42934691364933686, + "grad_norm": 0.8898273634896448, + "learning_rate": 1.2740075666877205e-05, + "loss": 0.8655, + "step": 4795 + }, + { + "epoch": 0.4294364541944149, + "grad_norm": 0.878411403977995, + "learning_rate": 1.273728626422703e-05, + "loss": 0.7576, + "step": 4796 + }, + { + "epoch": 0.429525994739493, + "grad_norm": 0.8595654190197719, + "learning_rate": 1.2734496631325249e-05, + "loss": 0.895, + "step": 4797 + }, + { + "epoch": 0.429615535284571, + "grad_norm": 0.9624770323553657, + "learning_rate": 1.2731706768406528e-05, + "loss": 0.907, + "step": 4798 + }, + { + "epoch": 0.4297050758296491, + "grad_norm": 1.0601072596173775, + "learning_rate": 1.272891667570553e-05, + "loss": 0.8776, + "step": 4799 + }, + { + "epoch": 0.42979461637472716, + "grad_norm": 0.9388296844225305, + "learning_rate": 1.2726126353456955e-05, + "loss": 0.8274, + "step": 4800 + }, + { + "epoch": 0.42988415691980525, + "grad_norm": 1.0526180882921847, + "learning_rate": 1.272333580189552e-05, + "loss": 0.9228, + "step": 4801 + }, + { + "epoch": 0.42997369746488334, + "grad_norm": 0.9495504636937622, + "learning_rate": 1.2720545021255947e-05, + "loss": 0.8765, + "step": 4802 + }, + { + "epoch": 0.4300632380099614, + "grad_norm": 0.9287615676153879, + "learning_rate": 1.2717754011772992e-05, + "loss": 0.8196, + "step": 4803 + }, + { + "epoch": 0.43015277855503947, + "grad_norm": 0.9412930538689297, + "learning_rate": 1.271496277368143e-05, + "loss": 0.8379, + "step": 4804 + }, + { + "epoch": 0.4302423191001175, + "grad_norm": 0.8732131087061276, + "learning_rate": 1.2712171307216044e-05, + "loss": 0.8842, + "step": 4805 + }, + { + "epoch": 0.4303318596451956, + "grad_norm": 1.0794507928906578, + "learning_rate": 1.2709379612611646e-05, + "loss": 0.8675, + "step": 4806 + }, + { + "epoch": 0.43042140019027364, + "grad_norm": 0.8814229789906701, + "learning_rate": 1.2706587690103062e-05, + "loss": 0.8459, + "step": 4807 + }, + { + "epoch": 0.43051094073535173, + "grad_norm": 0.8801983363210407, + "learning_rate": 1.2703795539925143e-05, + "loss": 0.8062, + "step": 4808 + }, + { + "epoch": 0.43060048128042977, + "grad_norm": 0.9977529720533943, + "learning_rate": 1.2701003162312757e-05, + "loss": 0.8327, + "step": 4809 + }, + { + "epoch": 0.43069002182550786, + "grad_norm": 1.0032653114416341, + "learning_rate": 1.2698210557500783e-05, + "loss": 0.8315, + "step": 4810 + }, + { + "epoch": 0.43077956237058596, + "grad_norm": 1.0009242305469093, + "learning_rate": 1.2695417725724131e-05, + "loss": 0.8891, + "step": 4811 + }, + { + "epoch": 0.430869102915664, + "grad_norm": 0.9127557994630798, + "learning_rate": 1.2692624667217724e-05, + "loss": 0.9202, + "step": 4812 + }, + { + "epoch": 0.4309586434607421, + "grad_norm": 0.8440858240013827, + "learning_rate": 1.2689831382216502e-05, + "loss": 0.8061, + "step": 4813 + }, + { + "epoch": 0.4310481840058201, + "grad_norm": 0.9026101363841126, + "learning_rate": 1.2687037870955431e-05, + "loss": 0.8699, + "step": 4814 + }, + { + "epoch": 0.4311377245508982, + "grad_norm": 0.9270997150201402, + "learning_rate": 1.2684244133669492e-05, + "loss": 0.8513, + "step": 4815 + }, + { + "epoch": 0.43122726509597625, + "grad_norm": 0.8518418837022311, + "learning_rate": 1.2681450170593683e-05, + "loss": 0.857, + "step": 4816 + }, + { + "epoch": 0.43131680564105435, + "grad_norm": 0.9311937806731825, + "learning_rate": 1.2678655981963022e-05, + "loss": 0.855, + "step": 4817 + }, + { + "epoch": 0.4314063461861324, + "grad_norm": 0.8894540801131331, + "learning_rate": 1.2675861568012551e-05, + "loss": 0.8156, + "step": 4818 + }, + { + "epoch": 0.4314958867312105, + "grad_norm": 0.9950315713130442, + "learning_rate": 1.2673066928977323e-05, + "loss": 0.9056, + "step": 4819 + }, + { + "epoch": 0.43158542727628857, + "grad_norm": 1.0382160882555977, + "learning_rate": 1.2670272065092417e-05, + "loss": 0.8151, + "step": 4820 + }, + { + "epoch": 0.4316749678213666, + "grad_norm": 0.9207360957385227, + "learning_rate": 1.2667476976592925e-05, + "loss": 0.7916, + "step": 4821 + }, + { + "epoch": 0.4317645083664447, + "grad_norm": 0.9725214312370394, + "learning_rate": 1.2664681663713963e-05, + "loss": 0.8183, + "step": 4822 + }, + { + "epoch": 0.43185404891152274, + "grad_norm": 0.9327426230225193, + "learning_rate": 1.2661886126690664e-05, + "loss": 0.8434, + "step": 4823 + }, + { + "epoch": 0.43194358945660083, + "grad_norm": 0.9235941356474715, + "learning_rate": 1.2659090365758176e-05, + "loss": 0.8293, + "step": 4824 + }, + { + "epoch": 0.43203313000167887, + "grad_norm": 0.851534251188331, + "learning_rate": 1.2656294381151673e-05, + "loss": 0.8013, + "step": 4825 + }, + { + "epoch": 0.43212267054675696, + "grad_norm": 0.9258449941398924, + "learning_rate": 1.2653498173106344e-05, + "loss": 0.8544, + "step": 4826 + }, + { + "epoch": 0.432212211091835, + "grad_norm": 0.9362566732375528, + "learning_rate": 1.2650701741857391e-05, + "loss": 0.8508, + "step": 4827 + }, + { + "epoch": 0.4323017516369131, + "grad_norm": 0.9940060583671982, + "learning_rate": 1.2647905087640051e-05, + "loss": 0.7994, + "step": 4828 + }, + { + "epoch": 0.4323912921819912, + "grad_norm": 1.1747164512861237, + "learning_rate": 1.2645108210689561e-05, + "loss": 0.8672, + "step": 4829 + }, + { + "epoch": 0.4324808327270692, + "grad_norm": 1.0171557734206085, + "learning_rate": 1.2642311111241185e-05, + "loss": 0.8463, + "step": 4830 + }, + { + "epoch": 0.4325703732721473, + "grad_norm": 0.9474973124697055, + "learning_rate": 1.2639513789530215e-05, + "loss": 0.8719, + "step": 4831 + }, + { + "epoch": 0.43265991381722535, + "grad_norm": 0.9634603113537945, + "learning_rate": 1.2636716245791945e-05, + "loss": 0.8977, + "step": 4832 + }, + { + "epoch": 0.43274945436230344, + "grad_norm": 0.9062129184938401, + "learning_rate": 1.2633918480261693e-05, + "loss": 0.8575, + "step": 4833 + }, + { + "epoch": 0.4328389949073815, + "grad_norm": 0.9513956853223187, + "learning_rate": 1.2631120493174804e-05, + "loss": 0.8477, + "step": 4834 + }, + { + "epoch": 0.4329285354524596, + "grad_norm": 0.9756218803232527, + "learning_rate": 1.2628322284766635e-05, + "loss": 0.8697, + "step": 4835 + }, + { + "epoch": 0.4330180759975376, + "grad_norm": 0.9539701351709329, + "learning_rate": 1.2625523855272556e-05, + "loss": 0.831, + "step": 4836 + }, + { + "epoch": 0.4331076165426157, + "grad_norm": 0.9269016930659613, + "learning_rate": 1.2622725204927968e-05, + "loss": 0.8674, + "step": 4837 + }, + { + "epoch": 0.4331971570876938, + "grad_norm": 0.9579227621477914, + "learning_rate": 1.2619926333968285e-05, + "loss": 0.8577, + "step": 4838 + }, + { + "epoch": 0.43328669763277183, + "grad_norm": 0.8837061266557809, + "learning_rate": 1.2617127242628932e-05, + "loss": 0.8776, + "step": 4839 + }, + { + "epoch": 0.4333762381778499, + "grad_norm": 0.9463837983354312, + "learning_rate": 1.2614327931145366e-05, + "loss": 0.8372, + "step": 4840 + }, + { + "epoch": 0.43346577872292796, + "grad_norm": 0.8972352040612186, + "learning_rate": 1.2611528399753055e-05, + "loss": 0.7941, + "step": 4841 + }, + { + "epoch": 0.43355531926800606, + "grad_norm": 1.0377929563538764, + "learning_rate": 1.2608728648687482e-05, + "loss": 0.8392, + "step": 4842 + }, + { + "epoch": 0.4336448598130841, + "grad_norm": 1.0271316609340724, + "learning_rate": 1.2605928678184158e-05, + "loss": 0.854, + "step": 4843 + }, + { + "epoch": 0.4337344003581622, + "grad_norm": 0.9741405693757601, + "learning_rate": 1.2603128488478606e-05, + "loss": 0.7994, + "step": 4844 + }, + { + "epoch": 0.4338239409032402, + "grad_norm": 1.0124372921632732, + "learning_rate": 1.260032807980637e-05, + "loss": 0.7715, + "step": 4845 + }, + { + "epoch": 0.4339134814483183, + "grad_norm": 0.849358403799566, + "learning_rate": 1.2597527452403007e-05, + "loss": 0.8, + "step": 4846 + }, + { + "epoch": 0.4340030219933964, + "grad_norm": 0.8999586212096153, + "learning_rate": 1.2594726606504099e-05, + "loss": 0.8974, + "step": 4847 + }, + { + "epoch": 0.43409256253847445, + "grad_norm": 0.9943050642371936, + "learning_rate": 1.2591925542345244e-05, + "loss": 0.828, + "step": 4848 + }, + { + "epoch": 0.43418210308355254, + "grad_norm": 0.9287191183927296, + "learning_rate": 1.258912426016206e-05, + "loss": 0.8001, + "step": 4849 + }, + { + "epoch": 0.4342716436286306, + "grad_norm": 1.1642083723544498, + "learning_rate": 1.2586322760190183e-05, + "loss": 0.8739, + "step": 4850 + }, + { + "epoch": 0.43436118417370867, + "grad_norm": 0.9312804456714632, + "learning_rate": 1.258352104266526e-05, + "loss": 0.8281, + "step": 4851 + }, + { + "epoch": 0.4344507247187867, + "grad_norm": 0.956289400656988, + "learning_rate": 1.2580719107822966e-05, + "loss": 0.8484, + "step": 4852 + }, + { + "epoch": 0.4345402652638648, + "grad_norm": 0.8857536963242103, + "learning_rate": 1.2577916955898993e-05, + "loss": 0.8614, + "step": 4853 + }, + { + "epoch": 0.43462980580894284, + "grad_norm": 0.9593652202117886, + "learning_rate": 1.2575114587129042e-05, + "loss": 0.8533, + "step": 4854 + }, + { + "epoch": 0.43471934635402093, + "grad_norm": 0.9766609288880667, + "learning_rate": 1.2572312001748845e-05, + "loss": 0.8229, + "step": 4855 + }, + { + "epoch": 0.434808886899099, + "grad_norm": 0.9907412472258096, + "learning_rate": 1.2569509199994147e-05, + "loss": 0.8451, + "step": 4856 + }, + { + "epoch": 0.43489842744417706, + "grad_norm": 0.9600086977177898, + "learning_rate": 1.2566706182100706e-05, + "loss": 0.8456, + "step": 4857 + }, + { + "epoch": 0.43498796798925515, + "grad_norm": 0.8453638121218173, + "learning_rate": 1.256390294830431e-05, + "loss": 0.7841, + "step": 4858 + }, + { + "epoch": 0.4350775085343332, + "grad_norm": 0.8854204102440567, + "learning_rate": 1.2561099498840748e-05, + "loss": 0.8831, + "step": 4859 + }, + { + "epoch": 0.4351670490794113, + "grad_norm": 0.92437048691386, + "learning_rate": 1.2558295833945842e-05, + "loss": 0.8276, + "step": 4860 + }, + { + "epoch": 0.4352565896244893, + "grad_norm": 0.9321453878329122, + "learning_rate": 1.2555491953855427e-05, + "loss": 0.7855, + "step": 4861 + }, + { + "epoch": 0.4353461301695674, + "grad_norm": 0.9238108323672232, + "learning_rate": 1.2552687858805359e-05, + "loss": 0.8151, + "step": 4862 + }, + { + "epoch": 0.43543567071464545, + "grad_norm": 0.9826108417409795, + "learning_rate": 1.2549883549031505e-05, + "loss": 0.8301, + "step": 4863 + }, + { + "epoch": 0.43552521125972354, + "grad_norm": 1.0144682853648659, + "learning_rate": 1.2547079024769757e-05, + "loss": 0.8668, + "step": 4864 + }, + { + "epoch": 0.43561475180480164, + "grad_norm": 0.9581370800110325, + "learning_rate": 1.2544274286256021e-05, + "loss": 0.8043, + "step": 4865 + }, + { + "epoch": 0.4357042923498797, + "grad_norm": 0.9355672582910216, + "learning_rate": 1.2541469333726225e-05, + "loss": 0.8319, + "step": 4866 + }, + { + "epoch": 0.43579383289495777, + "grad_norm": 0.8879904719894574, + "learning_rate": 1.2538664167416308e-05, + "loss": 0.8221, + "step": 4867 + }, + { + "epoch": 0.4358833734400358, + "grad_norm": 0.8914566367794373, + "learning_rate": 1.2535858787562237e-05, + "loss": 0.8331, + "step": 4868 + }, + { + "epoch": 0.4359729139851139, + "grad_norm": 0.9439988126122387, + "learning_rate": 1.2533053194399984e-05, + "loss": 0.8195, + "step": 4869 + }, + { + "epoch": 0.43606245453019193, + "grad_norm": 1.032441963435167, + "learning_rate": 1.2530247388165553e-05, + "loss": 0.7837, + "step": 4870 + }, + { + "epoch": 0.43615199507527, + "grad_norm": 0.9839367158883598, + "learning_rate": 1.2527441369094958e-05, + "loss": 0.9404, + "step": 4871 + }, + { + "epoch": 0.43624153562034806, + "grad_norm": 0.8936881609992845, + "learning_rate": 1.252463513742423e-05, + "loss": 0.861, + "step": 4872 + }, + { + "epoch": 0.43633107616542616, + "grad_norm": 0.9919945228462781, + "learning_rate": 1.2521828693389422e-05, + "loss": 0.8732, + "step": 4873 + }, + { + "epoch": 0.43642061671050425, + "grad_norm": 0.9998797561955459, + "learning_rate": 1.25190220372266e-05, + "loss": 0.8568, + "step": 4874 + }, + { + "epoch": 0.4365101572555823, + "grad_norm": 0.8743666337756882, + "learning_rate": 1.2516215169171854e-05, + "loss": 0.902, + "step": 4875 + }, + { + "epoch": 0.4365996978006604, + "grad_norm": 0.9929221273125726, + "learning_rate": 1.251340808946129e-05, + "loss": 0.8634, + "step": 4876 + }, + { + "epoch": 0.4366892383457384, + "grad_norm": 0.9164505987848556, + "learning_rate": 1.2510600798331028e-05, + "loss": 0.8194, + "step": 4877 + }, + { + "epoch": 0.4367787788908165, + "grad_norm": 0.9094308825181555, + "learning_rate": 1.2507793296017203e-05, + "loss": 0.7992, + "step": 4878 + }, + { + "epoch": 0.43686831943589455, + "grad_norm": 0.9837583632315312, + "learning_rate": 1.2504985582755981e-05, + "loss": 0.7807, + "step": 4879 + }, + { + "epoch": 0.43695785998097264, + "grad_norm": 0.9395724757938536, + "learning_rate": 1.2502177658783538e-05, + "loss": 0.8375, + "step": 4880 + }, + { + "epoch": 0.4370474005260507, + "grad_norm": 0.9354370429545157, + "learning_rate": 1.249936952433606e-05, + "loss": 0.8013, + "step": 4881 + }, + { + "epoch": 0.43713694107112877, + "grad_norm": 1.0593030466375308, + "learning_rate": 1.2496561179649764e-05, + "loss": 0.8032, + "step": 4882 + }, + { + "epoch": 0.43722648161620686, + "grad_norm": 0.989252234045883, + "learning_rate": 1.2493752624960879e-05, + "loss": 0.8859, + "step": 4883 + }, + { + "epoch": 0.4373160221612849, + "grad_norm": 0.9363586019273621, + "learning_rate": 1.2490943860505647e-05, + "loss": 0.8421, + "step": 4884 + }, + { + "epoch": 0.437405562706363, + "grad_norm": 0.9116939840105585, + "learning_rate": 1.2488134886520334e-05, + "loss": 0.8249, + "step": 4885 + }, + { + "epoch": 0.43749510325144103, + "grad_norm": 0.9944678951709268, + "learning_rate": 1.2485325703241226e-05, + "loss": 0.7938, + "step": 4886 + }, + { + "epoch": 0.4375846437965191, + "grad_norm": 1.0142632450539617, + "learning_rate": 1.2482516310904616e-05, + "loss": 0.8001, + "step": 4887 + }, + { + "epoch": 0.43767418434159716, + "grad_norm": 1.0490125939385535, + "learning_rate": 1.2479706709746821e-05, + "loss": 0.8641, + "step": 4888 + }, + { + "epoch": 0.43776372488667525, + "grad_norm": 1.0543424651295565, + "learning_rate": 1.2476896900004185e-05, + "loss": 0.8338, + "step": 4889 + }, + { + "epoch": 0.4378532654317533, + "grad_norm": 0.9110593979964402, + "learning_rate": 1.247408688191305e-05, + "loss": 0.8224, + "step": 4890 + }, + { + "epoch": 0.4379428059768314, + "grad_norm": 0.9884299234095539, + "learning_rate": 1.2471276655709788e-05, + "loss": 0.8014, + "step": 4891 + }, + { + "epoch": 0.4380323465219095, + "grad_norm": 0.9723874547467449, + "learning_rate": 1.2468466221630787e-05, + "loss": 0.8338, + "step": 4892 + }, + { + "epoch": 0.4381218870669875, + "grad_norm": 0.9351858518365292, + "learning_rate": 1.2465655579912453e-05, + "loss": 0.8033, + "step": 4893 + }, + { + "epoch": 0.4382114276120656, + "grad_norm": 0.9688692987112623, + "learning_rate": 1.2462844730791203e-05, + "loss": 0.8242, + "step": 4894 + }, + { + "epoch": 0.43830096815714364, + "grad_norm": 0.940403444449089, + "learning_rate": 1.2460033674503484e-05, + "loss": 0.8321, + "step": 4895 + }, + { + "epoch": 0.43839050870222174, + "grad_norm": 0.9515037006589611, + "learning_rate": 1.2457222411285745e-05, + "loss": 0.8176, + "step": 4896 + }, + { + "epoch": 0.4384800492472998, + "grad_norm": 0.8863816820392372, + "learning_rate": 1.2454410941374469e-05, + "loss": 0.8396, + "step": 4897 + }, + { + "epoch": 0.43856958979237787, + "grad_norm": 1.0309614707191332, + "learning_rate": 1.2451599265006138e-05, + "loss": 0.8648, + "step": 4898 + }, + { + "epoch": 0.4386591303374559, + "grad_norm": 1.004976265427351, + "learning_rate": 1.2448787382417269e-05, + "loss": 0.8449, + "step": 4899 + }, + { + "epoch": 0.438748670882534, + "grad_norm": 1.0998398318460583, + "learning_rate": 1.2445975293844383e-05, + "loss": 0.8284, + "step": 4900 + }, + { + "epoch": 0.4388382114276121, + "grad_norm": 0.8518638399587809, + "learning_rate": 1.2443162999524027e-05, + "loss": 0.7896, + "step": 4901 + }, + { + "epoch": 0.43892775197269013, + "grad_norm": 0.9732771886053379, + "learning_rate": 1.244035049969276e-05, + "loss": 0.9182, + "step": 4902 + }, + { + "epoch": 0.4390172925177682, + "grad_norm": 0.9420961100348079, + "learning_rate": 1.2437537794587163e-05, + "loss": 0.8357, + "step": 4903 + }, + { + "epoch": 0.43910683306284626, + "grad_norm": 0.9314178207335466, + "learning_rate": 1.243472488444383e-05, + "loss": 0.8404, + "step": 4904 + }, + { + "epoch": 0.43919637360792435, + "grad_norm": 0.9242272731296275, + "learning_rate": 1.2431911769499372e-05, + "loss": 0.8412, + "step": 4905 + }, + { + "epoch": 0.4392859141530024, + "grad_norm": 0.9995187945094381, + "learning_rate": 1.2429098449990423e-05, + "loss": 0.8139, + "step": 4906 + }, + { + "epoch": 0.4393754546980805, + "grad_norm": 0.8723115759546067, + "learning_rate": 1.2426284926153627e-05, + "loss": 0.8221, + "step": 4907 + }, + { + "epoch": 0.4394649952431585, + "grad_norm": 0.9078321455272073, + "learning_rate": 1.242347119822565e-05, + "loss": 0.9048, + "step": 4908 + }, + { + "epoch": 0.4395545357882366, + "grad_norm": 1.020795044404057, + "learning_rate": 1.2420657266443172e-05, + "loss": 0.7848, + "step": 4909 + }, + { + "epoch": 0.4396440763333147, + "grad_norm": 1.0316547736063222, + "learning_rate": 1.2417843131042894e-05, + "loss": 0.8401, + "step": 4910 + }, + { + "epoch": 0.43973361687839274, + "grad_norm": 0.9798567204117883, + "learning_rate": 1.2415028792261529e-05, + "loss": 0.8512, + "step": 4911 + }, + { + "epoch": 0.43982315742347083, + "grad_norm": 1.0317789462671159, + "learning_rate": 1.2412214250335815e-05, + "loss": 0.834, + "step": 4912 + }, + { + "epoch": 0.43991269796854887, + "grad_norm": 0.8923677523236467, + "learning_rate": 1.24093995055025e-05, + "loss": 0.8545, + "step": 4913 + }, + { + "epoch": 0.44000223851362696, + "grad_norm": 0.8500561079129809, + "learning_rate": 1.2406584557998347e-05, + "loss": 0.8319, + "step": 4914 + }, + { + "epoch": 0.440091779058705, + "grad_norm": 0.9447697684315952, + "learning_rate": 1.240376940806014e-05, + "loss": 0.8887, + "step": 4915 + }, + { + "epoch": 0.4401813196037831, + "grad_norm": 0.8556924786478811, + "learning_rate": 1.240095405592469e-05, + "loss": 0.8691, + "step": 4916 + }, + { + "epoch": 0.44027086014886113, + "grad_norm": 0.9621086002716165, + "learning_rate": 1.2398138501828806e-05, + "loss": 0.8927, + "step": 4917 + }, + { + "epoch": 0.4403604006939392, + "grad_norm": 1.0390473445427628, + "learning_rate": 1.2395322746009323e-05, + "loss": 0.8319, + "step": 4918 + }, + { + "epoch": 0.4404499412390173, + "grad_norm": 0.9989174376592065, + "learning_rate": 1.2392506788703103e-05, + "loss": 0.8595, + "step": 4919 + }, + { + "epoch": 0.44053948178409535, + "grad_norm": 0.8543573444440964, + "learning_rate": 1.2389690630147004e-05, + "loss": 0.8381, + "step": 4920 + }, + { + "epoch": 0.44062902232917345, + "grad_norm": 0.9305264194522433, + "learning_rate": 1.2386874270577918e-05, + "loss": 0.811, + "step": 4921 + }, + { + "epoch": 0.4407185628742515, + "grad_norm": 0.9129230439157308, + "learning_rate": 1.2384057710232747e-05, + "loss": 0.8336, + "step": 4922 + }, + { + "epoch": 0.4408081034193296, + "grad_norm": 1.021099217122807, + "learning_rate": 1.2381240949348407e-05, + "loss": 0.8498, + "step": 4923 + }, + { + "epoch": 0.4408976439644076, + "grad_norm": 0.9470821676390883, + "learning_rate": 1.2378423988161843e-05, + "loss": 0.8161, + "step": 4924 + }, + { + "epoch": 0.4409871845094857, + "grad_norm": 1.062166192138627, + "learning_rate": 1.2375606826910001e-05, + "loss": 0.8032, + "step": 4925 + }, + { + "epoch": 0.44107672505456375, + "grad_norm": 1.184185396934736, + "learning_rate": 1.2372789465829853e-05, + "loss": 0.864, + "step": 4926 + }, + { + "epoch": 0.44116626559964184, + "grad_norm": 0.9313128033183719, + "learning_rate": 1.2369971905158389e-05, + "loss": 0.8264, + "step": 4927 + }, + { + "epoch": 0.44125580614471993, + "grad_norm": 1.0072106537347125, + "learning_rate": 1.2367154145132609e-05, + "loss": 0.7892, + "step": 4928 + }, + { + "epoch": 0.44134534668979797, + "grad_norm": 0.9670566761518096, + "learning_rate": 1.2364336185989538e-05, + "loss": 0.88, + "step": 4929 + }, + { + "epoch": 0.44143488723487606, + "grad_norm": 0.8704635214354152, + "learning_rate": 1.2361518027966213e-05, + "loss": 0.8261, + "step": 4930 + }, + { + "epoch": 0.4415244277799541, + "grad_norm": 0.951435724989145, + "learning_rate": 1.2358699671299685e-05, + "loss": 0.7763, + "step": 4931 + }, + { + "epoch": 0.4416139683250322, + "grad_norm": 1.0785750820972066, + "learning_rate": 1.2355881116227028e-05, + "loss": 0.8176, + "step": 4932 + }, + { + "epoch": 0.44170350887011023, + "grad_norm": 1.2443039006183512, + "learning_rate": 1.2353062362985329e-05, + "loss": 0.8671, + "step": 4933 + }, + { + "epoch": 0.4417930494151883, + "grad_norm": 0.885145197162479, + "learning_rate": 1.2350243411811691e-05, + "loss": 0.8548, + "step": 4934 + }, + { + "epoch": 0.44188258996026636, + "grad_norm": 0.9248300110923634, + "learning_rate": 1.2347424262943235e-05, + "loss": 0.8323, + "step": 4935 + }, + { + "epoch": 0.44197213050534445, + "grad_norm": 0.9126143159353564, + "learning_rate": 1.2344604916617102e-05, + "loss": 0.8299, + "step": 4936 + }, + { + "epoch": 0.44206167105042254, + "grad_norm": 1.0233899041280883, + "learning_rate": 1.2341785373070442e-05, + "loss": 0.8526, + "step": 4937 + }, + { + "epoch": 0.4421512115955006, + "grad_norm": 0.950629001855324, + "learning_rate": 1.2338965632540428e-05, + "loss": 0.733, + "step": 4938 + }, + { + "epoch": 0.4422407521405787, + "grad_norm": 1.032065747350411, + "learning_rate": 1.2336145695264247e-05, + "loss": 0.8403, + "step": 4939 + }, + { + "epoch": 0.4423302926856567, + "grad_norm": 0.8957667603492465, + "learning_rate": 1.2333325561479106e-05, + "loss": 0.8039, + "step": 4940 + }, + { + "epoch": 0.4424198332307348, + "grad_norm": 0.9266927363038796, + "learning_rate": 1.2330505231422219e-05, + "loss": 0.835, + "step": 4941 + }, + { + "epoch": 0.44250937377581284, + "grad_norm": 1.0413648888592126, + "learning_rate": 1.2327684705330825e-05, + "loss": 0.8436, + "step": 4942 + }, + { + "epoch": 0.44259891432089093, + "grad_norm": 0.8938951236187573, + "learning_rate": 1.2324863983442184e-05, + "loss": 0.8329, + "step": 4943 + }, + { + "epoch": 0.44268845486596897, + "grad_norm": 0.8915640194846318, + "learning_rate": 1.2322043065993556e-05, + "loss": 0.8559, + "step": 4944 + }, + { + "epoch": 0.44277799541104707, + "grad_norm": 0.9845823567038516, + "learning_rate": 1.2319221953222232e-05, + "loss": 0.7961, + "step": 4945 + }, + { + "epoch": 0.44286753595612516, + "grad_norm": 0.9210903379218929, + "learning_rate": 1.2316400645365518e-05, + "loss": 0.8894, + "step": 4946 + }, + { + "epoch": 0.4429570765012032, + "grad_norm": 0.9067395159248738, + "learning_rate": 1.2313579142660727e-05, + "loss": 0.8569, + "step": 4947 + }, + { + "epoch": 0.4430466170462813, + "grad_norm": 0.8280645533265587, + "learning_rate": 1.2310757445345199e-05, + "loss": 0.8803, + "step": 4948 + }, + { + "epoch": 0.4431361575913593, + "grad_norm": 0.9893197676544135, + "learning_rate": 1.2307935553656288e-05, + "loss": 0.8423, + "step": 4949 + }, + { + "epoch": 0.4432256981364374, + "grad_norm": 0.9962626141771275, + "learning_rate": 1.2305113467831356e-05, + "loss": 0.8947, + "step": 4950 + }, + { + "epoch": 0.44331523868151546, + "grad_norm": 1.0520409540531206, + "learning_rate": 1.230229118810779e-05, + "loss": 0.8478, + "step": 4951 + }, + { + "epoch": 0.44340477922659355, + "grad_norm": 0.9643138102887774, + "learning_rate": 1.2299468714722993e-05, + "loss": 0.8375, + "step": 4952 + }, + { + "epoch": 0.4434943197716716, + "grad_norm": 0.936928678486314, + "learning_rate": 1.229664604791438e-05, + "loss": 0.8371, + "step": 4953 + }, + { + "epoch": 0.4435838603167497, + "grad_norm": 0.9232266086815668, + "learning_rate": 1.2293823187919388e-05, + "loss": 0.8445, + "step": 4954 + }, + { + "epoch": 0.44367340086182777, + "grad_norm": 1.0084610926388942, + "learning_rate": 1.2291000134975462e-05, + "loss": 0.8885, + "step": 4955 + }, + { + "epoch": 0.4437629414069058, + "grad_norm": 0.8668814579577111, + "learning_rate": 1.228817688932007e-05, + "loss": 0.8227, + "step": 4956 + }, + { + "epoch": 0.4438524819519839, + "grad_norm": 0.9969676529499523, + "learning_rate": 1.2285353451190696e-05, + "loss": 0.8772, + "step": 4957 + }, + { + "epoch": 0.44394202249706194, + "grad_norm": 0.9952897460148868, + "learning_rate": 1.2282529820824837e-05, + "loss": 0.8021, + "step": 4958 + }, + { + "epoch": 0.44403156304214003, + "grad_norm": 0.9623233913075947, + "learning_rate": 1.2279705998460008e-05, + "loss": 0.8399, + "step": 4959 + }, + { + "epoch": 0.44412110358721807, + "grad_norm": 0.9248963466963206, + "learning_rate": 1.2276881984333738e-05, + "loss": 0.846, + "step": 4960 + }, + { + "epoch": 0.44421064413229616, + "grad_norm": 1.0384997867644628, + "learning_rate": 1.2274057778683574e-05, + "loss": 0.8739, + "step": 4961 + }, + { + "epoch": 0.4443001846773742, + "grad_norm": 1.1292807330123693, + "learning_rate": 1.2271233381747082e-05, + "loss": 0.8295, + "step": 4962 + }, + { + "epoch": 0.4443897252224523, + "grad_norm": 0.9459633704729262, + "learning_rate": 1.2268408793761839e-05, + "loss": 0.9017, + "step": 4963 + }, + { + "epoch": 0.4444792657675304, + "grad_norm": 1.035876805320125, + "learning_rate": 1.2265584014965439e-05, + "loss": 0.9068, + "step": 4964 + }, + { + "epoch": 0.4445688063126084, + "grad_norm": 0.9490420753535469, + "learning_rate": 1.2262759045595497e-05, + "loss": 0.8556, + "step": 4965 + }, + { + "epoch": 0.4446583468576865, + "grad_norm": 0.9694011833638522, + "learning_rate": 1.2259933885889636e-05, + "loss": 0.8797, + "step": 4966 + }, + { + "epoch": 0.44474788740276455, + "grad_norm": 0.8440779978244876, + "learning_rate": 1.2257108536085502e-05, + "loss": 0.8496, + "step": 4967 + }, + { + "epoch": 0.44483742794784265, + "grad_norm": 0.8780891172009224, + "learning_rate": 1.2254282996420755e-05, + "loss": 0.795, + "step": 4968 + }, + { + "epoch": 0.4449269684929207, + "grad_norm": 1.0158621285964142, + "learning_rate": 1.2251457267133065e-05, + "loss": 0.8642, + "step": 4969 + }, + { + "epoch": 0.4450165090379988, + "grad_norm": 0.8798105786000459, + "learning_rate": 1.224863134846013e-05, + "loss": 0.7793, + "step": 4970 + }, + { + "epoch": 0.4451060495830768, + "grad_norm": 1.016548071332554, + "learning_rate": 1.224580524063965e-05, + "loss": 0.8275, + "step": 4971 + }, + { + "epoch": 0.4451955901281549, + "grad_norm": 1.0451586237062631, + "learning_rate": 1.2242978943909352e-05, + "loss": 0.8224, + "step": 4972 + }, + { + "epoch": 0.445285130673233, + "grad_norm": 0.9168964105503629, + "learning_rate": 1.2240152458506975e-05, + "loss": 0.8517, + "step": 4973 + }, + { + "epoch": 0.44537467121831104, + "grad_norm": 0.9804228743898941, + "learning_rate": 1.2237325784670272e-05, + "loss": 0.835, + "step": 4974 + }, + { + "epoch": 0.44546421176338913, + "grad_norm": 0.9384641262746605, + "learning_rate": 1.2234498922637017e-05, + "loss": 0.8186, + "step": 4975 + }, + { + "epoch": 0.44555375230846717, + "grad_norm": 1.1958438975670578, + "learning_rate": 1.2231671872644995e-05, + "loss": 0.8754, + "step": 4976 + }, + { + "epoch": 0.44564329285354526, + "grad_norm": 0.8264561709159851, + "learning_rate": 1.2228844634932005e-05, + "loss": 0.8065, + "step": 4977 + }, + { + "epoch": 0.4457328333986233, + "grad_norm": 1.1828203154188872, + "learning_rate": 1.2226017209735867e-05, + "loss": 0.8772, + "step": 4978 + }, + { + "epoch": 0.4458223739437014, + "grad_norm": 0.9188282304430239, + "learning_rate": 1.2223189597294419e-05, + "loss": 0.8193, + "step": 4979 + }, + { + "epoch": 0.4459119144887794, + "grad_norm": 1.0597947556272984, + "learning_rate": 1.2220361797845504e-05, + "loss": 0.867, + "step": 4980 + }, + { + "epoch": 0.4460014550338575, + "grad_norm": 0.9156626830669515, + "learning_rate": 1.2217533811626988e-05, + "loss": 0.8115, + "step": 4981 + }, + { + "epoch": 0.4460909955789356, + "grad_norm": 1.0755799364806071, + "learning_rate": 1.2214705638876757e-05, + "loss": 0.9017, + "step": 4982 + }, + { + "epoch": 0.44618053612401365, + "grad_norm": 0.8569980167747868, + "learning_rate": 1.2211877279832704e-05, + "loss": 0.8334, + "step": 4983 + }, + { + "epoch": 0.44627007666909174, + "grad_norm": 1.0293003650500874, + "learning_rate": 1.2209048734732742e-05, + "loss": 0.8303, + "step": 4984 + }, + { + "epoch": 0.4463596172141698, + "grad_norm": 0.9230990220496825, + "learning_rate": 1.22062200038148e-05, + "loss": 0.8172, + "step": 4985 + }, + { + "epoch": 0.44644915775924787, + "grad_norm": 0.8764458824383204, + "learning_rate": 1.2203391087316821e-05, + "loss": 0.8459, + "step": 4986 + }, + { + "epoch": 0.4465386983043259, + "grad_norm": 0.8885519757059731, + "learning_rate": 1.2200561985476762e-05, + "loss": 0.8104, + "step": 4987 + }, + { + "epoch": 0.446628238849404, + "grad_norm": 1.2263345648822574, + "learning_rate": 1.21977326985326e-05, + "loss": 0.7992, + "step": 4988 + }, + { + "epoch": 0.44671777939448204, + "grad_norm": 1.3156167415923492, + "learning_rate": 1.2194903226722328e-05, + "loss": 0.86, + "step": 4989 + }, + { + "epoch": 0.44680731993956013, + "grad_norm": 1.029644122199806, + "learning_rate": 1.2192073570283947e-05, + "loss": 0.8398, + "step": 4990 + }, + { + "epoch": 0.4468968604846382, + "grad_norm": 1.1465405872284344, + "learning_rate": 1.218924372945548e-05, + "loss": 0.8523, + "step": 4991 + }, + { + "epoch": 0.44698640102971626, + "grad_norm": 0.9363230774719453, + "learning_rate": 1.2186413704474964e-05, + "loss": 0.8589, + "step": 4992 + }, + { + "epoch": 0.44707594157479436, + "grad_norm": 1.1094642252568914, + "learning_rate": 1.2183583495580453e-05, + "loss": 0.8392, + "step": 4993 + }, + { + "epoch": 0.4471654821198724, + "grad_norm": 1.039528691212776, + "learning_rate": 1.2180753103010015e-05, + "loss": 0.8872, + "step": 4994 + }, + { + "epoch": 0.4472550226649505, + "grad_norm": 0.9589759577702714, + "learning_rate": 1.2177922527001734e-05, + "loss": 0.885, + "step": 4995 + }, + { + "epoch": 0.4473445632100285, + "grad_norm": 0.9175534626459917, + "learning_rate": 1.2175091767793701e-05, + "loss": 0.8294, + "step": 4996 + }, + { + "epoch": 0.4474341037551066, + "grad_norm": 0.9449186173401207, + "learning_rate": 1.217226082562404e-05, + "loss": 0.8429, + "step": 4997 + }, + { + "epoch": 0.44752364430018465, + "grad_norm": 1.024442959510463, + "learning_rate": 1.216942970073088e-05, + "loss": 0.8517, + "step": 4998 + }, + { + "epoch": 0.44761318484526275, + "grad_norm": 0.9028098604588379, + "learning_rate": 1.216659839335236e-05, + "loss": 0.8256, + "step": 4999 + }, + { + "epoch": 0.44770272539034084, + "grad_norm": 1.0690473628953165, + "learning_rate": 1.2163766903726645e-05, + "loss": 0.8876, + "step": 5000 + }, + { + "epoch": 0.4477922659354189, + "grad_norm": 0.9830249177088282, + "learning_rate": 1.2160935232091908e-05, + "loss": 0.858, + "step": 5001 + }, + { + "epoch": 0.44788180648049697, + "grad_norm": 0.9521578278960316, + "learning_rate": 1.215810337868634e-05, + "loss": 0.8528, + "step": 5002 + }, + { + "epoch": 0.447971347025575, + "grad_norm": 1.1102308415365079, + "learning_rate": 1.2155271343748151e-05, + "loss": 0.9412, + "step": 5003 + }, + { + "epoch": 0.4480608875706531, + "grad_norm": 0.9455047671976106, + "learning_rate": 1.2152439127515558e-05, + "loss": 0.8757, + "step": 5004 + }, + { + "epoch": 0.44815042811573114, + "grad_norm": 0.9175710622762737, + "learning_rate": 1.21496067302268e-05, + "loss": 0.8845, + "step": 5005 + }, + { + "epoch": 0.44823996866080923, + "grad_norm": 0.9735470488833643, + "learning_rate": 1.2146774152120128e-05, + "loss": 0.858, + "step": 5006 + }, + { + "epoch": 0.44832950920588727, + "grad_norm": 0.9515093341645374, + "learning_rate": 1.2143941393433813e-05, + "loss": 0.8402, + "step": 5007 + }, + { + "epoch": 0.44841904975096536, + "grad_norm": 1.075878236999601, + "learning_rate": 1.214110845440613e-05, + "loss": 0.8303, + "step": 5008 + }, + { + "epoch": 0.44850859029604345, + "grad_norm": 1.0775874471880393, + "learning_rate": 1.2138275335275387e-05, + "loss": 0.8854, + "step": 5009 + }, + { + "epoch": 0.4485981308411215, + "grad_norm": 0.9838436071431359, + "learning_rate": 1.2135442036279885e-05, + "loss": 0.8022, + "step": 5010 + }, + { + "epoch": 0.4486876713861996, + "grad_norm": 0.8715541070223323, + "learning_rate": 1.2132608557657961e-05, + "loss": 0.838, + "step": 5011 + }, + { + "epoch": 0.4487772119312776, + "grad_norm": 0.920424404198566, + "learning_rate": 1.2129774899647955e-05, + "loss": 0.909, + "step": 5012 + }, + { + "epoch": 0.4488667524763557, + "grad_norm": 1.2476885087120966, + "learning_rate": 1.2126941062488222e-05, + "loss": 0.8564, + "step": 5013 + }, + { + "epoch": 0.44895629302143375, + "grad_norm": 0.9691536001664944, + "learning_rate": 1.212410704641714e-05, + "loss": 0.8518, + "step": 5014 + }, + { + "epoch": 0.44904583356651184, + "grad_norm": 0.8748288122334094, + "learning_rate": 1.2121272851673094e-05, + "loss": 0.7749, + "step": 5015 + }, + { + "epoch": 0.4491353741115899, + "grad_norm": 0.9663868279098115, + "learning_rate": 1.211843847849449e-05, + "loss": 0.8512, + "step": 5016 + }, + { + "epoch": 0.449224914656668, + "grad_norm": 0.8963985780723251, + "learning_rate": 1.2115603927119744e-05, + "loss": 0.8501, + "step": 5017 + }, + { + "epoch": 0.44931445520174607, + "grad_norm": 0.9513994561232421, + "learning_rate": 1.2112769197787288e-05, + "loss": 0.8996, + "step": 5018 + }, + { + "epoch": 0.4494039957468241, + "grad_norm": 0.9265616177900434, + "learning_rate": 1.2109934290735572e-05, + "loss": 0.8653, + "step": 5019 + }, + { + "epoch": 0.4494935362919022, + "grad_norm": 0.906233274036701, + "learning_rate": 1.2107099206203061e-05, + "loss": 0.8348, + "step": 5020 + }, + { + "epoch": 0.44958307683698023, + "grad_norm": 0.9562366941701399, + "learning_rate": 1.210426394442823e-05, + "loss": 0.9177, + "step": 5021 + }, + { + "epoch": 0.4496726173820583, + "grad_norm": 0.9691958071315939, + "learning_rate": 1.2101428505649578e-05, + "loss": 0.8193, + "step": 5022 + }, + { + "epoch": 0.44976215792713636, + "grad_norm": 0.8736806838470305, + "learning_rate": 1.20985928901056e-05, + "loss": 0.8036, + "step": 5023 + }, + { + "epoch": 0.44985169847221446, + "grad_norm": 0.9464448440226463, + "learning_rate": 1.209575709803483e-05, + "loss": 0.8988, + "step": 5024 + }, + { + "epoch": 0.4499412390172925, + "grad_norm": 0.9527657137557682, + "learning_rate": 1.2092921129675806e-05, + "loss": 0.9084, + "step": 5025 + }, + { + "epoch": 0.4500307795623706, + "grad_norm": 0.8756618404720549, + "learning_rate": 1.209008498526707e-05, + "loss": 0.8439, + "step": 5026 + }, + { + "epoch": 0.4501203201074487, + "grad_norm": 1.1309710970522686, + "learning_rate": 1.20872486650472e-05, + "loss": 0.8143, + "step": 5027 + }, + { + "epoch": 0.4502098606525267, + "grad_norm": 0.9583075346596197, + "learning_rate": 1.2084412169254776e-05, + "loss": 0.7868, + "step": 5028 + }, + { + "epoch": 0.4502994011976048, + "grad_norm": 0.8817625853100305, + "learning_rate": 1.2081575498128389e-05, + "loss": 0.8208, + "step": 5029 + }, + { + "epoch": 0.45038894174268285, + "grad_norm": 1.0500416547906286, + "learning_rate": 1.2078738651906657e-05, + "loss": 0.8986, + "step": 5030 + }, + { + "epoch": 0.45047848228776094, + "grad_norm": 0.9426854713842331, + "learning_rate": 1.2075901630828201e-05, + "loss": 0.8589, + "step": 5031 + }, + { + "epoch": 0.450568022832839, + "grad_norm": 0.8786347066571443, + "learning_rate": 1.2073064435131665e-05, + "loss": 0.8035, + "step": 5032 + }, + { + "epoch": 0.45065756337791707, + "grad_norm": 1.085281747249534, + "learning_rate": 1.2070227065055707e-05, + "loss": 0.8606, + "step": 5033 + }, + { + "epoch": 0.4507471039229951, + "grad_norm": 0.8858325152944133, + "learning_rate": 1.2067389520838993e-05, + "loss": 0.8499, + "step": 5034 + }, + { + "epoch": 0.4508366444680732, + "grad_norm": 0.978484079414316, + "learning_rate": 1.2064551802720206e-05, + "loss": 0.813, + "step": 5035 + }, + { + "epoch": 0.4509261850131513, + "grad_norm": 0.9669722128065028, + "learning_rate": 1.2061713910938055e-05, + "loss": 0.8472, + "step": 5036 + }, + { + "epoch": 0.45101572555822933, + "grad_norm": 0.9185166457149108, + "learning_rate": 1.2058875845731246e-05, + "loss": 0.8386, + "step": 5037 + }, + { + "epoch": 0.4511052661033074, + "grad_norm": 0.8713806588817347, + "learning_rate": 1.2056037607338507e-05, + "loss": 0.7731, + "step": 5038 + }, + { + "epoch": 0.45119480664838546, + "grad_norm": 0.9426875708284569, + "learning_rate": 1.2053199195998588e-05, + "loss": 0.8327, + "step": 5039 + }, + { + "epoch": 0.45128434719346355, + "grad_norm": 1.0103196506640122, + "learning_rate": 1.2050360611950245e-05, + "loss": 0.8511, + "step": 5040 + }, + { + "epoch": 0.4513738877385416, + "grad_norm": 0.8751700931689197, + "learning_rate": 1.2047521855432245e-05, + "loss": 0.807, + "step": 5041 + }, + { + "epoch": 0.4514634282836197, + "grad_norm": 0.9615425688301869, + "learning_rate": 1.204468292668338e-05, + "loss": 0.836, + "step": 5042 + }, + { + "epoch": 0.4515529688286977, + "grad_norm": 1.0200752562956759, + "learning_rate": 1.2041843825942452e-05, + "loss": 0.8344, + "step": 5043 + }, + { + "epoch": 0.4516425093737758, + "grad_norm": 1.0404064713980927, + "learning_rate": 1.2039004553448272e-05, + "loss": 0.8832, + "step": 5044 + }, + { + "epoch": 0.4517320499188539, + "grad_norm": 1.1332377058641891, + "learning_rate": 1.2036165109439675e-05, + "loss": 0.8583, + "step": 5045 + }, + { + "epoch": 0.45182159046393194, + "grad_norm": 0.8467009664062819, + "learning_rate": 1.2033325494155505e-05, + "loss": 0.7623, + "step": 5046 + }, + { + "epoch": 0.45191113100901004, + "grad_norm": 0.8533850006801387, + "learning_rate": 1.203048570783462e-05, + "loss": 0.8314, + "step": 5047 + }, + { + "epoch": 0.4520006715540881, + "grad_norm": 0.8891812973518456, + "learning_rate": 1.2027645750715894e-05, + "loss": 0.8855, + "step": 5048 + }, + { + "epoch": 0.45209021209916617, + "grad_norm": 0.9720290914438073, + "learning_rate": 1.2024805623038214e-05, + "loss": 0.8662, + "step": 5049 + }, + { + "epoch": 0.4521797526442442, + "grad_norm": 0.952712247465624, + "learning_rate": 1.2021965325040483e-05, + "loss": 0.8539, + "step": 5050 + }, + { + "epoch": 0.4522692931893223, + "grad_norm": 0.9706085889264378, + "learning_rate": 1.2019124856961619e-05, + "loss": 0.8322, + "step": 5051 + }, + { + "epoch": 0.45235883373440033, + "grad_norm": 0.9439906860264836, + "learning_rate": 1.2016284219040555e-05, + "loss": 0.8252, + "step": 5052 + }, + { + "epoch": 0.4524483742794784, + "grad_norm": 1.1548567721346144, + "learning_rate": 1.2013443411516228e-05, + "loss": 0.8043, + "step": 5053 + }, + { + "epoch": 0.4525379148245565, + "grad_norm": 1.0843588209208894, + "learning_rate": 1.2010602434627603e-05, + "loss": 0.891, + "step": 5054 + }, + { + "epoch": 0.45262745536963456, + "grad_norm": 0.991124332534902, + "learning_rate": 1.2007761288613655e-05, + "loss": 0.8852, + "step": 5055 + }, + { + "epoch": 0.45271699591471265, + "grad_norm": 1.0093878302310264, + "learning_rate": 1.200491997371337e-05, + "loss": 0.8069, + "step": 5056 + }, + { + "epoch": 0.4528065364597907, + "grad_norm": 1.2559665885680094, + "learning_rate": 1.2002078490165747e-05, + "loss": 0.8714, + "step": 5057 + }, + { + "epoch": 0.4528960770048688, + "grad_norm": 1.0262695295007849, + "learning_rate": 1.1999236838209812e-05, + "loss": 0.8129, + "step": 5058 + }, + { + "epoch": 0.4529856175499468, + "grad_norm": 0.8968808186122779, + "learning_rate": 1.1996395018084581e-05, + "loss": 0.8495, + "step": 5059 + }, + { + "epoch": 0.4530751580950249, + "grad_norm": 0.9031510893666217, + "learning_rate": 1.1993553030029115e-05, + "loss": 0.8235, + "step": 5060 + }, + { + "epoch": 0.45316469864010295, + "grad_norm": 0.8860369160878107, + "learning_rate": 1.199071087428246e-05, + "loss": 0.8462, + "step": 5061 + }, + { + "epoch": 0.45325423918518104, + "grad_norm": 0.8163072797688293, + "learning_rate": 1.1987868551083693e-05, + "loss": 0.8635, + "step": 5062 + }, + { + "epoch": 0.45334377973025913, + "grad_norm": 0.9075454864860621, + "learning_rate": 1.1985026060671903e-05, + "loss": 0.8916, + "step": 5063 + }, + { + "epoch": 0.45343332027533717, + "grad_norm": 1.0349385187091114, + "learning_rate": 1.1982183403286186e-05, + "loss": 0.8544, + "step": 5064 + }, + { + "epoch": 0.45352286082041526, + "grad_norm": 0.9843618909773673, + "learning_rate": 1.1979340579165664e-05, + "loss": 0.853, + "step": 5065 + }, + { + "epoch": 0.4536124013654933, + "grad_norm": 1.104034288122838, + "learning_rate": 1.1976497588549462e-05, + "loss": 0.8408, + "step": 5066 + }, + { + "epoch": 0.4537019419105714, + "grad_norm": 0.9659715076829284, + "learning_rate": 1.1973654431676724e-05, + "loss": 0.8183, + "step": 5067 + }, + { + "epoch": 0.45379148245564943, + "grad_norm": 0.8930634387351026, + "learning_rate": 1.1970811108786604e-05, + "loss": 0.855, + "step": 5068 + }, + { + "epoch": 0.4538810230007275, + "grad_norm": 0.9434983981650649, + "learning_rate": 1.196796762011828e-05, + "loss": 0.814, + "step": 5069 + }, + { + "epoch": 0.45397056354580556, + "grad_norm": 0.8963944008765798, + "learning_rate": 1.196512396591093e-05, + "loss": 0.8658, + "step": 5070 + }, + { + "epoch": 0.45406010409088365, + "grad_norm": 1.0549202590809732, + "learning_rate": 1.1962280146403757e-05, + "loss": 0.8881, + "step": 5071 + }, + { + "epoch": 0.45414964463596175, + "grad_norm": 0.9763210000438982, + "learning_rate": 1.1959436161835971e-05, + "loss": 0.8121, + "step": 5072 + }, + { + "epoch": 0.4542391851810398, + "grad_norm": 0.8721554302357839, + "learning_rate": 1.1956592012446802e-05, + "loss": 0.8405, + "step": 5073 + }, + { + "epoch": 0.4543287257261179, + "grad_norm": 0.9252083745266856, + "learning_rate": 1.1953747698475488e-05, + "loss": 0.8765, + "step": 5074 + }, + { + "epoch": 0.4544182662711959, + "grad_norm": 0.8973514272673419, + "learning_rate": 1.1950903220161286e-05, + "loss": 0.8193, + "step": 5075 + }, + { + "epoch": 0.454507806816274, + "grad_norm": 0.9574005373761372, + "learning_rate": 1.194805857774346e-05, + "loss": 0.862, + "step": 5076 + }, + { + "epoch": 0.45459734736135204, + "grad_norm": 0.8591463346459571, + "learning_rate": 1.1945213771461295e-05, + "loss": 0.8689, + "step": 5077 + }, + { + "epoch": 0.45468688790643014, + "grad_norm": 1.0080441587426137, + "learning_rate": 1.1942368801554087e-05, + "loss": 0.8481, + "step": 5078 + }, + { + "epoch": 0.4547764284515082, + "grad_norm": 0.8771598341755856, + "learning_rate": 1.1939523668261144e-05, + "loss": 0.8337, + "step": 5079 + }, + { + "epoch": 0.45486596899658627, + "grad_norm": 0.9629426693749846, + "learning_rate": 1.1936678371821792e-05, + "loss": 0.872, + "step": 5080 + }, + { + "epoch": 0.45495550954166436, + "grad_norm": 0.949637300793534, + "learning_rate": 1.1933832912475365e-05, + "loss": 0.8725, + "step": 5081 + }, + { + "epoch": 0.4550450500867424, + "grad_norm": 0.9462173293029135, + "learning_rate": 1.1930987290461217e-05, + "loss": 0.8229, + "step": 5082 + }, + { + "epoch": 0.4551345906318205, + "grad_norm": 1.1939740197640527, + "learning_rate": 1.1928141506018708e-05, + "loss": 0.879, + "step": 5083 + }, + { + "epoch": 0.4552241311768985, + "grad_norm": 1.066220151447293, + "learning_rate": 1.1925295559387222e-05, + "loss": 0.8385, + "step": 5084 + }, + { + "epoch": 0.4553136717219766, + "grad_norm": 0.9959461896673916, + "learning_rate": 1.1922449450806148e-05, + "loss": 0.8122, + "step": 5085 + }, + { + "epoch": 0.45540321226705466, + "grad_norm": 0.8973387329768747, + "learning_rate": 1.1919603180514888e-05, + "loss": 0.7462, + "step": 5086 + }, + { + "epoch": 0.45549275281213275, + "grad_norm": 1.2050414135735144, + "learning_rate": 1.1916756748752862e-05, + "loss": 0.8801, + "step": 5087 + }, + { + "epoch": 0.4555822933572108, + "grad_norm": 1.0826626837115767, + "learning_rate": 1.191391015575951e-05, + "loss": 0.8144, + "step": 5088 + }, + { + "epoch": 0.4556718339022889, + "grad_norm": 0.9510047669372982, + "learning_rate": 1.1911063401774268e-05, + "loss": 0.8414, + "step": 5089 + }, + { + "epoch": 0.455761374447367, + "grad_norm": 0.9026229596587412, + "learning_rate": 1.1908216487036602e-05, + "loss": 0.8454, + "step": 5090 + }, + { + "epoch": 0.455850914992445, + "grad_norm": 0.9845568415979884, + "learning_rate": 1.1905369411785985e-05, + "loss": 0.7829, + "step": 5091 + }, + { + "epoch": 0.4559404555375231, + "grad_norm": 2.0467374846165822, + "learning_rate": 1.1902522176261897e-05, + "loss": 0.8519, + "step": 5092 + }, + { + "epoch": 0.45602999608260114, + "grad_norm": 0.904289742905037, + "learning_rate": 1.189967478070385e-05, + "loss": 0.7921, + "step": 5093 + }, + { + "epoch": 0.45611953662767923, + "grad_norm": 1.0154336909027895, + "learning_rate": 1.1896827225351347e-05, + "loss": 0.919, + "step": 5094 + }, + { + "epoch": 0.45620907717275727, + "grad_norm": 0.9394985334954377, + "learning_rate": 1.1893979510443918e-05, + "loss": 0.8153, + "step": 5095 + }, + { + "epoch": 0.45629861771783536, + "grad_norm": 0.9789784836354222, + "learning_rate": 1.1891131636221107e-05, + "loss": 0.8504, + "step": 5096 + }, + { + "epoch": 0.4563881582629134, + "grad_norm": 0.84521230857603, + "learning_rate": 1.1888283602922466e-05, + "loss": 0.8045, + "step": 5097 + }, + { + "epoch": 0.4564776988079915, + "grad_norm": 0.9077526319778918, + "learning_rate": 1.1885435410787558e-05, + "loss": 0.8424, + "step": 5098 + }, + { + "epoch": 0.4565672393530696, + "grad_norm": 0.9812593693485887, + "learning_rate": 1.188258706005597e-05, + "loss": 0.8637, + "step": 5099 + }, + { + "epoch": 0.4566567798981476, + "grad_norm": 1.1596095294244895, + "learning_rate": 1.1879738550967295e-05, + "loss": 0.7684, + "step": 5100 + }, + { + "epoch": 0.4567463204432257, + "grad_norm": 0.9701778638188038, + "learning_rate": 1.1876889883761136e-05, + "loss": 0.8413, + "step": 5101 + }, + { + "epoch": 0.45683586098830375, + "grad_norm": 0.9801421940186926, + "learning_rate": 1.1874041058677115e-05, + "loss": 0.8595, + "step": 5102 + }, + { + "epoch": 0.45692540153338185, + "grad_norm": 1.0641837438955042, + "learning_rate": 1.187119207595487e-05, + "loss": 0.8564, + "step": 5103 + }, + { + "epoch": 0.4570149420784599, + "grad_norm": 0.934191559272803, + "learning_rate": 1.1868342935834043e-05, + "loss": 0.7732, + "step": 5104 + }, + { + "epoch": 0.457104482623538, + "grad_norm": 0.9082685161884676, + "learning_rate": 1.1865493638554298e-05, + "loss": 0.8364, + "step": 5105 + }, + { + "epoch": 0.457194023168616, + "grad_norm": 0.926208624429448, + "learning_rate": 1.1862644184355307e-05, + "loss": 0.8419, + "step": 5106 + }, + { + "epoch": 0.4572835637136941, + "grad_norm": 0.9167973198404721, + "learning_rate": 1.1859794573476757e-05, + "loss": 0.8095, + "step": 5107 + }, + { + "epoch": 0.4573731042587722, + "grad_norm": 1.2181386293302687, + "learning_rate": 1.1856944806158348e-05, + "loss": 0.8321, + "step": 5108 + }, + { + "epoch": 0.45746264480385024, + "grad_norm": 1.3809273745703932, + "learning_rate": 1.1854094882639792e-05, + "loss": 0.8362, + "step": 5109 + }, + { + "epoch": 0.45755218534892833, + "grad_norm": 0.8974751594210281, + "learning_rate": 1.1851244803160818e-05, + "loss": 0.8863, + "step": 5110 + }, + { + "epoch": 0.45764172589400637, + "grad_norm": 1.1250431284468114, + "learning_rate": 1.1848394567961163e-05, + "loss": 0.8926, + "step": 5111 + }, + { + "epoch": 0.45773126643908446, + "grad_norm": 0.9693129387220083, + "learning_rate": 1.1845544177280581e-05, + "loss": 0.8296, + "step": 5112 + }, + { + "epoch": 0.4578208069841625, + "grad_norm": 1.082412697049325, + "learning_rate": 1.1842693631358835e-05, + "loss": 0.8589, + "step": 5113 + }, + { + "epoch": 0.4579103475292406, + "grad_norm": 0.9978118112796628, + "learning_rate": 1.1839842930435707e-05, + "loss": 0.8798, + "step": 5114 + }, + { + "epoch": 0.45799988807431863, + "grad_norm": 0.963276683881721, + "learning_rate": 1.183699207475099e-05, + "loss": 0.8816, + "step": 5115 + }, + { + "epoch": 0.4580894286193967, + "grad_norm": 0.9160337842433388, + "learning_rate": 1.183414106454448e-05, + "loss": 0.879, + "step": 5116 + }, + { + "epoch": 0.4581789691644748, + "grad_norm": 0.9436601993934784, + "learning_rate": 1.1831289900056005e-05, + "loss": 0.8024, + "step": 5117 + }, + { + "epoch": 0.45826850970955285, + "grad_norm": 1.0221115122408104, + "learning_rate": 1.182843858152539e-05, + "loss": 0.8323, + "step": 5118 + }, + { + "epoch": 0.45835805025463094, + "grad_norm": 0.9255867967578555, + "learning_rate": 1.1825587109192478e-05, + "loss": 0.8009, + "step": 5119 + }, + { + "epoch": 0.458447590799709, + "grad_norm": 0.9910793504294045, + "learning_rate": 1.182273548329713e-05, + "loss": 0.8418, + "step": 5120 + }, + { + "epoch": 0.4585371313447871, + "grad_norm": 1.0377871238486296, + "learning_rate": 1.1819883704079214e-05, + "loss": 0.8156, + "step": 5121 + }, + { + "epoch": 0.4586266718898651, + "grad_norm": 0.9929060557856917, + "learning_rate": 1.1817031771778607e-05, + "loss": 0.8313, + "step": 5122 + }, + { + "epoch": 0.4587162124349432, + "grad_norm": 1.033280629583944, + "learning_rate": 1.1814179686635213e-05, + "loss": 0.8734, + "step": 5123 + }, + { + "epoch": 0.45880575298002124, + "grad_norm": 0.9225136025281566, + "learning_rate": 1.1811327448888933e-05, + "loss": 0.8464, + "step": 5124 + }, + { + "epoch": 0.45889529352509933, + "grad_norm": 1.1199092820297125, + "learning_rate": 1.180847505877969e-05, + "loss": 0.8247, + "step": 5125 + }, + { + "epoch": 0.4589848340701774, + "grad_norm": 0.9189131256374843, + "learning_rate": 1.180562251654742e-05, + "loss": 0.8147, + "step": 5126 + }, + { + "epoch": 0.45907437461525546, + "grad_norm": 1.076456297574399, + "learning_rate": 1.1802769822432068e-05, + "loss": 0.8545, + "step": 5127 + }, + { + "epoch": 0.45916391516033356, + "grad_norm": 1.0370810627361717, + "learning_rate": 1.1799916976673589e-05, + "loss": 0.893, + "step": 5128 + }, + { + "epoch": 0.4592534557054116, + "grad_norm": 1.1895294582205767, + "learning_rate": 1.1797063979511964e-05, + "loss": 0.732, + "step": 5129 + }, + { + "epoch": 0.4593429962504897, + "grad_norm": 1.0168987893379378, + "learning_rate": 1.1794210831187174e-05, + "loss": 0.8667, + "step": 5130 + }, + { + "epoch": 0.4594325367955677, + "grad_norm": 0.8843046531508095, + "learning_rate": 1.1791357531939211e-05, + "loss": 0.7884, + "step": 5131 + }, + { + "epoch": 0.4595220773406458, + "grad_norm": 0.9614994258948922, + "learning_rate": 1.1788504082008093e-05, + "loss": 0.9285, + "step": 5132 + }, + { + "epoch": 0.45961161788572386, + "grad_norm": 0.9687012149307961, + "learning_rate": 1.1785650481633841e-05, + "loss": 0.8307, + "step": 5133 + }, + { + "epoch": 0.45970115843080195, + "grad_norm": 1.0292601584866816, + "learning_rate": 1.1782796731056487e-05, + "loss": 0.8554, + "step": 5134 + }, + { + "epoch": 0.45979069897588004, + "grad_norm": 0.9430173864660034, + "learning_rate": 1.1779942830516083e-05, + "loss": 0.8545, + "step": 5135 + }, + { + "epoch": 0.4598802395209581, + "grad_norm": 1.0922230750751905, + "learning_rate": 1.1777088780252688e-05, + "loss": 0.7958, + "step": 5136 + }, + { + "epoch": 0.45996978006603617, + "grad_norm": 0.905540854383264, + "learning_rate": 1.1774234580506374e-05, + "loss": 0.884, + "step": 5137 + }, + { + "epoch": 0.4600593206111142, + "grad_norm": 0.9490256894100174, + "learning_rate": 1.1771380231517231e-05, + "loss": 0.8821, + "step": 5138 + }, + { + "epoch": 0.4601488611561923, + "grad_norm": 0.9087771187164633, + "learning_rate": 1.1768525733525356e-05, + "loss": 0.8391, + "step": 5139 + }, + { + "epoch": 0.46023840170127034, + "grad_norm": 0.8544891362161957, + "learning_rate": 1.1765671086770855e-05, + "loss": 0.8323, + "step": 5140 + }, + { + "epoch": 0.46032794224634843, + "grad_norm": 0.8918519262694055, + "learning_rate": 1.1762816291493862e-05, + "loss": 0.8632, + "step": 5141 + }, + { + "epoch": 0.46041748279142647, + "grad_norm": 0.9406230848093153, + "learning_rate": 1.1759961347934505e-05, + "loss": 0.7528, + "step": 5142 + }, + { + "epoch": 0.46050702333650456, + "grad_norm": 0.9507773370465508, + "learning_rate": 1.175710625633293e-05, + "loss": 0.8197, + "step": 5143 + }, + { + "epoch": 0.46059656388158265, + "grad_norm": 1.0554815453727129, + "learning_rate": 1.1754251016929308e-05, + "loss": 0.8339, + "step": 5144 + }, + { + "epoch": 0.4606861044266607, + "grad_norm": 0.9793904364171417, + "learning_rate": 1.1751395629963806e-05, + "loss": 0.8699, + "step": 5145 + }, + { + "epoch": 0.4607756449717388, + "grad_norm": 0.8967591221463577, + "learning_rate": 1.1748540095676609e-05, + "loss": 0.8494, + "step": 5146 + }, + { + "epoch": 0.4608651855168168, + "grad_norm": 1.0052731232315066, + "learning_rate": 1.1745684414307919e-05, + "loss": 0.8263, + "step": 5147 + }, + { + "epoch": 0.4609547260618949, + "grad_norm": 1.0766045531543664, + "learning_rate": 1.1742828586097945e-05, + "loss": 0.8371, + "step": 5148 + }, + { + "epoch": 0.46104426660697295, + "grad_norm": 0.9870349156594975, + "learning_rate": 1.1739972611286908e-05, + "loss": 0.8153, + "step": 5149 + }, + { + "epoch": 0.46113380715205105, + "grad_norm": 1.1063983806107454, + "learning_rate": 1.1737116490115046e-05, + "loss": 0.8194, + "step": 5150 + }, + { + "epoch": 0.4612233476971291, + "grad_norm": 1.2037774365506213, + "learning_rate": 1.1734260222822606e-05, + "loss": 0.8096, + "step": 5151 + }, + { + "epoch": 0.4613128882422072, + "grad_norm": 0.9391945356514018, + "learning_rate": 1.1731403809649847e-05, + "loss": 0.855, + "step": 5152 + }, + { + "epoch": 0.46140242878728527, + "grad_norm": 0.9320474389705087, + "learning_rate": 1.1728547250837042e-05, + "loss": 0.879, + "step": 5153 + }, + { + "epoch": 0.4614919693323633, + "grad_norm": 0.9235509884755432, + "learning_rate": 1.1725690546624475e-05, + "loss": 0.831, + "step": 5154 + }, + { + "epoch": 0.4615815098774414, + "grad_norm": 1.0247354495996444, + "learning_rate": 1.172283369725244e-05, + "loss": 0.8569, + "step": 5155 + }, + { + "epoch": 0.46167105042251944, + "grad_norm": 0.9262693555228466, + "learning_rate": 1.1719976702961253e-05, + "loss": 0.8696, + "step": 5156 + }, + { + "epoch": 0.46176059096759753, + "grad_norm": 0.8628726572076715, + "learning_rate": 1.1717119563991228e-05, + "loss": 0.8643, + "step": 5157 + }, + { + "epoch": 0.46185013151267557, + "grad_norm": 0.9568026555805302, + "learning_rate": 1.1714262280582703e-05, + "loss": 0.8583, + "step": 5158 + }, + { + "epoch": 0.46193967205775366, + "grad_norm": 0.8971088630736636, + "learning_rate": 1.1711404852976019e-05, + "loss": 0.8681, + "step": 5159 + }, + { + "epoch": 0.4620292126028317, + "grad_norm": 0.8600036959318377, + "learning_rate": 1.1708547281411535e-05, + "loss": 0.8564, + "step": 5160 + }, + { + "epoch": 0.4621187531479098, + "grad_norm": 0.9427869977381004, + "learning_rate": 1.1705689566129624e-05, + "loss": 0.8509, + "step": 5161 + }, + { + "epoch": 0.4622082936929879, + "grad_norm": 0.951829353340297, + "learning_rate": 1.1702831707370662e-05, + "loss": 0.8261, + "step": 5162 + }, + { + "epoch": 0.4622978342380659, + "grad_norm": 0.9416540892702926, + "learning_rate": 1.169997370537505e-05, + "loss": 0.8263, + "step": 5163 + }, + { + "epoch": 0.462387374783144, + "grad_norm": 0.9606430843275499, + "learning_rate": 1.1697115560383186e-05, + "loss": 0.8713, + "step": 5164 + }, + { + "epoch": 0.46247691532822205, + "grad_norm": 1.0073479095188298, + "learning_rate": 1.1694257272635494e-05, + "loss": 0.7987, + "step": 5165 + }, + { + "epoch": 0.46256645587330014, + "grad_norm": 1.290285035991937, + "learning_rate": 1.1691398842372398e-05, + "loss": 0.8418, + "step": 5166 + }, + { + "epoch": 0.4626559964183782, + "grad_norm": 0.903550390064754, + "learning_rate": 1.1688540269834346e-05, + "loss": 0.8542, + "step": 5167 + }, + { + "epoch": 0.46274553696345627, + "grad_norm": 0.9029447663126926, + "learning_rate": 1.1685681555261788e-05, + "loss": 0.7914, + "step": 5168 + }, + { + "epoch": 0.4628350775085343, + "grad_norm": 0.9613588116446969, + "learning_rate": 1.168282269889519e-05, + "loss": 0.8754, + "step": 5169 + }, + { + "epoch": 0.4629246180536124, + "grad_norm": 2.1611118205773168, + "learning_rate": 1.1679963700975031e-05, + "loss": 0.8822, + "step": 5170 + }, + { + "epoch": 0.4630141585986905, + "grad_norm": 0.9144672855589865, + "learning_rate": 1.1677104561741801e-05, + "loss": 0.828, + "step": 5171 + }, + { + "epoch": 0.46310369914376853, + "grad_norm": 0.9906521946167535, + "learning_rate": 1.1674245281436001e-05, + "loss": 0.8563, + "step": 5172 + }, + { + "epoch": 0.4631932396888466, + "grad_norm": 0.9277476759628505, + "learning_rate": 1.1671385860298141e-05, + "loss": 0.8661, + "step": 5173 + }, + { + "epoch": 0.46328278023392466, + "grad_norm": 0.9793713132605708, + "learning_rate": 1.166852629856875e-05, + "loss": 0.8088, + "step": 5174 + }, + { + "epoch": 0.46337232077900276, + "grad_norm": 0.9893867605180711, + "learning_rate": 1.1665666596488368e-05, + "loss": 0.857, + "step": 5175 + }, + { + "epoch": 0.4634618613240808, + "grad_norm": 0.9843420190742015, + "learning_rate": 1.1662806754297533e-05, + "loss": 0.8846, + "step": 5176 + }, + { + "epoch": 0.4635514018691589, + "grad_norm": 0.9594780492778098, + "learning_rate": 1.1659946772236817e-05, + "loss": 0.8368, + "step": 5177 + }, + { + "epoch": 0.4636409424142369, + "grad_norm": 0.8638476420391954, + "learning_rate": 1.1657086650546788e-05, + "loss": 0.8056, + "step": 5178 + }, + { + "epoch": 0.463730482959315, + "grad_norm": 1.0030252752936568, + "learning_rate": 1.1654226389468026e-05, + "loss": 0.9096, + "step": 5179 + }, + { + "epoch": 0.4638200235043931, + "grad_norm": 0.9642909848922914, + "learning_rate": 1.1651365989241132e-05, + "loss": 0.8064, + "step": 5180 + }, + { + "epoch": 0.46390956404947115, + "grad_norm": 0.947620777082785, + "learning_rate": 1.1648505450106716e-05, + "loss": 0.8621, + "step": 5181 + }, + { + "epoch": 0.46399910459454924, + "grad_norm": 0.8862060660325074, + "learning_rate": 1.164564477230539e-05, + "loss": 0.8082, + "step": 5182 + }, + { + "epoch": 0.4640886451396273, + "grad_norm": 1.0577093037378118, + "learning_rate": 1.164278395607779e-05, + "loss": 0.9186, + "step": 5183 + }, + { + "epoch": 0.46417818568470537, + "grad_norm": 1.0455588028285767, + "learning_rate": 1.1639923001664557e-05, + "loss": 0.88, + "step": 5184 + }, + { + "epoch": 0.4642677262297834, + "grad_norm": 1.0200264244446493, + "learning_rate": 1.1637061909306344e-05, + "loss": 0.8856, + "step": 5185 + }, + { + "epoch": 0.4643572667748615, + "grad_norm": 0.9924458646803535, + "learning_rate": 1.1634200679243816e-05, + "loss": 0.8404, + "step": 5186 + }, + { + "epoch": 0.46444680731993954, + "grad_norm": 0.9239883304364668, + "learning_rate": 1.1631339311717655e-05, + "loss": 0.8553, + "step": 5187 + }, + { + "epoch": 0.46453634786501763, + "grad_norm": 1.1516541175943453, + "learning_rate": 1.1628477806968547e-05, + "loss": 0.8624, + "step": 5188 + }, + { + "epoch": 0.4646258884100957, + "grad_norm": 0.8792909404843124, + "learning_rate": 1.1625616165237193e-05, + "loss": 0.787, + "step": 5189 + }, + { + "epoch": 0.46471542895517376, + "grad_norm": 0.8970280224538852, + "learning_rate": 1.1622754386764303e-05, + "loss": 0.8196, + "step": 5190 + }, + { + "epoch": 0.46480496950025185, + "grad_norm": 0.9805322893003451, + "learning_rate": 1.1619892471790604e-05, + "loss": 0.8214, + "step": 5191 + }, + { + "epoch": 0.4648945100453299, + "grad_norm": 0.9689784369555546, + "learning_rate": 1.1617030420556828e-05, + "loss": 0.8824, + "step": 5192 + }, + { + "epoch": 0.464984050590408, + "grad_norm": 1.0666476611090014, + "learning_rate": 1.1614168233303721e-05, + "loss": 0.8795, + "step": 5193 + }, + { + "epoch": 0.465073591135486, + "grad_norm": 0.9748989040614077, + "learning_rate": 1.1611305910272046e-05, + "loss": 0.8099, + "step": 5194 + }, + { + "epoch": 0.4651631316805641, + "grad_norm": 0.9859242649711023, + "learning_rate": 1.1608443451702565e-05, + "loss": 0.8432, + "step": 5195 + }, + { + "epoch": 0.46525267222564215, + "grad_norm": 0.9022376373477163, + "learning_rate": 1.1605580857836063e-05, + "loss": 0.7724, + "step": 5196 + }, + { + "epoch": 0.46534221277072024, + "grad_norm": 0.9676367478826834, + "learning_rate": 1.1602718128913333e-05, + "loss": 0.8558, + "step": 5197 + }, + { + "epoch": 0.46543175331579834, + "grad_norm": 0.919082370067064, + "learning_rate": 1.1599855265175174e-05, + "loss": 0.8599, + "step": 5198 + }, + { + "epoch": 0.4655212938608764, + "grad_norm": 0.984967753640184, + "learning_rate": 1.1596992266862408e-05, + "loss": 0.875, + "step": 5199 + }, + { + "epoch": 0.46561083440595447, + "grad_norm": 0.8645127895422162, + "learning_rate": 1.1594129134215852e-05, + "loss": 0.8127, + "step": 5200 + }, + { + "epoch": 0.4657003749510325, + "grad_norm": 0.9754446044729783, + "learning_rate": 1.1591265867476351e-05, + "loss": 0.8826, + "step": 5201 + }, + { + "epoch": 0.4657899154961106, + "grad_norm": 0.8628398572804993, + "learning_rate": 1.1588402466884751e-05, + "loss": 0.8535, + "step": 5202 + }, + { + "epoch": 0.46587945604118863, + "grad_norm": 1.0215292997433247, + "learning_rate": 1.1585538932681909e-05, + "loss": 0.8635, + "step": 5203 + }, + { + "epoch": 0.4659689965862667, + "grad_norm": 0.8733754395936902, + "learning_rate": 1.15826752651087e-05, + "loss": 0.8165, + "step": 5204 + }, + { + "epoch": 0.46605853713134476, + "grad_norm": 1.3161709859107618, + "learning_rate": 1.1579811464406005e-05, + "loss": 0.8091, + "step": 5205 + }, + { + "epoch": 0.46614807767642286, + "grad_norm": 1.006162528928787, + "learning_rate": 1.1576947530814717e-05, + "loss": 0.8355, + "step": 5206 + }, + { + "epoch": 0.46623761822150095, + "grad_norm": 0.915255026807611, + "learning_rate": 1.1574083464575744e-05, + "loss": 0.849, + "step": 5207 + }, + { + "epoch": 0.466327158766579, + "grad_norm": 0.9330250055520248, + "learning_rate": 1.1571219265929997e-05, + "loss": 0.8982, + "step": 5208 + }, + { + "epoch": 0.4664166993116571, + "grad_norm": 0.9291402823972272, + "learning_rate": 1.1568354935118407e-05, + "loss": 0.7836, + "step": 5209 + }, + { + "epoch": 0.4665062398567351, + "grad_norm": 1.0190295482150298, + "learning_rate": 1.1565490472381908e-05, + "loss": 0.825, + "step": 5210 + }, + { + "epoch": 0.4665957804018132, + "grad_norm": 0.8710376182816013, + "learning_rate": 1.1562625877961458e-05, + "loss": 0.805, + "step": 5211 + }, + { + "epoch": 0.46668532094689125, + "grad_norm": 0.9739225021879631, + "learning_rate": 1.1559761152098005e-05, + "loss": 0.832, + "step": 5212 + }, + { + "epoch": 0.46677486149196934, + "grad_norm": 0.9713575139842687, + "learning_rate": 1.1556896295032531e-05, + "loss": 0.8717, + "step": 5213 + }, + { + "epoch": 0.4668644020370474, + "grad_norm": 0.9989192148678726, + "learning_rate": 1.155403130700601e-05, + "loss": 0.8226, + "step": 5214 + }, + { + "epoch": 0.46695394258212547, + "grad_norm": 0.9551333948031926, + "learning_rate": 1.1551166188259445e-05, + "loss": 0.8249, + "step": 5215 + }, + { + "epoch": 0.46704348312720356, + "grad_norm": 0.9115808532065003, + "learning_rate": 1.154830093903383e-05, + "loss": 0.8501, + "step": 5216 + }, + { + "epoch": 0.4671330236722816, + "grad_norm": 1.0123276888428039, + "learning_rate": 1.1545435559570186e-05, + "loss": 0.865, + "step": 5217 + }, + { + "epoch": 0.4672225642173597, + "grad_norm": 0.97820114146102, + "learning_rate": 1.154257005010954e-05, + "loss": 0.8277, + "step": 5218 + }, + { + "epoch": 0.46731210476243773, + "grad_norm": 1.1312219882918144, + "learning_rate": 1.153970441089293e-05, + "loss": 0.8106, + "step": 5219 + }, + { + "epoch": 0.4674016453075158, + "grad_norm": 0.9306810239962637, + "learning_rate": 1.1536838642161398e-05, + "loss": 0.8438, + "step": 5220 + }, + { + "epoch": 0.46749118585259386, + "grad_norm": 0.8812904992510471, + "learning_rate": 1.1533972744156012e-05, + "loss": 0.8261, + "step": 5221 + }, + { + "epoch": 0.46758072639767195, + "grad_norm": 0.8968564150309098, + "learning_rate": 1.1531106717117834e-05, + "loss": 0.8034, + "step": 5222 + }, + { + "epoch": 0.46767026694275, + "grad_norm": 0.9611065536353001, + "learning_rate": 1.1528240561287951e-05, + "loss": 0.9246, + "step": 5223 + }, + { + "epoch": 0.4677598074878281, + "grad_norm": 0.9497328001822333, + "learning_rate": 1.1525374276907451e-05, + "loss": 0.8114, + "step": 5224 + }, + { + "epoch": 0.4678493480329062, + "grad_norm": 0.8867585082037666, + "learning_rate": 1.1522507864217438e-05, + "loss": 0.8775, + "step": 5225 + }, + { + "epoch": 0.4679388885779842, + "grad_norm": 0.9621814364210087, + "learning_rate": 1.1519641323459024e-05, + "loss": 0.7805, + "step": 5226 + }, + { + "epoch": 0.4680284291230623, + "grad_norm": 1.030873953249709, + "learning_rate": 1.1516774654873335e-05, + "loss": 0.8962, + "step": 5227 + }, + { + "epoch": 0.46811796966814034, + "grad_norm": 1.0035366362948042, + "learning_rate": 1.1513907858701503e-05, + "loss": 0.7912, + "step": 5228 + }, + { + "epoch": 0.46820751021321844, + "grad_norm": 0.9992846537933064, + "learning_rate": 1.1511040935184676e-05, + "loss": 0.8769, + "step": 5229 + }, + { + "epoch": 0.4682970507582965, + "grad_norm": 0.9545721801065259, + "learning_rate": 1.150817388456401e-05, + "loss": 0.8308, + "step": 5230 + }, + { + "epoch": 0.46838659130337457, + "grad_norm": 0.9945648840769662, + "learning_rate": 1.1505306707080673e-05, + "loss": 0.8391, + "step": 5231 + }, + { + "epoch": 0.4684761318484526, + "grad_norm": 0.990723166997344, + "learning_rate": 1.1502439402975842e-05, + "loss": 0.8269, + "step": 5232 + }, + { + "epoch": 0.4685656723935307, + "grad_norm": 0.9558470924019299, + "learning_rate": 1.14995719724907e-05, + "loss": 0.7981, + "step": 5233 + }, + { + "epoch": 0.4686552129386088, + "grad_norm": 0.9746648704838762, + "learning_rate": 1.149670441586645e-05, + "loss": 0.8895, + "step": 5234 + }, + { + "epoch": 0.4687447534836868, + "grad_norm": 0.9025191809931887, + "learning_rate": 1.1493836733344307e-05, + "loss": 0.8466, + "step": 5235 + }, + { + "epoch": 0.4688342940287649, + "grad_norm": 0.92594171384849, + "learning_rate": 1.1490968925165482e-05, + "loss": 0.844, + "step": 5236 + }, + { + "epoch": 0.46892383457384296, + "grad_norm": 0.9293577437869477, + "learning_rate": 1.1488100991571211e-05, + "loss": 0.8687, + "step": 5237 + }, + { + "epoch": 0.46901337511892105, + "grad_norm": 0.9521795691404596, + "learning_rate": 1.1485232932802737e-05, + "loss": 0.8584, + "step": 5238 + }, + { + "epoch": 0.4691029156639991, + "grad_norm": 0.9629467247553939, + "learning_rate": 1.1482364749101305e-05, + "loss": 0.8044, + "step": 5239 + }, + { + "epoch": 0.4691924562090772, + "grad_norm": 1.0842044339258565, + "learning_rate": 1.147949644070818e-05, + "loss": 0.8668, + "step": 5240 + }, + { + "epoch": 0.4692819967541552, + "grad_norm": 0.946594935878108, + "learning_rate": 1.147662800786464e-05, + "loss": 0.8767, + "step": 5241 + }, + { + "epoch": 0.4693715372992333, + "grad_norm": 1.0023315680115483, + "learning_rate": 1.147375945081196e-05, + "loss": 0.8026, + "step": 5242 + }, + { + "epoch": 0.4694610778443114, + "grad_norm": 1.1560960046529032, + "learning_rate": 1.1470890769791438e-05, + "loss": 0.8832, + "step": 5243 + }, + { + "epoch": 0.46955061838938944, + "grad_norm": 0.9770830932469063, + "learning_rate": 1.1468021965044378e-05, + "loss": 0.9262, + "step": 5244 + }, + { + "epoch": 0.46964015893446753, + "grad_norm": 0.9627355111775144, + "learning_rate": 1.1465153036812094e-05, + "loss": 0.8343, + "step": 5245 + }, + { + "epoch": 0.46972969947954557, + "grad_norm": 1.088746897026918, + "learning_rate": 1.1462283985335911e-05, + "loss": 0.8421, + "step": 5246 + }, + { + "epoch": 0.46981924002462366, + "grad_norm": 0.9432298660556239, + "learning_rate": 1.1459414810857164e-05, + "loss": 0.8156, + "step": 5247 + }, + { + "epoch": 0.4699087805697017, + "grad_norm": 0.902636627672977, + "learning_rate": 1.1456545513617199e-05, + "loss": 0.8539, + "step": 5248 + }, + { + "epoch": 0.4699983211147798, + "grad_norm": 1.0367685513016893, + "learning_rate": 1.1453676093857372e-05, + "loss": 0.8088, + "step": 5249 + }, + { + "epoch": 0.47008786165985783, + "grad_norm": 1.0050452151289615, + "learning_rate": 1.145080655181905e-05, + "loss": 0.8384, + "step": 5250 + }, + { + "epoch": 0.4701774022049359, + "grad_norm": 0.9021852078817674, + "learning_rate": 1.1447936887743607e-05, + "loss": 0.8838, + "step": 5251 + }, + { + "epoch": 0.470266942750014, + "grad_norm": 0.9414374375219461, + "learning_rate": 1.1445067101872434e-05, + "loss": 0.837, + "step": 5252 + }, + { + "epoch": 0.47035648329509205, + "grad_norm": 0.845039856388987, + "learning_rate": 1.1442197194446922e-05, + "loss": 0.7847, + "step": 5253 + }, + { + "epoch": 0.47044602384017015, + "grad_norm": 0.8964249772572265, + "learning_rate": 1.1439327165708486e-05, + "loss": 0.8417, + "step": 5254 + }, + { + "epoch": 0.4705355643852482, + "grad_norm": 1.0019252989596703, + "learning_rate": 1.1436457015898536e-05, + "loss": 0.861, + "step": 5255 + }, + { + "epoch": 0.4706251049303263, + "grad_norm": 0.8803237976162153, + "learning_rate": 1.1433586745258503e-05, + "loss": 0.8227, + "step": 5256 + }, + { + "epoch": 0.4707146454754043, + "grad_norm": 0.994006604480196, + "learning_rate": 1.1430716354029825e-05, + "loss": 0.8874, + "step": 5257 + }, + { + "epoch": 0.4708041860204824, + "grad_norm": 0.90857179307338, + "learning_rate": 1.142784584245395e-05, + "loss": 0.8868, + "step": 5258 + }, + { + "epoch": 0.47089372656556044, + "grad_norm": 0.9197600515747429, + "learning_rate": 1.1424975210772336e-05, + "loss": 0.7741, + "step": 5259 + }, + { + "epoch": 0.47098326711063854, + "grad_norm": 0.9763544796916975, + "learning_rate": 1.1422104459226449e-05, + "loss": 0.822, + "step": 5260 + }, + { + "epoch": 0.47107280765571663, + "grad_norm": 0.9549436020294078, + "learning_rate": 1.141923358805777e-05, + "loss": 0.7983, + "step": 5261 + }, + { + "epoch": 0.47116234820079467, + "grad_norm": 1.5787089199491313, + "learning_rate": 1.1416362597507789e-05, + "loss": 0.7917, + "step": 5262 + }, + { + "epoch": 0.47125188874587276, + "grad_norm": 0.8864948746732515, + "learning_rate": 1.1413491487817998e-05, + "loss": 0.8122, + "step": 5263 + }, + { + "epoch": 0.4713414292909508, + "grad_norm": 1.0090843716660998, + "learning_rate": 1.141062025922991e-05, + "loss": 0.8489, + "step": 5264 + }, + { + "epoch": 0.4714309698360289, + "grad_norm": 0.9471400267410108, + "learning_rate": 1.1407748911985045e-05, + "loss": 0.8311, + "step": 5265 + }, + { + "epoch": 0.4715205103811069, + "grad_norm": 0.9706015020485944, + "learning_rate": 1.1404877446324928e-05, + "loss": 0.8219, + "step": 5266 + }, + { + "epoch": 0.471610050926185, + "grad_norm": 0.9396569204242291, + "learning_rate": 1.1402005862491094e-05, + "loss": 0.8228, + "step": 5267 + }, + { + "epoch": 0.47169959147126306, + "grad_norm": 0.998623564237825, + "learning_rate": 1.1399134160725103e-05, + "loss": 0.8738, + "step": 5268 + }, + { + "epoch": 0.47178913201634115, + "grad_norm": 1.0201159456173834, + "learning_rate": 1.1396262341268503e-05, + "loss": 0.8165, + "step": 5269 + }, + { + "epoch": 0.47187867256141924, + "grad_norm": 1.186615338368212, + "learning_rate": 1.139339040436286e-05, + "loss": 0.8468, + "step": 5270 + }, + { + "epoch": 0.4719682131064973, + "grad_norm": 0.9723645916864768, + "learning_rate": 1.1390518350249762e-05, + "loss": 0.819, + "step": 5271 + }, + { + "epoch": 0.4720577536515754, + "grad_norm": 1.0045527476200615, + "learning_rate": 1.138764617917079e-05, + "loss": 0.748, + "step": 5272 + }, + { + "epoch": 0.4721472941966534, + "grad_norm": 1.0257631215986733, + "learning_rate": 1.1384773891367544e-05, + "loss": 0.8178, + "step": 5273 + }, + { + "epoch": 0.4722368347417315, + "grad_norm": 0.9091084448257286, + "learning_rate": 1.138190148708163e-05, + "loss": 0.846, + "step": 5274 + }, + { + "epoch": 0.47232637528680954, + "grad_norm": 0.9087784936486357, + "learning_rate": 1.1379028966554669e-05, + "loss": 0.8278, + "step": 5275 + }, + { + "epoch": 0.47241591583188763, + "grad_norm": 0.9196960278653166, + "learning_rate": 1.1376156330028281e-05, + "loss": 0.9109, + "step": 5276 + }, + { + "epoch": 0.47250545637696567, + "grad_norm": 1.1089444181201233, + "learning_rate": 1.137328357774411e-05, + "loss": 0.8534, + "step": 5277 + }, + { + "epoch": 0.47259499692204376, + "grad_norm": 0.9387743007259313, + "learning_rate": 1.1370410709943798e-05, + "loss": 0.789, + "step": 5278 + }, + { + "epoch": 0.47268453746712186, + "grad_norm": 1.0193530898892347, + "learning_rate": 1.1367537726869003e-05, + "loss": 0.7974, + "step": 5279 + }, + { + "epoch": 0.4727740780121999, + "grad_norm": 0.9508104504992084, + "learning_rate": 1.1364664628761391e-05, + "loss": 0.8522, + "step": 5280 + }, + { + "epoch": 0.472863618557278, + "grad_norm": 0.8999457405036402, + "learning_rate": 1.1361791415862637e-05, + "loss": 0.812, + "step": 5281 + }, + { + "epoch": 0.472953159102356, + "grad_norm": 0.9339050837264762, + "learning_rate": 1.1358918088414427e-05, + "loss": 0.7978, + "step": 5282 + }, + { + "epoch": 0.4730426996474341, + "grad_norm": 0.9910159270876545, + "learning_rate": 1.1356044646658455e-05, + "loss": 0.8413, + "step": 5283 + }, + { + "epoch": 0.47313224019251215, + "grad_norm": 1.0551357894416837, + "learning_rate": 1.1353171090836427e-05, + "loss": 0.8935, + "step": 5284 + }, + { + "epoch": 0.47322178073759025, + "grad_norm": 0.861611819650731, + "learning_rate": 1.1350297421190058e-05, + "loss": 0.8156, + "step": 5285 + }, + { + "epoch": 0.4733113212826683, + "grad_norm": 0.9325490434811302, + "learning_rate": 1.1347423637961067e-05, + "loss": 0.8779, + "step": 5286 + }, + { + "epoch": 0.4734008618277464, + "grad_norm": 0.9469048301140901, + "learning_rate": 1.1344549741391193e-05, + "loss": 0.7747, + "step": 5287 + }, + { + "epoch": 0.47349040237282447, + "grad_norm": 0.9306991540983031, + "learning_rate": 1.1341675731722175e-05, + "loss": 0.7733, + "step": 5288 + }, + { + "epoch": 0.4735799429179025, + "grad_norm": 0.9949786844847933, + "learning_rate": 1.1338801609195769e-05, + "loss": 0.8305, + "step": 5289 + }, + { + "epoch": 0.4736694834629806, + "grad_norm": 0.8816959185076279, + "learning_rate": 1.133592737405373e-05, + "loss": 0.8267, + "step": 5290 + }, + { + "epoch": 0.47375902400805864, + "grad_norm": 0.9132957126578524, + "learning_rate": 1.1333053026537837e-05, + "loss": 0.835, + "step": 5291 + }, + { + "epoch": 0.47384856455313673, + "grad_norm": 1.0847778536707446, + "learning_rate": 1.1330178566889866e-05, + "loss": 0.904, + "step": 5292 + }, + { + "epoch": 0.47393810509821477, + "grad_norm": 0.9214369869536464, + "learning_rate": 1.132730399535161e-05, + "loss": 0.7884, + "step": 5293 + }, + { + "epoch": 0.47402764564329286, + "grad_norm": 0.8969466418700005, + "learning_rate": 1.1324429312164866e-05, + "loss": 0.8416, + "step": 5294 + }, + { + "epoch": 0.4741171861883709, + "grad_norm": 0.9569458733886527, + "learning_rate": 1.1321554517571447e-05, + "loss": 0.9044, + "step": 5295 + }, + { + "epoch": 0.474206726733449, + "grad_norm": 0.8659255960461684, + "learning_rate": 1.1318679611813166e-05, + "loss": 0.8621, + "step": 5296 + }, + { + "epoch": 0.4742962672785271, + "grad_norm": 0.9560804327918336, + "learning_rate": 1.1315804595131849e-05, + "loss": 0.8404, + "step": 5297 + }, + { + "epoch": 0.4743858078236051, + "grad_norm": 0.9075687691457829, + "learning_rate": 1.1312929467769345e-05, + "loss": 0.8109, + "step": 5298 + }, + { + "epoch": 0.4744753483686832, + "grad_norm": 0.9819848432450048, + "learning_rate": 1.1310054229967488e-05, + "loss": 0.8254, + "step": 5299 + }, + { + "epoch": 0.47456488891376125, + "grad_norm": 0.9753265965935348, + "learning_rate": 1.1307178881968139e-05, + "loss": 0.7944, + "step": 5300 + }, + { + "epoch": 0.47465442945883934, + "grad_norm": 0.8925099788153175, + "learning_rate": 1.1304303424013163e-05, + "loss": 0.8204, + "step": 5301 + }, + { + "epoch": 0.4747439700039174, + "grad_norm": 0.9341656523766776, + "learning_rate": 1.1301427856344433e-05, + "loss": 0.8194, + "step": 5302 + }, + { + "epoch": 0.4748335105489955, + "grad_norm": 1.1056015584190042, + "learning_rate": 1.1298552179203834e-05, + "loss": 0.8962, + "step": 5303 + }, + { + "epoch": 0.4749230510940735, + "grad_norm": 0.8560590125901193, + "learning_rate": 1.1295676392833254e-05, + "loss": 0.7768, + "step": 5304 + }, + { + "epoch": 0.4750125916391516, + "grad_norm": 0.9260195831733976, + "learning_rate": 1.1292800497474601e-05, + "loss": 0.8857, + "step": 5305 + }, + { + "epoch": 0.4751021321842297, + "grad_norm": 0.9641733702747228, + "learning_rate": 1.1289924493369782e-05, + "loss": 0.8098, + "step": 5306 + }, + { + "epoch": 0.47519167272930773, + "grad_norm": 1.100794042172999, + "learning_rate": 1.1287048380760719e-05, + "loss": 0.8201, + "step": 5307 + }, + { + "epoch": 0.4752812132743858, + "grad_norm": 1.0504780829263825, + "learning_rate": 1.1284172159889339e-05, + "loss": 0.8227, + "step": 5308 + }, + { + "epoch": 0.47537075381946386, + "grad_norm": 0.8424012057000588, + "learning_rate": 1.1281295830997583e-05, + "loss": 0.7736, + "step": 5309 + }, + { + "epoch": 0.47546029436454196, + "grad_norm": 0.9109376046758272, + "learning_rate": 1.1278419394327395e-05, + "loss": 0.8218, + "step": 5310 + }, + { + "epoch": 0.47554983490962, + "grad_norm": 0.9450459875303185, + "learning_rate": 1.1275542850120735e-05, + "loss": 0.8689, + "step": 5311 + }, + { + "epoch": 0.4756393754546981, + "grad_norm": 1.0344027311439215, + "learning_rate": 1.1272666198619567e-05, + "loss": 0.8271, + "step": 5312 + }, + { + "epoch": 0.4757289159997761, + "grad_norm": 0.9823633530088418, + "learning_rate": 1.1269789440065864e-05, + "loss": 0.8202, + "step": 5313 + }, + { + "epoch": 0.4758184565448542, + "grad_norm": 0.9071368910867725, + "learning_rate": 1.1266912574701612e-05, + "loss": 0.8894, + "step": 5314 + }, + { + "epoch": 0.4759079970899323, + "grad_norm": 0.9419612514456097, + "learning_rate": 1.1264035602768803e-05, + "loss": 0.7942, + "step": 5315 + }, + { + "epoch": 0.47599753763501035, + "grad_norm": 0.885260171135509, + "learning_rate": 1.1261158524509438e-05, + "loss": 0.8187, + "step": 5316 + }, + { + "epoch": 0.47608707818008844, + "grad_norm": 0.9217523928714639, + "learning_rate": 1.125828134016553e-05, + "loss": 0.8655, + "step": 5317 + }, + { + "epoch": 0.4761766187251665, + "grad_norm": 0.9415069331724792, + "learning_rate": 1.1255404049979093e-05, + "loss": 0.8531, + "step": 5318 + }, + { + "epoch": 0.47626615927024457, + "grad_norm": 1.0909940732086685, + "learning_rate": 1.125252665419216e-05, + "loss": 0.8186, + "step": 5319 + }, + { + "epoch": 0.4763556998153226, + "grad_norm": 0.9677106078542571, + "learning_rate": 1.1249649153046767e-05, + "loss": 0.8627, + "step": 5320 + }, + { + "epoch": 0.4764452403604007, + "grad_norm": 0.9648149993541045, + "learning_rate": 1.1246771546784956e-05, + "loss": 0.843, + "step": 5321 + }, + { + "epoch": 0.47653478090547874, + "grad_norm": 0.8976075828437056, + "learning_rate": 1.1243893835648789e-05, + "loss": 0.8248, + "step": 5322 + }, + { + "epoch": 0.47662432145055683, + "grad_norm": 1.2291949984363775, + "learning_rate": 1.1241016019880326e-05, + "loss": 0.91, + "step": 5323 + }, + { + "epoch": 0.4767138619956349, + "grad_norm": 0.8890010688239305, + "learning_rate": 1.1238138099721637e-05, + "loss": 0.7462, + "step": 5324 + }, + { + "epoch": 0.47680340254071296, + "grad_norm": 0.9409122006338185, + "learning_rate": 1.1235260075414809e-05, + "loss": 0.8526, + "step": 5325 + }, + { + "epoch": 0.47689294308579105, + "grad_norm": 0.9744496690637215, + "learning_rate": 1.1232381947201928e-05, + "loss": 0.7907, + "step": 5326 + }, + { + "epoch": 0.4769824836308691, + "grad_norm": 0.8940813575429236, + "learning_rate": 1.1229503715325087e-05, + "loss": 0.8231, + "step": 5327 + }, + { + "epoch": 0.4770720241759472, + "grad_norm": 0.9807049036041172, + "learning_rate": 1.1226625380026407e-05, + "loss": 0.8874, + "step": 5328 + }, + { + "epoch": 0.4771615647210252, + "grad_norm": 0.9880819562569806, + "learning_rate": 1.1223746941547997e-05, + "loss": 0.8332, + "step": 5329 + }, + { + "epoch": 0.4772511052661033, + "grad_norm": 0.9843482983780973, + "learning_rate": 1.122086840013198e-05, + "loss": 0.8834, + "step": 5330 + }, + { + "epoch": 0.47734064581118135, + "grad_norm": 1.1282045937893888, + "learning_rate": 1.1217989756020494e-05, + "loss": 0.841, + "step": 5331 + }, + { + "epoch": 0.47743018635625945, + "grad_norm": 1.0002996211313124, + "learning_rate": 1.1215111009455677e-05, + "loss": 0.8522, + "step": 5332 + }, + { + "epoch": 0.47751972690133754, + "grad_norm": 1.0550676589162387, + "learning_rate": 1.1212232160679682e-05, + "loss": 0.8034, + "step": 5333 + }, + { + "epoch": 0.4776092674464156, + "grad_norm": 0.9614182501843216, + "learning_rate": 1.1209353209934666e-05, + "loss": 0.7838, + "step": 5334 + }, + { + "epoch": 0.47769880799149367, + "grad_norm": 0.9089386146544342, + "learning_rate": 1.12064741574628e-05, + "loss": 0.8519, + "step": 5335 + }, + { + "epoch": 0.4777883485365717, + "grad_norm": 0.9701278563413372, + "learning_rate": 1.1203595003506261e-05, + "loss": 0.7866, + "step": 5336 + }, + { + "epoch": 0.4778778890816498, + "grad_norm": 0.8681129107144012, + "learning_rate": 1.120071574830723e-05, + "loss": 0.793, + "step": 5337 + }, + { + "epoch": 0.47796742962672784, + "grad_norm": 1.0124925356339436, + "learning_rate": 1.1197836392107906e-05, + "loss": 0.8155, + "step": 5338 + }, + { + "epoch": 0.47805697017180593, + "grad_norm": 0.9986727757610999, + "learning_rate": 1.1194956935150488e-05, + "loss": 0.8516, + "step": 5339 + }, + { + "epoch": 0.47814651071688397, + "grad_norm": 1.1592841084519814, + "learning_rate": 1.1192077377677185e-05, + "loss": 0.8658, + "step": 5340 + }, + { + "epoch": 0.47823605126196206, + "grad_norm": 0.9301736508772399, + "learning_rate": 1.1189197719930215e-05, + "loss": 0.7669, + "step": 5341 + }, + { + "epoch": 0.47832559180704015, + "grad_norm": 0.9743045436127313, + "learning_rate": 1.118631796215181e-05, + "loss": 0.8376, + "step": 5342 + }, + { + "epoch": 0.4784151323521182, + "grad_norm": 0.8881080948058735, + "learning_rate": 1.1183438104584208e-05, + "loss": 0.8218, + "step": 5343 + }, + { + "epoch": 0.4785046728971963, + "grad_norm": 0.9321029195240634, + "learning_rate": 1.1180558147469645e-05, + "loss": 0.8418, + "step": 5344 + }, + { + "epoch": 0.4785942134422743, + "grad_norm": 0.9691402667829844, + "learning_rate": 1.117767809105038e-05, + "loss": 0.8968, + "step": 5345 + }, + { + "epoch": 0.4786837539873524, + "grad_norm": 1.0052834874806957, + "learning_rate": 1.1174797935568668e-05, + "loss": 0.8599, + "step": 5346 + }, + { + "epoch": 0.47877329453243045, + "grad_norm": 0.8892325473464305, + "learning_rate": 1.1171917681266789e-05, + "loss": 0.846, + "step": 5347 + }, + { + "epoch": 0.47886283507750854, + "grad_norm": 0.9193999652398854, + "learning_rate": 1.1169037328387005e-05, + "loss": 0.8371, + "step": 5348 + }, + { + "epoch": 0.4789523756225866, + "grad_norm": 1.0398757816722264, + "learning_rate": 1.1166156877171614e-05, + "loss": 0.861, + "step": 5349 + }, + { + "epoch": 0.47904191616766467, + "grad_norm": 0.9689115400559034, + "learning_rate": 1.116327632786291e-05, + "loss": 0.805, + "step": 5350 + }, + { + "epoch": 0.47913145671274276, + "grad_norm": 0.9849120376974381, + "learning_rate": 1.1160395680703187e-05, + "loss": 0.8045, + "step": 5351 + }, + { + "epoch": 0.4792209972578208, + "grad_norm": 0.8844120702938685, + "learning_rate": 1.1157514935934762e-05, + "loss": 0.825, + "step": 5352 + }, + { + "epoch": 0.4793105378028989, + "grad_norm": 1.073761274866184, + "learning_rate": 1.1154634093799957e-05, + "loss": 0.8266, + "step": 5353 + }, + { + "epoch": 0.47940007834797693, + "grad_norm": 0.932521315664131, + "learning_rate": 1.1151753154541087e-05, + "loss": 0.8292, + "step": 5354 + }, + { + "epoch": 0.479489618893055, + "grad_norm": 0.9619430248145938, + "learning_rate": 1.1148872118400503e-05, + "loss": 0.8719, + "step": 5355 + }, + { + "epoch": 0.47957915943813306, + "grad_norm": 0.9666819666110861, + "learning_rate": 1.1145990985620533e-05, + "loss": 0.8504, + "step": 5356 + }, + { + "epoch": 0.47966869998321116, + "grad_norm": 0.92643309206178, + "learning_rate": 1.1143109756443537e-05, + "loss": 0.8137, + "step": 5357 + }, + { + "epoch": 0.4797582405282892, + "grad_norm": 0.9137776345501791, + "learning_rate": 1.114022843111188e-05, + "loss": 0.8639, + "step": 5358 + }, + { + "epoch": 0.4798477810733673, + "grad_norm": 0.8833077466944291, + "learning_rate": 1.1137347009867916e-05, + "loss": 0.8054, + "step": 5359 + }, + { + "epoch": 0.4799373216184454, + "grad_norm": 0.9434909319503336, + "learning_rate": 1.1134465492954028e-05, + "loss": 0.8058, + "step": 5360 + }, + { + "epoch": 0.4800268621635234, + "grad_norm": 0.8345190191062126, + "learning_rate": 1.1131583880612605e-05, + "loss": 0.7599, + "step": 5361 + }, + { + "epoch": 0.4801164027086015, + "grad_norm": 0.908944382634431, + "learning_rate": 1.112870217308603e-05, + "loss": 0.8206, + "step": 5362 + }, + { + "epoch": 0.48020594325367955, + "grad_norm": 1.3502354468938789, + "learning_rate": 1.1125820370616704e-05, + "loss": 0.8862, + "step": 5363 + }, + { + "epoch": 0.48029548379875764, + "grad_norm": 1.0129019353336564, + "learning_rate": 1.112293847344704e-05, + "loss": 0.8011, + "step": 5364 + }, + { + "epoch": 0.4803850243438357, + "grad_norm": 0.9548234925075353, + "learning_rate": 1.1120056481819452e-05, + "loss": 0.7599, + "step": 5365 + }, + { + "epoch": 0.48047456488891377, + "grad_norm": 0.9132712187569844, + "learning_rate": 1.111717439597636e-05, + "loss": 0.8075, + "step": 5366 + }, + { + "epoch": 0.4805641054339918, + "grad_norm": 0.9296303720271222, + "learning_rate": 1.11142922161602e-05, + "loss": 0.7982, + "step": 5367 + }, + { + "epoch": 0.4806536459790699, + "grad_norm": 0.912759742432175, + "learning_rate": 1.1111409942613408e-05, + "loss": 0.8247, + "step": 5368 + }, + { + "epoch": 0.480743186524148, + "grad_norm": 1.00883625490817, + "learning_rate": 1.1108527575578436e-05, + "loss": 0.8052, + "step": 5369 + }, + { + "epoch": 0.48083272706922603, + "grad_norm": 1.0415350359980045, + "learning_rate": 1.1105645115297736e-05, + "loss": 0.8119, + "step": 5370 + }, + { + "epoch": 0.4809222676143041, + "grad_norm": 0.932589819911679, + "learning_rate": 1.1102762562013771e-05, + "loss": 0.8567, + "step": 5371 + }, + { + "epoch": 0.48101180815938216, + "grad_norm": 0.9726114043484292, + "learning_rate": 1.1099879915969014e-05, + "loss": 0.8348, + "step": 5372 + }, + { + "epoch": 0.48110134870446025, + "grad_norm": 0.9355877473825388, + "learning_rate": 1.1096997177405942e-05, + "loss": 0.8597, + "step": 5373 + }, + { + "epoch": 0.4811908892495383, + "grad_norm": 0.8686910496285023, + "learning_rate": 1.1094114346567045e-05, + "loss": 0.8975, + "step": 5374 + }, + { + "epoch": 0.4812804297946164, + "grad_norm": 1.2004109116118875, + "learning_rate": 1.1091231423694808e-05, + "loss": 0.8308, + "step": 5375 + }, + { + "epoch": 0.4813699703396944, + "grad_norm": 0.9355256448265609, + "learning_rate": 1.1088348409031744e-05, + "loss": 0.7949, + "step": 5376 + }, + { + "epoch": 0.4814595108847725, + "grad_norm": 1.2255405327531765, + "learning_rate": 1.108546530282036e-05, + "loss": 0.8366, + "step": 5377 + }, + { + "epoch": 0.4815490514298506, + "grad_norm": 0.8870258691877803, + "learning_rate": 1.1082582105303169e-05, + "loss": 0.7971, + "step": 5378 + }, + { + "epoch": 0.48163859197492864, + "grad_norm": 0.8868642407447398, + "learning_rate": 1.1079698816722698e-05, + "loss": 0.8412, + "step": 5379 + }, + { + "epoch": 0.48172813252000674, + "grad_norm": 0.9891033673540561, + "learning_rate": 1.1076815437321484e-05, + "loss": 0.8475, + "step": 5380 + }, + { + "epoch": 0.4818176730650848, + "grad_norm": 1.0043119362438915, + "learning_rate": 1.1073931967342062e-05, + "loss": 0.8415, + "step": 5381 + }, + { + "epoch": 0.48190721361016287, + "grad_norm": 0.918227254841356, + "learning_rate": 1.1071048407026983e-05, + "loss": 0.8186, + "step": 5382 + }, + { + "epoch": 0.4819967541552409, + "grad_norm": 1.1826903954689694, + "learning_rate": 1.1068164756618807e-05, + "loss": 0.8629, + "step": 5383 + }, + { + "epoch": 0.482086294700319, + "grad_norm": 0.9166736532192641, + "learning_rate": 1.1065281016360086e-05, + "loss": 0.8627, + "step": 5384 + }, + { + "epoch": 0.48217583524539703, + "grad_norm": 0.9504508792568868, + "learning_rate": 1.1062397186493402e-05, + "loss": 0.8634, + "step": 5385 + }, + { + "epoch": 0.4822653757904751, + "grad_norm": 1.0813402837060233, + "learning_rate": 1.1059513267261326e-05, + "loss": 0.8333, + "step": 5386 + }, + { + "epoch": 0.4823549163355532, + "grad_norm": 0.8371839805303918, + "learning_rate": 1.1056629258906443e-05, + "loss": 0.7965, + "step": 5387 + }, + { + "epoch": 0.48244445688063126, + "grad_norm": 0.8953452109452927, + "learning_rate": 1.1053745161671358e-05, + "loss": 0.8327, + "step": 5388 + }, + { + "epoch": 0.48253399742570935, + "grad_norm": 0.9580487965469747, + "learning_rate": 1.105086097579866e-05, + "loss": 0.8031, + "step": 5389 + }, + { + "epoch": 0.4826235379707874, + "grad_norm": 1.067431629750438, + "learning_rate": 1.1047976701530958e-05, + "loss": 0.8997, + "step": 5390 + }, + { + "epoch": 0.4827130785158655, + "grad_norm": 0.9467978736790414, + "learning_rate": 1.1045092339110877e-05, + "loss": 0.7866, + "step": 5391 + }, + { + "epoch": 0.4828026190609435, + "grad_norm": 0.9110524929768579, + "learning_rate": 1.1042207888781031e-05, + "loss": 0.8394, + "step": 5392 + }, + { + "epoch": 0.4828921596060216, + "grad_norm": 1.0658681871401243, + "learning_rate": 1.1039323350784052e-05, + "loss": 0.8576, + "step": 5393 + }, + { + "epoch": 0.48298170015109965, + "grad_norm": 0.8631443704125721, + "learning_rate": 1.1036438725362584e-05, + "loss": 0.8834, + "step": 5394 + }, + { + "epoch": 0.48307124069617774, + "grad_norm": 0.9527470188076916, + "learning_rate": 1.1033554012759265e-05, + "loss": 0.8576, + "step": 5395 + }, + { + "epoch": 0.48316078124125583, + "grad_norm": 0.9112305561373075, + "learning_rate": 1.1030669213216749e-05, + "loss": 0.8741, + "step": 5396 + }, + { + "epoch": 0.48325032178633387, + "grad_norm": 1.0056935939331737, + "learning_rate": 1.10277843269777e-05, + "loss": 0.8603, + "step": 5397 + }, + { + "epoch": 0.48333986233141196, + "grad_norm": 0.9301890561895692, + "learning_rate": 1.1024899354284782e-05, + "loss": 0.9033, + "step": 5398 + }, + { + "epoch": 0.48342940287649, + "grad_norm": 1.0743897791097297, + "learning_rate": 1.1022014295380669e-05, + "loss": 0.8539, + "step": 5399 + }, + { + "epoch": 0.4835189434215681, + "grad_norm": 0.8898366429043726, + "learning_rate": 1.1019129150508046e-05, + "loss": 0.823, + "step": 5400 + }, + { + "epoch": 0.48360848396664613, + "grad_norm": 0.854253191833201, + "learning_rate": 1.10162439199096e-05, + "loss": 0.829, + "step": 5401 + }, + { + "epoch": 0.4836980245117242, + "grad_norm": 0.8529121732026164, + "learning_rate": 1.1013358603828023e-05, + "loss": 0.8047, + "step": 5402 + }, + { + "epoch": 0.48378756505680226, + "grad_norm": 1.067078131272578, + "learning_rate": 1.1010473202506027e-05, + "loss": 0.8607, + "step": 5403 + }, + { + "epoch": 0.48387710560188035, + "grad_norm": 0.9187570510517816, + "learning_rate": 1.1007587716186319e-05, + "loss": 0.8643, + "step": 5404 + }, + { + "epoch": 0.48396664614695845, + "grad_norm": 0.8726738048027067, + "learning_rate": 1.100470214511161e-05, + "loss": 0.875, + "step": 5405 + }, + { + "epoch": 0.4840561866920365, + "grad_norm": 0.936790486933609, + "learning_rate": 1.1001816489524636e-05, + "loss": 0.825, + "step": 5406 + }, + { + "epoch": 0.4841457272371146, + "grad_norm": 1.0581603299640654, + "learning_rate": 1.0998930749668122e-05, + "loss": 0.8593, + "step": 5407 + }, + { + "epoch": 0.4842352677821926, + "grad_norm": 0.8844108711404719, + "learning_rate": 1.0996044925784805e-05, + "loss": 0.8809, + "step": 5408 + }, + { + "epoch": 0.4843248083272707, + "grad_norm": 0.9428760047661111, + "learning_rate": 1.0993159018117436e-05, + "loss": 0.8317, + "step": 5409 + }, + { + "epoch": 0.48441434887234874, + "grad_norm": 0.887983642764275, + "learning_rate": 1.0990273026908771e-05, + "loss": 0.8451, + "step": 5410 + }, + { + "epoch": 0.48450388941742684, + "grad_norm": 0.9647754581659951, + "learning_rate": 1.0987386952401562e-05, + "loss": 0.8375, + "step": 5411 + }, + { + "epoch": 0.4845934299625049, + "grad_norm": 0.9140107956337725, + "learning_rate": 1.0984500794838582e-05, + "loss": 0.8524, + "step": 5412 + }, + { + "epoch": 0.48468297050758297, + "grad_norm": 0.9900890472653607, + "learning_rate": 1.0981614554462604e-05, + "loss": 0.8663, + "step": 5413 + }, + { + "epoch": 0.48477251105266106, + "grad_norm": 0.9227293071651652, + "learning_rate": 1.0978728231516404e-05, + "loss": 0.8496, + "step": 5414 + }, + { + "epoch": 0.4848620515977391, + "grad_norm": 0.8583150348441748, + "learning_rate": 1.097584182624278e-05, + "loss": 0.829, + "step": 5415 + }, + { + "epoch": 0.4849515921428172, + "grad_norm": 1.0536022862678383, + "learning_rate": 1.0972955338884521e-05, + "loss": 0.8111, + "step": 5416 + }, + { + "epoch": 0.4850411326878952, + "grad_norm": 0.8411416135608347, + "learning_rate": 1.0970068769684425e-05, + "loss": 0.7849, + "step": 5417 + }, + { + "epoch": 0.4851306732329733, + "grad_norm": 0.9529371851790517, + "learning_rate": 1.0967182118885309e-05, + "loss": 0.7718, + "step": 5418 + }, + { + "epoch": 0.48522021377805136, + "grad_norm": 1.352909888161765, + "learning_rate": 1.0964295386729984e-05, + "loss": 0.8397, + "step": 5419 + }, + { + "epoch": 0.48530975432312945, + "grad_norm": 1.0854258816340463, + "learning_rate": 1.0961408573461272e-05, + "loss": 0.8103, + "step": 5420 + }, + { + "epoch": 0.4853992948682075, + "grad_norm": 0.9264208832796995, + "learning_rate": 1.0958521679322007e-05, + "loss": 0.8398, + "step": 5421 + }, + { + "epoch": 0.4854888354132856, + "grad_norm": 0.9325702894583737, + "learning_rate": 1.0955634704555021e-05, + "loss": 0.8468, + "step": 5422 + }, + { + "epoch": 0.4855783759583637, + "grad_norm": 0.9220840111458508, + "learning_rate": 1.0952747649403155e-05, + "loss": 0.8158, + "step": 5423 + }, + { + "epoch": 0.4856679165034417, + "grad_norm": 0.8874265474025742, + "learning_rate": 1.0949860514109265e-05, + "loss": 0.8323, + "step": 5424 + }, + { + "epoch": 0.4857574570485198, + "grad_norm": 0.9688237992333443, + "learning_rate": 1.09469732989162e-05, + "loss": 0.9099, + "step": 5425 + }, + { + "epoch": 0.48584699759359784, + "grad_norm": 0.9426734855077556, + "learning_rate": 1.094408600406683e-05, + "loss": 0.7316, + "step": 5426 + }, + { + "epoch": 0.48593653813867593, + "grad_norm": 0.8908555974865792, + "learning_rate": 1.0941198629804022e-05, + "loss": 0.8018, + "step": 5427 + }, + { + "epoch": 0.48602607868375397, + "grad_norm": 0.9598272351460286, + "learning_rate": 1.093831117637065e-05, + "loss": 0.8116, + "step": 5428 + }, + { + "epoch": 0.48611561922883206, + "grad_norm": 0.9617190541527875, + "learning_rate": 1.0935423644009602e-05, + "loss": 0.8229, + "step": 5429 + }, + { + "epoch": 0.4862051597739101, + "grad_norm": 0.9275113141684821, + "learning_rate": 1.0932536032963764e-05, + "loss": 0.8691, + "step": 5430 + }, + { + "epoch": 0.4862947003189882, + "grad_norm": 0.8661965046068462, + "learning_rate": 1.0929648343476033e-05, + "loss": 0.8572, + "step": 5431 + }, + { + "epoch": 0.4863842408640663, + "grad_norm": 0.9486107758254199, + "learning_rate": 1.0926760575789315e-05, + "loss": 0.7991, + "step": 5432 + }, + { + "epoch": 0.4864737814091443, + "grad_norm": 0.9542512562255702, + "learning_rate": 1.0923872730146514e-05, + "loss": 0.7692, + "step": 5433 + }, + { + "epoch": 0.4865633219542224, + "grad_norm": 0.9106043017178462, + "learning_rate": 1.0920984806790555e-05, + "loss": 0.7474, + "step": 5434 + }, + { + "epoch": 0.48665286249930045, + "grad_norm": 0.9694032467390674, + "learning_rate": 1.0918096805964349e-05, + "loss": 0.803, + "step": 5435 + }, + { + "epoch": 0.48674240304437855, + "grad_norm": 0.9212763675758805, + "learning_rate": 1.0915208727910835e-05, + "loss": 0.8476, + "step": 5436 + }, + { + "epoch": 0.4868319435894566, + "grad_norm": 0.9251803197997206, + "learning_rate": 1.0912320572872948e-05, + "loss": 0.8984, + "step": 5437 + }, + { + "epoch": 0.4869214841345347, + "grad_norm": 1.0582315687264296, + "learning_rate": 1.090943234109362e-05, + "loss": 0.8716, + "step": 5438 + }, + { + "epoch": 0.4870110246796127, + "grad_norm": 0.9623755970767499, + "learning_rate": 1.0906544032815811e-05, + "loss": 0.8118, + "step": 5439 + }, + { + "epoch": 0.4871005652246908, + "grad_norm": 1.0814228233221772, + "learning_rate": 1.0903655648282476e-05, + "loss": 0.8055, + "step": 5440 + }, + { + "epoch": 0.4871901057697689, + "grad_norm": 0.8804642863839655, + "learning_rate": 1.0900767187736566e-05, + "loss": 0.8195, + "step": 5441 + }, + { + "epoch": 0.48727964631484694, + "grad_norm": 0.9163496790548435, + "learning_rate": 1.0897878651421058e-05, + "loss": 0.8669, + "step": 5442 + }, + { + "epoch": 0.48736918685992503, + "grad_norm": 0.9423984611808082, + "learning_rate": 1.0894990039578925e-05, + "loss": 0.8683, + "step": 5443 + }, + { + "epoch": 0.48745872740500307, + "grad_norm": 1.0493576747564988, + "learning_rate": 1.0892101352453143e-05, + "loss": 0.8463, + "step": 5444 + }, + { + "epoch": 0.48754826795008116, + "grad_norm": 0.9991593377221076, + "learning_rate": 1.0889212590286709e-05, + "loss": 0.8297, + "step": 5445 + }, + { + "epoch": 0.4876378084951592, + "grad_norm": 0.9548597681163442, + "learning_rate": 1.0886323753322605e-05, + "loss": 0.8356, + "step": 5446 + }, + { + "epoch": 0.4877273490402373, + "grad_norm": 0.9207230704892666, + "learning_rate": 1.0883434841803833e-05, + "loss": 0.8576, + "step": 5447 + }, + { + "epoch": 0.4878168895853153, + "grad_norm": 0.9687441810145719, + "learning_rate": 1.0880545855973405e-05, + "loss": 0.8455, + "step": 5448 + }, + { + "epoch": 0.4879064301303934, + "grad_norm": 0.9611885396337851, + "learning_rate": 1.0877656796074328e-05, + "loss": 0.845, + "step": 5449 + }, + { + "epoch": 0.4879959706754715, + "grad_norm": 0.9652694901842425, + "learning_rate": 1.0874767662349618e-05, + "loss": 0.8563, + "step": 5450 + }, + { + "epoch": 0.48808551122054955, + "grad_norm": 1.0009151789637358, + "learning_rate": 1.0871878455042308e-05, + "loss": 0.7752, + "step": 5451 + }, + { + "epoch": 0.48817505176562764, + "grad_norm": 0.8885801711557764, + "learning_rate": 1.086898917439542e-05, + "loss": 0.8046, + "step": 5452 + }, + { + "epoch": 0.4882645923107057, + "grad_norm": 0.9320281469574639, + "learning_rate": 1.0866099820651996e-05, + "loss": 0.8198, + "step": 5453 + }, + { + "epoch": 0.4883541328557838, + "grad_norm": 0.9087009745454233, + "learning_rate": 1.0863210394055079e-05, + "loss": 0.8053, + "step": 5454 + }, + { + "epoch": 0.4884436734008618, + "grad_norm": 0.9031195754697942, + "learning_rate": 1.0860320894847713e-05, + "loss": 0.7949, + "step": 5455 + }, + { + "epoch": 0.4885332139459399, + "grad_norm": 0.9154585308593028, + "learning_rate": 1.085743132327296e-05, + "loss": 0.8731, + "step": 5456 + }, + { + "epoch": 0.48862275449101794, + "grad_norm": 1.0024831952038893, + "learning_rate": 1.0854541679573876e-05, + "loss": 0.8445, + "step": 5457 + }, + { + "epoch": 0.48871229503609603, + "grad_norm": 0.9692453837554905, + "learning_rate": 1.0851651963993533e-05, + "loss": 0.8406, + "step": 5458 + }, + { + "epoch": 0.4888018355811741, + "grad_norm": 1.2416721180199812, + "learning_rate": 1.0848762176775001e-05, + "loss": 0.8821, + "step": 5459 + }, + { + "epoch": 0.48889137612625216, + "grad_norm": 0.9533333988824881, + "learning_rate": 1.084587231816136e-05, + "loss": 0.8044, + "step": 5460 + }, + { + "epoch": 0.48898091667133026, + "grad_norm": 0.8934345258848013, + "learning_rate": 1.0842982388395696e-05, + "loss": 0.8389, + "step": 5461 + }, + { + "epoch": 0.4890704572164083, + "grad_norm": 0.9778464424481985, + "learning_rate": 1.08400923877211e-05, + "loss": 0.8735, + "step": 5462 + }, + { + "epoch": 0.4891599977614864, + "grad_norm": 0.9846564271636775, + "learning_rate": 1.083720231638067e-05, + "loss": 0.9005, + "step": 5463 + }, + { + "epoch": 0.4892495383065644, + "grad_norm": 1.0014082779988795, + "learning_rate": 1.0834312174617509e-05, + "loss": 0.8457, + "step": 5464 + }, + { + "epoch": 0.4893390788516425, + "grad_norm": 0.9847442605117007, + "learning_rate": 1.0831421962674729e-05, + "loss": 0.8439, + "step": 5465 + }, + { + "epoch": 0.48942861939672055, + "grad_norm": 0.8398461484457317, + "learning_rate": 1.082853168079544e-05, + "loss": 0.8055, + "step": 5466 + }, + { + "epoch": 0.48951815994179865, + "grad_norm": 1.0501031710764737, + "learning_rate": 1.082564132922277e-05, + "loss": 0.8088, + "step": 5467 + }, + { + "epoch": 0.48960770048687674, + "grad_norm": 0.890401726837827, + "learning_rate": 1.0822750908199836e-05, + "loss": 0.7975, + "step": 5468 + }, + { + "epoch": 0.4896972410319548, + "grad_norm": 0.89436920611807, + "learning_rate": 1.081986041796978e-05, + "loss": 0.8339, + "step": 5469 + }, + { + "epoch": 0.48978678157703287, + "grad_norm": 0.8833076851602016, + "learning_rate": 1.0816969858775741e-05, + "loss": 0.7754, + "step": 5470 + }, + { + "epoch": 0.4898763221221109, + "grad_norm": 0.9504792994868865, + "learning_rate": 1.0814079230860852e-05, + "loss": 0.9009, + "step": 5471 + }, + { + "epoch": 0.489965862667189, + "grad_norm": 0.9232147500495367, + "learning_rate": 1.0811188534468275e-05, + "loss": 0.8757, + "step": 5472 + }, + { + "epoch": 0.49005540321226704, + "grad_norm": 0.9223899908993878, + "learning_rate": 1.0808297769841166e-05, + "loss": 0.8665, + "step": 5473 + }, + { + "epoch": 0.49014494375734513, + "grad_norm": 0.9853322266596035, + "learning_rate": 1.0805406937222676e-05, + "loss": 0.8355, + "step": 5474 + }, + { + "epoch": 0.49023448430242317, + "grad_norm": 0.9425596539241807, + "learning_rate": 1.0802516036855983e-05, + "loss": 0.8365, + "step": 5475 + }, + { + "epoch": 0.49032402484750126, + "grad_norm": 0.9844582230165297, + "learning_rate": 1.0799625068984255e-05, + "loss": 0.9095, + "step": 5476 + }, + { + "epoch": 0.49041356539257935, + "grad_norm": 0.9007098675792026, + "learning_rate": 1.0796734033850668e-05, + "loss": 0.8599, + "step": 5477 + }, + { + "epoch": 0.4905031059376574, + "grad_norm": 0.9123440669615296, + "learning_rate": 1.0793842931698417e-05, + "loss": 0.825, + "step": 5478 + }, + { + "epoch": 0.4905926464827355, + "grad_norm": 1.1960439609104925, + "learning_rate": 1.0790951762770682e-05, + "loss": 0.8434, + "step": 5479 + }, + { + "epoch": 0.4906821870278135, + "grad_norm": 0.9569361757493331, + "learning_rate": 1.078806052731066e-05, + "loss": 0.7619, + "step": 5480 + }, + { + "epoch": 0.4907717275728916, + "grad_norm": 0.8872471020010495, + "learning_rate": 1.078516922556156e-05, + "loss": 0.7861, + "step": 5481 + }, + { + "epoch": 0.49086126811796965, + "grad_norm": 0.9458726876412398, + "learning_rate": 1.0782277857766581e-05, + "loss": 0.8843, + "step": 5482 + }, + { + "epoch": 0.49095080866304774, + "grad_norm": 1.083925636241174, + "learning_rate": 1.0779386424168937e-05, + "loss": 0.7807, + "step": 5483 + }, + { + "epoch": 0.4910403492081258, + "grad_norm": 0.9381578970844493, + "learning_rate": 1.0776494925011847e-05, + "loss": 0.7161, + "step": 5484 + }, + { + "epoch": 0.4911298897532039, + "grad_norm": 1.1475326197011941, + "learning_rate": 1.0773603360538533e-05, + "loss": 0.8387, + "step": 5485 + }, + { + "epoch": 0.49121943029828197, + "grad_norm": 0.9731840756642766, + "learning_rate": 1.0770711730992227e-05, + "loss": 0.8387, + "step": 5486 + }, + { + "epoch": 0.49130897084336, + "grad_norm": 0.9327109535566369, + "learning_rate": 1.076782003661616e-05, + "loss": 0.8517, + "step": 5487 + }, + { + "epoch": 0.4913985113884381, + "grad_norm": 1.080701126343337, + "learning_rate": 1.0764928277653577e-05, + "loss": 0.8129, + "step": 5488 + }, + { + "epoch": 0.49148805193351613, + "grad_norm": 0.8484044701000448, + "learning_rate": 1.0762036454347717e-05, + "loss": 0.7872, + "step": 5489 + }, + { + "epoch": 0.4915775924785942, + "grad_norm": 0.943703289221061, + "learning_rate": 1.0759144566941836e-05, + "loss": 0.8399, + "step": 5490 + }, + { + "epoch": 0.49166713302367226, + "grad_norm": 0.8652998713933185, + "learning_rate": 1.0756252615679185e-05, + "loss": 0.8282, + "step": 5491 + }, + { + "epoch": 0.49175667356875036, + "grad_norm": 0.9269031885564512, + "learning_rate": 1.0753360600803031e-05, + "loss": 0.8445, + "step": 5492 + }, + { + "epoch": 0.4918462141138284, + "grad_norm": 0.9782034134416089, + "learning_rate": 1.0750468522556637e-05, + "loss": 0.8271, + "step": 5493 + }, + { + "epoch": 0.4919357546589065, + "grad_norm": 0.9373824050014058, + "learning_rate": 1.0747576381183276e-05, + "loss": 0.7676, + "step": 5494 + }, + { + "epoch": 0.4920252952039846, + "grad_norm": 0.8154979274825064, + "learning_rate": 1.0744684176926228e-05, + "loss": 0.83, + "step": 5495 + }, + { + "epoch": 0.4921148357490626, + "grad_norm": 0.9451577016550945, + "learning_rate": 1.0741791910028771e-05, + "loss": 0.8754, + "step": 5496 + }, + { + "epoch": 0.4922043762941407, + "grad_norm": 1.0658792237455592, + "learning_rate": 1.0738899580734198e-05, + "loss": 0.8898, + "step": 5497 + }, + { + "epoch": 0.49229391683921875, + "grad_norm": 0.9137708607556491, + "learning_rate": 1.0736007189285798e-05, + "loss": 0.8099, + "step": 5498 + }, + { + "epoch": 0.49238345738429684, + "grad_norm": 0.8727540825069028, + "learning_rate": 1.0733114735926872e-05, + "loss": 0.8386, + "step": 5499 + }, + { + "epoch": 0.4924729979293749, + "grad_norm": 1.047064906110096, + "learning_rate": 1.0730222220900727e-05, + "loss": 0.821, + "step": 5500 + }, + { + "epoch": 0.49256253847445297, + "grad_norm": 0.9554680456909219, + "learning_rate": 1.0727329644450663e-05, + "loss": 0.8287, + "step": 5501 + }, + { + "epoch": 0.492652079019531, + "grad_norm": 0.8786220082870211, + "learning_rate": 1.0724437006820002e-05, + "loss": 0.7562, + "step": 5502 + }, + { + "epoch": 0.4927416195646091, + "grad_norm": 0.9247342505870936, + "learning_rate": 1.0721544308252063e-05, + "loss": 0.8719, + "step": 5503 + }, + { + "epoch": 0.4928311601096872, + "grad_norm": 0.9465102164555348, + "learning_rate": 1.0718651548990165e-05, + "loss": 0.8918, + "step": 5504 + }, + { + "epoch": 0.49292070065476523, + "grad_norm": 0.9479122816958343, + "learning_rate": 1.0715758729277643e-05, + "loss": 0.8812, + "step": 5505 + }, + { + "epoch": 0.4930102411998433, + "grad_norm": 0.8911732447472639, + "learning_rate": 1.0712865849357827e-05, + "loss": 0.8545, + "step": 5506 + }, + { + "epoch": 0.49309978174492136, + "grad_norm": 0.9742305594792593, + "learning_rate": 1.0709972909474057e-05, + "loss": 0.7397, + "step": 5507 + }, + { + "epoch": 0.49318932228999945, + "grad_norm": 0.9459926111461088, + "learning_rate": 1.0707079909869684e-05, + "loss": 0.8108, + "step": 5508 + }, + { + "epoch": 0.4932788628350775, + "grad_norm": 0.9597562079227918, + "learning_rate": 1.0704186850788053e-05, + "loss": 0.7896, + "step": 5509 + }, + { + "epoch": 0.4933684033801556, + "grad_norm": 0.9065494028787365, + "learning_rate": 1.0701293732472515e-05, + "loss": 0.9132, + "step": 5510 + }, + { + "epoch": 0.4934579439252336, + "grad_norm": 0.9814941647116594, + "learning_rate": 1.0698400555166435e-05, + "loss": 0.7841, + "step": 5511 + }, + { + "epoch": 0.4935474844703117, + "grad_norm": 0.9736616534815627, + "learning_rate": 1.0695507319113177e-05, + "loss": 0.8373, + "step": 5512 + }, + { + "epoch": 0.4936370250153898, + "grad_norm": 0.9177502222837732, + "learning_rate": 1.069261402455611e-05, + "loss": 0.8069, + "step": 5513 + }, + { + "epoch": 0.49372656556046784, + "grad_norm": 0.8493040567039404, + "learning_rate": 1.0689720671738606e-05, + "loss": 0.8192, + "step": 5514 + }, + { + "epoch": 0.49381610610554594, + "grad_norm": 0.9808387690139264, + "learning_rate": 1.0686827260904049e-05, + "loss": 0.8178, + "step": 5515 + }, + { + "epoch": 0.493905646650624, + "grad_norm": 0.927205558067573, + "learning_rate": 1.068393379229582e-05, + "loss": 0.8075, + "step": 5516 + }, + { + "epoch": 0.49399518719570207, + "grad_norm": 0.8637030062662195, + "learning_rate": 1.068104026615731e-05, + "loss": 0.7892, + "step": 5517 + }, + { + "epoch": 0.4940847277407801, + "grad_norm": 0.940182825973553, + "learning_rate": 1.0678146682731911e-05, + "loss": 0.8264, + "step": 5518 + }, + { + "epoch": 0.4941742682858582, + "grad_norm": 0.9075927089055923, + "learning_rate": 1.0675253042263023e-05, + "loss": 0.7972, + "step": 5519 + }, + { + "epoch": 0.49426380883093624, + "grad_norm": 0.9865319126017165, + "learning_rate": 1.067235934499405e-05, + "loss": 0.8615, + "step": 5520 + }, + { + "epoch": 0.49435334937601433, + "grad_norm": 0.9386120717990005, + "learning_rate": 1.06694655911684e-05, + "loss": 0.8258, + "step": 5521 + }, + { + "epoch": 0.4944428899210924, + "grad_norm": 1.0466269900529461, + "learning_rate": 1.0666571781029487e-05, + "loss": 0.872, + "step": 5522 + }, + { + "epoch": 0.49453243046617046, + "grad_norm": 1.0367848702168003, + "learning_rate": 1.0663677914820724e-05, + "loss": 0.8437, + "step": 5523 + }, + { + "epoch": 0.49462197101124855, + "grad_norm": 0.9883651468063838, + "learning_rate": 1.0660783992785542e-05, + "loss": 0.8498, + "step": 5524 + }, + { + "epoch": 0.4947115115563266, + "grad_norm": 1.0617241774989314, + "learning_rate": 1.0657890015167363e-05, + "loss": 0.809, + "step": 5525 + }, + { + "epoch": 0.4948010521014047, + "grad_norm": 0.9285536384560348, + "learning_rate": 1.0654995982209617e-05, + "loss": 0.8019, + "step": 5526 + }, + { + "epoch": 0.4948905926464827, + "grad_norm": 0.9514566484270098, + "learning_rate": 1.0652101894155749e-05, + "loss": 0.7813, + "step": 5527 + }, + { + "epoch": 0.4949801331915608, + "grad_norm": 0.9939600922643165, + "learning_rate": 1.0649207751249188e-05, + "loss": 0.8168, + "step": 5528 + }, + { + "epoch": 0.49506967373663885, + "grad_norm": 0.9418871835676739, + "learning_rate": 1.064631355373339e-05, + "loss": 0.8876, + "step": 5529 + }, + { + "epoch": 0.49515921428171694, + "grad_norm": 0.8950925752811717, + "learning_rate": 1.0643419301851804e-05, + "loss": 0.8431, + "step": 5530 + }, + { + "epoch": 0.49524875482679503, + "grad_norm": 0.9492929151239158, + "learning_rate": 1.064052499584788e-05, + "loss": 0.8969, + "step": 5531 + }, + { + "epoch": 0.49533829537187307, + "grad_norm": 1.0364137086068224, + "learning_rate": 1.063763063596508e-05, + "loss": 0.8907, + "step": 5532 + }, + { + "epoch": 0.49542783591695116, + "grad_norm": 0.9529723244730066, + "learning_rate": 1.0634736222446873e-05, + "loss": 0.8545, + "step": 5533 + }, + { + "epoch": 0.4955173764620292, + "grad_norm": 0.9419168354959362, + "learning_rate": 1.0631841755536719e-05, + "loss": 0.8461, + "step": 5534 + }, + { + "epoch": 0.4956069170071073, + "grad_norm": 0.9464035725028185, + "learning_rate": 1.0628947235478098e-05, + "loss": 0.844, + "step": 5535 + }, + { + "epoch": 0.49569645755218533, + "grad_norm": 0.898385316526279, + "learning_rate": 1.0626052662514484e-05, + "loss": 0.805, + "step": 5536 + }, + { + "epoch": 0.4957859980972634, + "grad_norm": 0.914898577258325, + "learning_rate": 1.0623158036889361e-05, + "loss": 0.8842, + "step": 5537 + }, + { + "epoch": 0.49587553864234146, + "grad_norm": 0.909692154896812, + "learning_rate": 1.0620263358846212e-05, + "loss": 0.8223, + "step": 5538 + }, + { + "epoch": 0.49596507918741956, + "grad_norm": 1.04479570880073, + "learning_rate": 1.0617368628628533e-05, + "loss": 0.8922, + "step": 5539 + }, + { + "epoch": 0.49605461973249765, + "grad_norm": 1.0875278809468085, + "learning_rate": 1.0614473846479815e-05, + "loss": 0.8521, + "step": 5540 + }, + { + "epoch": 0.4961441602775757, + "grad_norm": 1.1454456565138784, + "learning_rate": 1.0611579012643562e-05, + "loss": 0.826, + "step": 5541 + }, + { + "epoch": 0.4962337008226538, + "grad_norm": 0.9765731232229852, + "learning_rate": 1.0608684127363274e-05, + "loss": 0.8179, + "step": 5542 + }, + { + "epoch": 0.4963232413677318, + "grad_norm": 0.8943157055690566, + "learning_rate": 1.060578919088246e-05, + "loss": 0.8398, + "step": 5543 + }, + { + "epoch": 0.4964127819128099, + "grad_norm": 1.0658644563426445, + "learning_rate": 1.0602894203444634e-05, + "loss": 0.8558, + "step": 5544 + }, + { + "epoch": 0.49650232245788795, + "grad_norm": 0.9847572261317876, + "learning_rate": 1.0599999165293314e-05, + "loss": 0.8497, + "step": 5545 + }, + { + "epoch": 0.49659186300296604, + "grad_norm": 1.0896747613966464, + "learning_rate": 1.0597104076672016e-05, + "loss": 0.8338, + "step": 5546 + }, + { + "epoch": 0.4966814035480441, + "grad_norm": 1.0182416176095934, + "learning_rate": 1.059420893782427e-05, + "loss": 0.8664, + "step": 5547 + }, + { + "epoch": 0.49677094409312217, + "grad_norm": 1.1166118919325323, + "learning_rate": 1.0591313748993605e-05, + "loss": 0.8607, + "step": 5548 + }, + { + "epoch": 0.49686048463820026, + "grad_norm": 0.8848185870243289, + "learning_rate": 1.0588418510423554e-05, + "loss": 0.8193, + "step": 5549 + }, + { + "epoch": 0.4969500251832783, + "grad_norm": 0.8671343187828997, + "learning_rate": 1.0585523222357657e-05, + "loss": 0.871, + "step": 5550 + }, + { + "epoch": 0.4970395657283564, + "grad_norm": 1.2493932025967889, + "learning_rate": 1.0582627885039454e-05, + "loss": 0.8987, + "step": 5551 + }, + { + "epoch": 0.49712910627343443, + "grad_norm": 0.9142869154250017, + "learning_rate": 1.057973249871249e-05, + "loss": 0.891, + "step": 5552 + }, + { + "epoch": 0.4972186468185125, + "grad_norm": 1.0455783016839881, + "learning_rate": 1.057683706362032e-05, + "loss": 0.7795, + "step": 5553 + }, + { + "epoch": 0.49730818736359056, + "grad_norm": 0.9029708844988072, + "learning_rate": 1.0573941580006494e-05, + "loss": 0.8062, + "step": 5554 + }, + { + "epoch": 0.49739772790866865, + "grad_norm": 1.102077207288504, + "learning_rate": 1.0571046048114573e-05, + "loss": 0.857, + "step": 5555 + }, + { + "epoch": 0.4974872684537467, + "grad_norm": 1.0723032582385812, + "learning_rate": 1.0568150468188119e-05, + "loss": 0.8173, + "step": 5556 + }, + { + "epoch": 0.4975768089988248, + "grad_norm": 0.8992947317065803, + "learning_rate": 1.0565254840470703e-05, + "loss": 0.897, + "step": 5557 + }, + { + "epoch": 0.4976663495439029, + "grad_norm": 0.8563259862578821, + "learning_rate": 1.0562359165205884e-05, + "loss": 0.8282, + "step": 5558 + }, + { + "epoch": 0.4977558900889809, + "grad_norm": 1.0838005421630286, + "learning_rate": 1.055946344263725e-05, + "loss": 0.8351, + "step": 5559 + }, + { + "epoch": 0.497845430634059, + "grad_norm": 0.8947836046135957, + "learning_rate": 1.0556567673008376e-05, + "loss": 0.7789, + "step": 5560 + }, + { + "epoch": 0.49793497117913704, + "grad_norm": 0.9492163018068949, + "learning_rate": 1.0553671856562836e-05, + "loss": 0.7946, + "step": 5561 + }, + { + "epoch": 0.49802451172421514, + "grad_norm": 0.9692056874135808, + "learning_rate": 1.0550775993544232e-05, + "loss": 0.8414, + "step": 5562 + }, + { + "epoch": 0.4981140522692932, + "grad_norm": 0.9531500419874599, + "learning_rate": 1.0547880084196142e-05, + "loss": 0.8732, + "step": 5563 + }, + { + "epoch": 0.49820359281437127, + "grad_norm": 0.9010628502269036, + "learning_rate": 1.0544984128762165e-05, + "loss": 0.8387, + "step": 5564 + }, + { + "epoch": 0.4982931333594493, + "grad_norm": 0.8789157813395974, + "learning_rate": 1.0542088127485896e-05, + "loss": 0.8, + "step": 5565 + }, + { + "epoch": 0.4983826739045274, + "grad_norm": 1.011682194798431, + "learning_rate": 1.0539192080610947e-05, + "loss": 0.7437, + "step": 5566 + }, + { + "epoch": 0.4984722144496055, + "grad_norm": 0.9118967096553129, + "learning_rate": 1.0536295988380914e-05, + "loss": 0.7881, + "step": 5567 + }, + { + "epoch": 0.4985617549946835, + "grad_norm": 0.8865521741903999, + "learning_rate": 1.053339985103941e-05, + "loss": 0.8251, + "step": 5568 + }, + { + "epoch": 0.4986512955397616, + "grad_norm": 0.9113690821592623, + "learning_rate": 1.0530503668830048e-05, + "loss": 0.8346, + "step": 5569 + }, + { + "epoch": 0.49874083608483966, + "grad_norm": 1.0489648222913055, + "learning_rate": 1.0527607441996445e-05, + "loss": 0.8174, + "step": 5570 + }, + { + "epoch": 0.49883037662991775, + "grad_norm": 1.0291688569295008, + "learning_rate": 1.0524711170782225e-05, + "loss": 0.8194, + "step": 5571 + }, + { + "epoch": 0.4989199171749958, + "grad_norm": 1.0336236844813076, + "learning_rate": 1.0521814855431011e-05, + "loss": 0.8136, + "step": 5572 + }, + { + "epoch": 0.4990094577200739, + "grad_norm": 1.0606173896180067, + "learning_rate": 1.0518918496186431e-05, + "loss": 0.8554, + "step": 5573 + }, + { + "epoch": 0.4990989982651519, + "grad_norm": 0.8971481616756988, + "learning_rate": 1.051602209329212e-05, + "loss": 0.8178, + "step": 5574 + }, + { + "epoch": 0.49918853881023, + "grad_norm": 0.9570364411683916, + "learning_rate": 1.0513125646991712e-05, + "loss": 0.7802, + "step": 5575 + }, + { + "epoch": 0.4992780793553081, + "grad_norm": 1.0126625278202206, + "learning_rate": 1.0510229157528844e-05, + "loss": 0.8646, + "step": 5576 + }, + { + "epoch": 0.49936761990038614, + "grad_norm": 0.8540957518673419, + "learning_rate": 1.0507332625147164e-05, + "loss": 0.8116, + "step": 5577 + }, + { + "epoch": 0.49945716044546423, + "grad_norm": 0.9162209421878439, + "learning_rate": 1.0504436050090316e-05, + "loss": 0.7847, + "step": 5578 + }, + { + "epoch": 0.49954670099054227, + "grad_norm": 0.9317959070033501, + "learning_rate": 1.050153943260195e-05, + "loss": 0.8294, + "step": 5579 + }, + { + "epoch": 0.49963624153562036, + "grad_norm": 0.9519429346333402, + "learning_rate": 1.0498642772925724e-05, + "loss": 0.8569, + "step": 5580 + }, + { + "epoch": 0.4997257820806984, + "grad_norm": 0.9345127321472849, + "learning_rate": 1.0495746071305293e-05, + "loss": 0.833, + "step": 5581 + }, + { + "epoch": 0.4998153226257765, + "grad_norm": 0.889599219493746, + "learning_rate": 1.0492849327984316e-05, + "loss": 0.8278, + "step": 5582 + }, + { + "epoch": 0.49990486317085453, + "grad_norm": 0.9514754041890596, + "learning_rate": 1.048995254320646e-05, + "loss": 0.8555, + "step": 5583 + }, + { + "epoch": 0.4999944037159326, + "grad_norm": 0.8351257042788979, + "learning_rate": 1.0487055717215394e-05, + "loss": 0.7965, + "step": 5584 + }, + { + "epoch": 0.5000839442610107, + "grad_norm": 0.9838067955483186, + "learning_rate": 1.0484158850254787e-05, + "loss": 0.8135, + "step": 5585 + }, + { + "epoch": 0.5001734848060888, + "grad_norm": 0.9840477103044719, + "learning_rate": 1.0481261942568315e-05, + "loss": 0.8436, + "step": 5586 + }, + { + "epoch": 0.5002630253511668, + "grad_norm": 1.0105657456983554, + "learning_rate": 1.0478364994399659e-05, + "loss": 0.8229, + "step": 5587 + }, + { + "epoch": 0.5003525658962449, + "grad_norm": 0.9179908232062686, + "learning_rate": 1.0475468005992495e-05, + "loss": 0.834, + "step": 5588 + }, + { + "epoch": 0.5004421064413229, + "grad_norm": 1.02529697336232, + "learning_rate": 1.0472570977590513e-05, + "loss": 0.8151, + "step": 5589 + }, + { + "epoch": 0.5005316469864011, + "grad_norm": 0.9481129392812507, + "learning_rate": 1.0469673909437404e-05, + "loss": 0.859, + "step": 5590 + }, + { + "epoch": 0.5006211875314791, + "grad_norm": 0.9670658230081969, + "learning_rate": 1.0466776801776852e-05, + "loss": 0.7935, + "step": 5591 + }, + { + "epoch": 0.5007107280765571, + "grad_norm": 0.8756442609641216, + "learning_rate": 1.0463879654852556e-05, + "loss": 0.8568, + "step": 5592 + }, + { + "epoch": 0.5008002686216352, + "grad_norm": 0.918635184947109, + "learning_rate": 1.0460982468908218e-05, + "loss": 0.8199, + "step": 5593 + }, + { + "epoch": 0.5008898091667133, + "grad_norm": 0.9524984967249571, + "learning_rate": 1.0458085244187537e-05, + "loss": 0.8024, + "step": 5594 + }, + { + "epoch": 0.5009793497117914, + "grad_norm": 1.0065523010054314, + "learning_rate": 1.0455187980934213e-05, + "loss": 0.7811, + "step": 5595 + }, + { + "epoch": 0.5010688902568694, + "grad_norm": 1.0549528396337997, + "learning_rate": 1.0452290679391965e-05, + "loss": 0.9018, + "step": 5596 + }, + { + "epoch": 0.5011584308019476, + "grad_norm": 1.2804268216657473, + "learning_rate": 1.0449393339804497e-05, + "loss": 0.9132, + "step": 5597 + }, + { + "epoch": 0.5012479713470256, + "grad_norm": 0.9024326326719799, + "learning_rate": 1.0446495962415527e-05, + "loss": 0.8817, + "step": 5598 + }, + { + "epoch": 0.5013375118921036, + "grad_norm": 0.9381537264660221, + "learning_rate": 1.044359854746877e-05, + "loss": 0.8095, + "step": 5599 + }, + { + "epoch": 0.5014270524371817, + "grad_norm": 0.9619689625656384, + "learning_rate": 1.0440701095207948e-05, + "loss": 0.8326, + "step": 5600 + }, + { + "epoch": 0.5015165929822598, + "grad_norm": 0.9192958598831402, + "learning_rate": 1.0437803605876785e-05, + "loss": 0.8526, + "step": 5601 + }, + { + "epoch": 0.5016061335273378, + "grad_norm": 1.2233757488710706, + "learning_rate": 1.0434906079719014e-05, + "loss": 0.7907, + "step": 5602 + }, + { + "epoch": 0.5016956740724159, + "grad_norm": 0.942825602122367, + "learning_rate": 1.0432008516978358e-05, + "loss": 0.8525, + "step": 5603 + }, + { + "epoch": 0.501785214617494, + "grad_norm": 0.9435089972127314, + "learning_rate": 1.0429110917898553e-05, + "loss": 0.8047, + "step": 5604 + }, + { + "epoch": 0.5018747551625721, + "grad_norm": 1.0978093484309475, + "learning_rate": 1.0426213282723337e-05, + "loss": 0.8861, + "step": 5605 + }, + { + "epoch": 0.5019642957076501, + "grad_norm": 1.0168516978382383, + "learning_rate": 1.0423315611696447e-05, + "loss": 0.8368, + "step": 5606 + }, + { + "epoch": 0.5020538362527281, + "grad_norm": 1.0276617535045034, + "learning_rate": 1.0420417905061629e-05, + "loss": 0.7736, + "step": 5607 + }, + { + "epoch": 0.5021433767978063, + "grad_norm": 0.9254192355055794, + "learning_rate": 1.0417520163062627e-05, + "loss": 0.8441, + "step": 5608 + }, + { + "epoch": 0.5022329173428843, + "grad_norm": 0.9339239083227069, + "learning_rate": 1.0414622385943187e-05, + "loss": 0.883, + "step": 5609 + }, + { + "epoch": 0.5023224578879624, + "grad_norm": 1.001848237517298, + "learning_rate": 1.0411724573947065e-05, + "loss": 0.8217, + "step": 5610 + }, + { + "epoch": 0.5024119984330404, + "grad_norm": 1.009722822791706, + "learning_rate": 1.0408826727318014e-05, + "loss": 0.7443, + "step": 5611 + }, + { + "epoch": 0.5025015389781186, + "grad_norm": 0.9294132603640504, + "learning_rate": 1.0405928846299789e-05, + "loss": 0.8289, + "step": 5612 + }, + { + "epoch": 0.5025910795231966, + "grad_norm": 1.0226094017551006, + "learning_rate": 1.0403030931136154e-05, + "loss": 0.8607, + "step": 5613 + }, + { + "epoch": 0.5026806200682746, + "grad_norm": 1.026875333863931, + "learning_rate": 1.0400132982070868e-05, + "loss": 0.8383, + "step": 5614 + }, + { + "epoch": 0.5027701606133528, + "grad_norm": 0.957124238308067, + "learning_rate": 1.03972349993477e-05, + "loss": 0.8264, + "step": 5615 + }, + { + "epoch": 0.5028597011584308, + "grad_norm": 0.9094004290289938, + "learning_rate": 1.039433698321042e-05, + "loss": 0.7768, + "step": 5616 + }, + { + "epoch": 0.5029492417035089, + "grad_norm": 1.0335680484552405, + "learning_rate": 1.03914389339028e-05, + "loss": 0.8495, + "step": 5617 + }, + { + "epoch": 0.5030387822485869, + "grad_norm": 0.9146139794142809, + "learning_rate": 1.038854085166861e-05, + "loss": 0.8259, + "step": 5618 + }, + { + "epoch": 0.503128322793665, + "grad_norm": 0.9034191594328688, + "learning_rate": 1.0385642736751627e-05, + "loss": 0.8347, + "step": 5619 + }, + { + "epoch": 0.5032178633387431, + "grad_norm": 0.8810751238713469, + "learning_rate": 1.0382744589395638e-05, + "loss": 0.8192, + "step": 5620 + }, + { + "epoch": 0.5033074038838211, + "grad_norm": 0.9044205690734595, + "learning_rate": 1.0379846409844421e-05, + "loss": 0.8528, + "step": 5621 + }, + { + "epoch": 0.5033969444288993, + "grad_norm": 0.9125155840134336, + "learning_rate": 1.0376948198341759e-05, + "loss": 0.7811, + "step": 5622 + }, + { + "epoch": 0.5034864849739773, + "grad_norm": 0.9727289194209204, + "learning_rate": 1.0374049955131444e-05, + "loss": 0.8097, + "step": 5623 + }, + { + "epoch": 0.5035760255190553, + "grad_norm": 0.9816898852134502, + "learning_rate": 1.0371151680457268e-05, + "loss": 0.8437, + "step": 5624 + }, + { + "epoch": 0.5036655660641334, + "grad_norm": 0.9214796603260058, + "learning_rate": 1.0368253374563018e-05, + "loss": 0.8542, + "step": 5625 + }, + { + "epoch": 0.5037551066092115, + "grad_norm": 0.9384612439202347, + "learning_rate": 1.0365355037692498e-05, + "loss": 0.8498, + "step": 5626 + }, + { + "epoch": 0.5038446471542896, + "grad_norm": 0.9018324365561423, + "learning_rate": 1.03624566700895e-05, + "loss": 0.8254, + "step": 5627 + }, + { + "epoch": 0.5039341876993676, + "grad_norm": 0.9668605876223945, + "learning_rate": 1.035955827199783e-05, + "loss": 0.8035, + "step": 5628 + }, + { + "epoch": 0.5040237282444456, + "grad_norm": 1.359179921382918, + "learning_rate": 1.035665984366129e-05, + "loss": 0.8322, + "step": 5629 + }, + { + "epoch": 0.5041132687895238, + "grad_norm": 0.9970508299282815, + "learning_rate": 1.0353761385323684e-05, + "loss": 0.8453, + "step": 5630 + }, + { + "epoch": 0.5042028093346018, + "grad_norm": 1.0323354953995, + "learning_rate": 1.0350862897228823e-05, + "loss": 0.8107, + "step": 5631 + }, + { + "epoch": 0.5042923498796799, + "grad_norm": 0.8931896203139051, + "learning_rate": 1.034796437962052e-05, + "loss": 0.8403, + "step": 5632 + }, + { + "epoch": 0.504381890424758, + "grad_norm": 0.9268168685818163, + "learning_rate": 1.034506583274259e-05, + "loss": 0.8649, + "step": 5633 + }, + { + "epoch": 0.504471430969836, + "grad_norm": 0.9183292408588057, + "learning_rate": 1.0342167256838842e-05, + "loss": 0.8149, + "step": 5634 + }, + { + "epoch": 0.5045609715149141, + "grad_norm": 0.8823094840847446, + "learning_rate": 1.03392686521531e-05, + "loss": 0.8016, + "step": 5635 + }, + { + "epoch": 0.5046505120599921, + "grad_norm": 1.1527839163753102, + "learning_rate": 1.0336370018929187e-05, + "loss": 0.8267, + "step": 5636 + }, + { + "epoch": 0.5047400526050703, + "grad_norm": 0.8892244683324797, + "learning_rate": 1.0333471357410923e-05, + "loss": 0.8084, + "step": 5637 + }, + { + "epoch": 0.5048295931501483, + "grad_norm": 0.9485727730380542, + "learning_rate": 1.0330572667842135e-05, + "loss": 0.8378, + "step": 5638 + }, + { + "epoch": 0.5049191336952263, + "grad_norm": 0.9234940048982382, + "learning_rate": 1.032767395046665e-05, + "loss": 0.8688, + "step": 5639 + }, + { + "epoch": 0.5050086742403045, + "grad_norm": 0.9838577263077368, + "learning_rate": 1.0324775205528304e-05, + "loss": 0.8507, + "step": 5640 + }, + { + "epoch": 0.5050982147853825, + "grad_norm": 0.9531037132937147, + "learning_rate": 1.0321876433270922e-05, + "loss": 0.8585, + "step": 5641 + }, + { + "epoch": 0.5051877553304606, + "grad_norm": 0.8929780630608709, + "learning_rate": 1.0318977633938346e-05, + "loss": 0.8638, + "step": 5642 + }, + { + "epoch": 0.5052772958755386, + "grad_norm": 0.8506284264992997, + "learning_rate": 1.0316078807774408e-05, + "loss": 0.8169, + "step": 5643 + }, + { + "epoch": 0.5053668364206167, + "grad_norm": 0.8347783881841847, + "learning_rate": 1.0313179955022952e-05, + "loss": 0.8382, + "step": 5644 + }, + { + "epoch": 0.5054563769656948, + "grad_norm": 1.4144879409799278, + "learning_rate": 1.0310281075927822e-05, + "loss": 0.8749, + "step": 5645 + }, + { + "epoch": 0.5055459175107728, + "grad_norm": 0.8344064144632978, + "learning_rate": 1.0307382170732853e-05, + "loss": 0.7805, + "step": 5646 + }, + { + "epoch": 0.5056354580558509, + "grad_norm": 0.8962987598690999, + "learning_rate": 1.0304483239681904e-05, + "loss": 0.8313, + "step": 5647 + }, + { + "epoch": 0.505724998600929, + "grad_norm": 0.9163357440818541, + "learning_rate": 1.0301584283018813e-05, + "loss": 0.826, + "step": 5648 + }, + { + "epoch": 0.505814539146007, + "grad_norm": 0.8676967806028741, + "learning_rate": 1.0298685300987434e-05, + "loss": 0.8369, + "step": 5649 + }, + { + "epoch": 0.5059040796910851, + "grad_norm": 0.9160550273681637, + "learning_rate": 1.0295786293831624e-05, + "loss": 0.8024, + "step": 5650 + }, + { + "epoch": 0.5059936202361632, + "grad_norm": 0.9878481845130673, + "learning_rate": 1.0292887261795233e-05, + "loss": 0.8119, + "step": 5651 + }, + { + "epoch": 0.5060831607812413, + "grad_norm": 1.0061763393403576, + "learning_rate": 1.0289988205122118e-05, + "loss": 0.8377, + "step": 5652 + }, + { + "epoch": 0.5061727013263193, + "grad_norm": 0.9854810788964102, + "learning_rate": 1.0287089124056144e-05, + "loss": 0.7974, + "step": 5653 + }, + { + "epoch": 0.5062622418713973, + "grad_norm": 0.8535170441105268, + "learning_rate": 1.0284190018841167e-05, + "loss": 0.8137, + "step": 5654 + }, + { + "epoch": 0.5063517824164755, + "grad_norm": 1.1565294516679432, + "learning_rate": 1.028129088972105e-05, + "loss": 0.827, + "step": 5655 + }, + { + "epoch": 0.5064413229615535, + "grad_norm": 0.9241579902072041, + "learning_rate": 1.0278391736939664e-05, + "loss": 0.7765, + "step": 5656 + }, + { + "epoch": 0.5065308635066316, + "grad_norm": 0.928523994970865, + "learning_rate": 1.027549256074087e-05, + "loss": 0.759, + "step": 5657 + }, + { + "epoch": 0.5066204040517097, + "grad_norm": 1.0271839089472052, + "learning_rate": 1.027259336136854e-05, + "loss": 0.8178, + "step": 5658 + }, + { + "epoch": 0.5067099445967878, + "grad_norm": 1.0768939092417489, + "learning_rate": 1.0269694139066541e-05, + "loss": 0.8353, + "step": 5659 + }, + { + "epoch": 0.5067994851418658, + "grad_norm": 0.8800049778567998, + "learning_rate": 1.0266794894078753e-05, + "loss": 0.8561, + "step": 5660 + }, + { + "epoch": 0.5068890256869438, + "grad_norm": 0.9707451025794508, + "learning_rate": 1.026389562664905e-05, + "loss": 0.8394, + "step": 5661 + }, + { + "epoch": 0.506978566232022, + "grad_norm": 1.0759671146740297, + "learning_rate": 1.0260996337021302e-05, + "loss": 0.8249, + "step": 5662 + }, + { + "epoch": 0.5070681067771, + "grad_norm": 0.8665457638347268, + "learning_rate": 1.0258097025439397e-05, + "loss": 0.8097, + "step": 5663 + }, + { + "epoch": 0.507157647322178, + "grad_norm": 0.9510320250166213, + "learning_rate": 1.025519769214721e-05, + "loss": 0.7812, + "step": 5664 + }, + { + "epoch": 0.5072471878672561, + "grad_norm": 0.9347308824193438, + "learning_rate": 1.0252298337388625e-05, + "loss": 0.8104, + "step": 5665 + }, + { + "epoch": 0.5073367284123342, + "grad_norm": 0.9148271693553773, + "learning_rate": 1.0249398961407523e-05, + "loss": 0.8807, + "step": 5666 + }, + { + "epoch": 0.5074262689574123, + "grad_norm": 0.8817225109044043, + "learning_rate": 1.0246499564447796e-05, + "loss": 0.835, + "step": 5667 + }, + { + "epoch": 0.5075158095024903, + "grad_norm": 0.9314648841176935, + "learning_rate": 1.024360014675333e-05, + "loss": 0.8253, + "step": 5668 + }, + { + "epoch": 0.5076053500475685, + "grad_norm": 0.9322579440048805, + "learning_rate": 1.024070070856801e-05, + "loss": 0.8481, + "step": 5669 + }, + { + "epoch": 0.5076948905926465, + "grad_norm": 0.9171280928073983, + "learning_rate": 1.0237801250135733e-05, + "loss": 0.798, + "step": 5670 + }, + { + "epoch": 0.5077844311377245, + "grad_norm": 1.0105736625965325, + "learning_rate": 1.023490177170039e-05, + "loss": 0.822, + "step": 5671 + }, + { + "epoch": 0.5078739716828026, + "grad_norm": 0.992994003637592, + "learning_rate": 1.0232002273505877e-05, + "loss": 0.8141, + "step": 5672 + }, + { + "epoch": 0.5079635122278807, + "grad_norm": 0.9460741283881552, + "learning_rate": 1.0229102755796083e-05, + "loss": 0.8254, + "step": 5673 + }, + { + "epoch": 0.5080530527729588, + "grad_norm": 0.9585354497853238, + "learning_rate": 1.0226203218814916e-05, + "loss": 0.8493, + "step": 5674 + }, + { + "epoch": 0.5081425933180368, + "grad_norm": 0.989025540061667, + "learning_rate": 1.0223303662806274e-05, + "loss": 0.863, + "step": 5675 + }, + { + "epoch": 0.5082321338631149, + "grad_norm": 1.188395277964902, + "learning_rate": 1.0220404088014049e-05, + "loss": 0.8485, + "step": 5676 + }, + { + "epoch": 0.508321674408193, + "grad_norm": 0.926224335645974, + "learning_rate": 1.0217504494682155e-05, + "loss": 0.8358, + "step": 5677 + }, + { + "epoch": 0.508411214953271, + "grad_norm": 0.9688517555777614, + "learning_rate": 1.021460488305449e-05, + "loss": 0.8255, + "step": 5678 + }, + { + "epoch": 0.508500755498349, + "grad_norm": 1.1015507395449424, + "learning_rate": 1.0211705253374962e-05, + "loss": 0.8861, + "step": 5679 + }, + { + "epoch": 0.5085902960434272, + "grad_norm": 1.0239398094009546, + "learning_rate": 1.020880560588748e-05, + "loss": 0.8873, + "step": 5680 + }, + { + "epoch": 0.5086798365885052, + "grad_norm": 0.999686397918096, + "learning_rate": 1.0205905940835948e-05, + "loss": 0.8627, + "step": 5681 + }, + { + "epoch": 0.5087693771335833, + "grad_norm": 0.9894233074326406, + "learning_rate": 1.0203006258464276e-05, + "loss": 0.8355, + "step": 5682 + }, + { + "epoch": 0.5088589176786613, + "grad_norm": 0.8910249281615787, + "learning_rate": 1.0200106559016387e-05, + "loss": 0.8322, + "step": 5683 + }, + { + "epoch": 0.5089484582237395, + "grad_norm": 0.945274786165729, + "learning_rate": 1.0197206842736182e-05, + "loss": 0.7911, + "step": 5684 + }, + { + "epoch": 0.5090379987688175, + "grad_norm": 0.9649104404992614, + "learning_rate": 1.0194307109867579e-05, + "loss": 0.8103, + "step": 5685 + }, + { + "epoch": 0.5091275393138955, + "grad_norm": 1.0349309359091792, + "learning_rate": 1.0191407360654497e-05, + "loss": 0.8337, + "step": 5686 + }, + { + "epoch": 0.5092170798589737, + "grad_norm": 0.9101053504996527, + "learning_rate": 1.0188507595340852e-05, + "loss": 0.8481, + "step": 5687 + }, + { + "epoch": 0.5093066204040517, + "grad_norm": 0.9521517634457553, + "learning_rate": 1.0185607814170561e-05, + "loss": 0.8125, + "step": 5688 + }, + { + "epoch": 0.5093961609491298, + "grad_norm": 1.046247005505056, + "learning_rate": 1.0182708017387545e-05, + "loss": 0.8921, + "step": 5689 + }, + { + "epoch": 0.5094857014942078, + "grad_norm": 0.9736685537150398, + "learning_rate": 1.0179808205235728e-05, + "loss": 0.8925, + "step": 5690 + }, + { + "epoch": 0.509575242039286, + "grad_norm": 0.87872915848908, + "learning_rate": 1.017690837795903e-05, + "loss": 0.8558, + "step": 5691 + }, + { + "epoch": 0.509664782584364, + "grad_norm": 0.9504394403276015, + "learning_rate": 1.0174008535801377e-05, + "loss": 0.8354, + "step": 5692 + }, + { + "epoch": 0.509754323129442, + "grad_norm": 0.8978687322180984, + "learning_rate": 1.017110867900669e-05, + "loss": 0.8089, + "step": 5693 + }, + { + "epoch": 0.5098438636745202, + "grad_norm": 0.9358443916739222, + "learning_rate": 1.01682088078189e-05, + "loss": 0.7893, + "step": 5694 + }, + { + "epoch": 0.5099334042195982, + "grad_norm": 0.9790316375246025, + "learning_rate": 1.0165308922481934e-05, + "loss": 0.8402, + "step": 5695 + }, + { + "epoch": 0.5100229447646762, + "grad_norm": 0.9277316035542695, + "learning_rate": 1.0162409023239718e-05, + "loss": 0.778, + "step": 5696 + }, + { + "epoch": 0.5101124853097543, + "grad_norm": 0.9432252138560028, + "learning_rate": 1.0159509110336185e-05, + "loss": 0.8598, + "step": 5697 + }, + { + "epoch": 0.5102020258548324, + "grad_norm": 0.9254987079443144, + "learning_rate": 1.0156609184015267e-05, + "loss": 0.8437, + "step": 5698 + }, + { + "epoch": 0.5102915663999105, + "grad_norm": 0.9366227658038045, + "learning_rate": 1.0153709244520896e-05, + "loss": 0.8759, + "step": 5699 + }, + { + "epoch": 0.5103811069449885, + "grad_norm": 1.0391836448213363, + "learning_rate": 1.0150809292096999e-05, + "loss": 0.8872, + "step": 5700 + }, + { + "epoch": 0.5104706474900665, + "grad_norm": 1.0040360243389448, + "learning_rate": 1.014790932698752e-05, + "loss": 0.8191, + "step": 5701 + }, + { + "epoch": 0.5105601880351447, + "grad_norm": 0.8388867553743186, + "learning_rate": 1.014500934943639e-05, + "loss": 0.8282, + "step": 5702 + }, + { + "epoch": 0.5106497285802227, + "grad_norm": 0.8999765401073014, + "learning_rate": 1.0142109359687542e-05, + "loss": 0.8168, + "step": 5703 + }, + { + "epoch": 0.5107392691253008, + "grad_norm": 0.9977696804638951, + "learning_rate": 1.0139209357984923e-05, + "loss": 0.8091, + "step": 5704 + }, + { + "epoch": 0.5108288096703789, + "grad_norm": 0.9896412627993668, + "learning_rate": 1.0136309344572465e-05, + "loss": 0.9126, + "step": 5705 + }, + { + "epoch": 0.510918350215457, + "grad_norm": 0.9361163637436256, + "learning_rate": 1.0133409319694107e-05, + "loss": 0.8287, + "step": 5706 + }, + { + "epoch": 0.511007890760535, + "grad_norm": 0.8668929837122763, + "learning_rate": 1.0130509283593795e-05, + "loss": 0.8654, + "step": 5707 + }, + { + "epoch": 0.511097431305613, + "grad_norm": 1.006381330493986, + "learning_rate": 1.0127609236515466e-05, + "loss": 0.8569, + "step": 5708 + }, + { + "epoch": 0.5111869718506912, + "grad_norm": 0.9339336685237292, + "learning_rate": 1.012470917870306e-05, + "loss": 0.8114, + "step": 5709 + }, + { + "epoch": 0.5112765123957692, + "grad_norm": 0.9337146448938235, + "learning_rate": 1.0121809110400531e-05, + "loss": 0.844, + "step": 5710 + }, + { + "epoch": 0.5113660529408472, + "grad_norm": 0.9208362710189054, + "learning_rate": 1.0118909031851814e-05, + "loss": 0.8212, + "step": 5711 + }, + { + "epoch": 0.5114555934859254, + "grad_norm": 1.013699665444257, + "learning_rate": 1.0116008943300852e-05, + "loss": 0.8707, + "step": 5712 + }, + { + "epoch": 0.5115451340310034, + "grad_norm": 0.957475425496647, + "learning_rate": 1.0113108844991603e-05, + "loss": 0.7581, + "step": 5713 + }, + { + "epoch": 0.5116346745760815, + "grad_norm": 1.1032190404957256, + "learning_rate": 1.0110208737168004e-05, + "loss": 0.766, + "step": 5714 + }, + { + "epoch": 0.5117242151211595, + "grad_norm": 0.9372153697871768, + "learning_rate": 1.0107308620074e-05, + "loss": 0.7944, + "step": 5715 + }, + { + "epoch": 0.5118137556662377, + "grad_norm": 0.9115984906035624, + "learning_rate": 1.0104408493953553e-05, + "loss": 0.829, + "step": 5716 + }, + { + "epoch": 0.5119032962113157, + "grad_norm": 1.0455012754565474, + "learning_rate": 1.01015083590506e-05, + "loss": 0.882, + "step": 5717 + }, + { + "epoch": 0.5119928367563937, + "grad_norm": 0.9267008740134861, + "learning_rate": 1.0098608215609093e-05, + "loss": 0.865, + "step": 5718 + }, + { + "epoch": 0.5120823773014718, + "grad_norm": 0.8458052458653388, + "learning_rate": 1.0095708063872987e-05, + "loss": 0.8746, + "step": 5719 + }, + { + "epoch": 0.5121719178465499, + "grad_norm": 0.950756241340812, + "learning_rate": 1.009280790408623e-05, + "loss": 0.8434, + "step": 5720 + }, + { + "epoch": 0.512261458391628, + "grad_norm": 0.9365497973498069, + "learning_rate": 1.0089907736492775e-05, + "loss": 0.8047, + "step": 5721 + }, + { + "epoch": 0.512350998936706, + "grad_norm": 0.8619053666743478, + "learning_rate": 1.008700756133657e-05, + "loss": 0.8396, + "step": 5722 + }, + { + "epoch": 0.5124405394817841, + "grad_norm": 1.0703625203452427, + "learning_rate": 1.0084107378861576e-05, + "loss": 0.8563, + "step": 5723 + }, + { + "epoch": 0.5125300800268622, + "grad_norm": 1.1073593472492376, + "learning_rate": 1.0081207189311744e-05, + "loss": 0.8995, + "step": 5724 + }, + { + "epoch": 0.5126196205719402, + "grad_norm": 1.026812377376004, + "learning_rate": 1.0078306992931026e-05, + "loss": 0.8336, + "step": 5725 + }, + { + "epoch": 0.5127091611170183, + "grad_norm": 0.9046759000873378, + "learning_rate": 1.007540678996338e-05, + "loss": 0.8437, + "step": 5726 + }, + { + "epoch": 0.5127987016620964, + "grad_norm": 0.8416369367749211, + "learning_rate": 1.0072506580652761e-05, + "loss": 0.8447, + "step": 5727 + }, + { + "epoch": 0.5128882422071744, + "grad_norm": 0.9347753644556931, + "learning_rate": 1.0069606365243123e-05, + "loss": 0.8211, + "step": 5728 + }, + { + "epoch": 0.5129777827522525, + "grad_norm": 0.9252804213041933, + "learning_rate": 1.0066706143978426e-05, + "loss": 0.818, + "step": 5729 + }, + { + "epoch": 0.5130673232973306, + "grad_norm": 0.960000271088663, + "learning_rate": 1.0063805917102625e-05, + "loss": 0.8279, + "step": 5730 + }, + { + "epoch": 0.5131568638424087, + "grad_norm": 0.9850243958833704, + "learning_rate": 1.0060905684859676e-05, + "loss": 0.8201, + "step": 5731 + }, + { + "epoch": 0.5132464043874867, + "grad_norm": 0.982282049149327, + "learning_rate": 1.0058005447493543e-05, + "loss": 0.8912, + "step": 5732 + }, + { + "epoch": 0.5133359449325647, + "grad_norm": 1.2195788138486465, + "learning_rate": 1.0055105205248179e-05, + "loss": 0.8399, + "step": 5733 + }, + { + "epoch": 0.5134254854776429, + "grad_norm": 0.8911986986009016, + "learning_rate": 1.0052204958367543e-05, + "loss": 0.7993, + "step": 5734 + }, + { + "epoch": 0.5135150260227209, + "grad_norm": 0.882611232844248, + "learning_rate": 1.0049304707095601e-05, + "loss": 0.829, + "step": 5735 + }, + { + "epoch": 0.513604566567799, + "grad_norm": 0.8881986387566153, + "learning_rate": 1.0046404451676301e-05, + "loss": 0.7916, + "step": 5736 + }, + { + "epoch": 0.513694107112877, + "grad_norm": 1.1044456942046341, + "learning_rate": 1.0043504192353617e-05, + "loss": 0.7922, + "step": 5737 + }, + { + "epoch": 0.5137836476579551, + "grad_norm": 0.9337394092539986, + "learning_rate": 1.0040603929371497e-05, + "loss": 0.8108, + "step": 5738 + }, + { + "epoch": 0.5138731882030332, + "grad_norm": 0.8626039663294794, + "learning_rate": 1.0037703662973908e-05, + "loss": 0.8106, + "step": 5739 + }, + { + "epoch": 0.5139627287481112, + "grad_norm": 0.9295625376946628, + "learning_rate": 1.003480339340481e-05, + "loss": 0.8095, + "step": 5740 + }, + { + "epoch": 0.5140522692931894, + "grad_norm": 0.9708669394459352, + "learning_rate": 1.0031903120908164e-05, + "loss": 0.878, + "step": 5741 + }, + { + "epoch": 0.5141418098382674, + "grad_norm": 0.9724627017908292, + "learning_rate": 1.002900284572793e-05, + "loss": 0.855, + "step": 5742 + }, + { + "epoch": 0.5142313503833454, + "grad_norm": 0.9994421806819294, + "learning_rate": 1.0026102568108073e-05, + "loss": 0.8142, + "step": 5743 + }, + { + "epoch": 0.5143208909284235, + "grad_norm": 0.9993004262931823, + "learning_rate": 1.0023202288292552e-05, + "loss": 0.822, + "step": 5744 + }, + { + "epoch": 0.5144104314735016, + "grad_norm": 0.9415485291817184, + "learning_rate": 1.002030200652533e-05, + "loss": 0.8269, + "step": 5745 + }, + { + "epoch": 0.5144999720185797, + "grad_norm": 0.8186878339858695, + "learning_rate": 1.0017401723050373e-05, + "loss": 0.7756, + "step": 5746 + }, + { + "epoch": 0.5145895125636577, + "grad_norm": 1.0452318836621595, + "learning_rate": 1.0014501438111634e-05, + "loss": 0.9124, + "step": 5747 + }, + { + "epoch": 0.5146790531087359, + "grad_norm": 0.9936390653578736, + "learning_rate": 1.0011601151953086e-05, + "loss": 0.8271, + "step": 5748 + }, + { + "epoch": 0.5147685936538139, + "grad_norm": 1.1648323143979917, + "learning_rate": 1.0008700864818684e-05, + "loss": 0.8792, + "step": 5749 + }, + { + "epoch": 0.5148581341988919, + "grad_norm": 0.9241611919959483, + "learning_rate": 1.0005800576952394e-05, + "loss": 0.8315, + "step": 5750 + }, + { + "epoch": 0.51494767474397, + "grad_norm": 0.9072341229587688, + "learning_rate": 1.0002900288598178e-05, + "loss": 0.8351, + "step": 5751 + }, + { + "epoch": 0.5150372152890481, + "grad_norm": 0.9174708563684035, + "learning_rate": 1e-05, + "loss": 0.837, + "step": 5752 + }, + { + "epoch": 0.5151267558341261, + "grad_norm": 0.9925731320875039, + "learning_rate": 9.997099711401824e-06, + "loss": 0.8403, + "step": 5753 + }, + { + "epoch": 0.5152162963792042, + "grad_norm": 0.9004261651982192, + "learning_rate": 9.994199423047606e-06, + "loss": 0.8183, + "step": 5754 + }, + { + "epoch": 0.5153058369242822, + "grad_norm": 0.93199335448373, + "learning_rate": 9.991299135181321e-06, + "loss": 0.8466, + "step": 5755 + }, + { + "epoch": 0.5153953774693604, + "grad_norm": 1.0153260567968183, + "learning_rate": 9.988398848046919e-06, + "loss": 0.8504, + "step": 5756 + }, + { + "epoch": 0.5154849180144384, + "grad_norm": 0.9423223317027095, + "learning_rate": 9.985498561888368e-06, + "loss": 0.8282, + "step": 5757 + }, + { + "epoch": 0.5155744585595164, + "grad_norm": 0.8948109955018279, + "learning_rate": 9.98259827694963e-06, + "loss": 0.7583, + "step": 5758 + }, + { + "epoch": 0.5156639991045946, + "grad_norm": 0.9254455779568171, + "learning_rate": 9.979697993474671e-06, + "loss": 0.809, + "step": 5759 + }, + { + "epoch": 0.5157535396496726, + "grad_norm": 0.9417150871515682, + "learning_rate": 9.97679771170745e-06, + "loss": 0.7941, + "step": 5760 + }, + { + "epoch": 0.5158430801947507, + "grad_norm": 1.0699868697742625, + "learning_rate": 9.973897431891932e-06, + "loss": 0.8488, + "step": 5761 + }, + { + "epoch": 0.5159326207398287, + "grad_norm": 0.9390206129846707, + "learning_rate": 9.970997154272072e-06, + "loss": 0.7701, + "step": 5762 + }, + { + "epoch": 0.5160221612849069, + "grad_norm": 1.1670611888440607, + "learning_rate": 9.96809687909184e-06, + "loss": 0.8077, + "step": 5763 + }, + { + "epoch": 0.5161117018299849, + "grad_norm": 0.93986931395637, + "learning_rate": 9.965196606595193e-06, + "loss": 0.7987, + "step": 5764 + }, + { + "epoch": 0.5162012423750629, + "grad_norm": 0.9488163763663193, + "learning_rate": 9.962296337026094e-06, + "loss": 0.8759, + "step": 5765 + }, + { + "epoch": 0.5162907829201411, + "grad_norm": 0.9771767832165023, + "learning_rate": 9.959396070628508e-06, + "loss": 0.8141, + "step": 5766 + }, + { + "epoch": 0.5163803234652191, + "grad_norm": 0.9869727106733011, + "learning_rate": 9.956495807646388e-06, + "loss": 0.8101, + "step": 5767 + }, + { + "epoch": 0.5164698640102972, + "grad_norm": 0.8908464818278669, + "learning_rate": 9.9535955483237e-06, + "loss": 0.8084, + "step": 5768 + }, + { + "epoch": 0.5165594045553752, + "grad_norm": 0.8874484652013991, + "learning_rate": 9.950695292904402e-06, + "loss": 0.8367, + "step": 5769 + }, + { + "epoch": 0.5166489451004533, + "grad_norm": 0.9108127737525271, + "learning_rate": 9.947795041632457e-06, + "loss": 0.8373, + "step": 5770 + }, + { + "epoch": 0.5167384856455314, + "grad_norm": 0.9571377336666812, + "learning_rate": 9.944894794751823e-06, + "loss": 0.8499, + "step": 5771 + }, + { + "epoch": 0.5168280261906094, + "grad_norm": 1.1099525240620316, + "learning_rate": 9.941994552506462e-06, + "loss": 0.7452, + "step": 5772 + }, + { + "epoch": 0.5169175667356875, + "grad_norm": 0.9098656941131136, + "learning_rate": 9.939094315140325e-06, + "loss": 0.8004, + "step": 5773 + }, + { + "epoch": 0.5170071072807656, + "grad_norm": 0.9335460843107476, + "learning_rate": 9.93619408289738e-06, + "loss": 0.8006, + "step": 5774 + }, + { + "epoch": 0.5170966478258436, + "grad_norm": 1.3956266387998333, + "learning_rate": 9.933293856021576e-06, + "loss": 0.7372, + "step": 5775 + }, + { + "epoch": 0.5171861883709217, + "grad_norm": 0.8927887634140342, + "learning_rate": 9.930393634756877e-06, + "loss": 0.8273, + "step": 5776 + }, + { + "epoch": 0.5172757289159998, + "grad_norm": 0.9540092831208936, + "learning_rate": 9.927493419347246e-06, + "loss": 0.8389, + "step": 5777 + }, + { + "epoch": 0.5173652694610779, + "grad_norm": 0.9908822230225323, + "learning_rate": 9.924593210036623e-06, + "loss": 0.8303, + "step": 5778 + }, + { + "epoch": 0.5174548100061559, + "grad_norm": 1.0847490114962337, + "learning_rate": 9.921693007068977e-06, + "loss": 0.8537, + "step": 5779 + }, + { + "epoch": 0.5175443505512339, + "grad_norm": 1.0196824876649921, + "learning_rate": 9.91879281068826e-06, + "loss": 0.8464, + "step": 5780 + }, + { + "epoch": 0.5176338910963121, + "grad_norm": 1.1038941403223972, + "learning_rate": 9.915892621138424e-06, + "loss": 0.8336, + "step": 5781 + }, + { + "epoch": 0.5177234316413901, + "grad_norm": 1.120034624716666, + "learning_rate": 9.91299243866343e-06, + "loss": 0.7779, + "step": 5782 + }, + { + "epoch": 0.5178129721864682, + "grad_norm": 0.9763755628576826, + "learning_rate": 9.910092263507232e-06, + "loss": 0.8868, + "step": 5783 + }, + { + "epoch": 0.5179025127315463, + "grad_norm": 0.9171080967412689, + "learning_rate": 9.907192095913773e-06, + "loss": 0.8597, + "step": 5784 + }, + { + "epoch": 0.5179920532766243, + "grad_norm": 0.9999311668989066, + "learning_rate": 9.904291936127015e-06, + "loss": 0.8253, + "step": 5785 + }, + { + "epoch": 0.5180815938217024, + "grad_norm": 0.9092114075698892, + "learning_rate": 9.901391784390909e-06, + "loss": 0.869, + "step": 5786 + }, + { + "epoch": 0.5181711343667804, + "grad_norm": 1.0014071092524957, + "learning_rate": 9.898491640949403e-06, + "loss": 0.8785, + "step": 5787 + }, + { + "epoch": 0.5182606749118586, + "grad_norm": 0.9659893298273803, + "learning_rate": 9.895591506046452e-06, + "loss": 0.9111, + "step": 5788 + }, + { + "epoch": 0.5183502154569366, + "grad_norm": 0.8925807927291977, + "learning_rate": 9.892691379926001e-06, + "loss": 0.8425, + "step": 5789 + }, + { + "epoch": 0.5184397560020146, + "grad_norm": 1.0341940291575344, + "learning_rate": 9.889791262832e-06, + "loss": 0.8685, + "step": 5790 + }, + { + "epoch": 0.5185292965470927, + "grad_norm": 0.9134144583256875, + "learning_rate": 9.886891155008399e-06, + "loss": 0.8611, + "step": 5791 + }, + { + "epoch": 0.5186188370921708, + "grad_norm": 1.13660767906761, + "learning_rate": 9.883991056699146e-06, + "loss": 0.8552, + "step": 5792 + }, + { + "epoch": 0.5187083776372489, + "grad_norm": 1.0032537207678789, + "learning_rate": 9.881090968148191e-06, + "loss": 0.7851, + "step": 5793 + }, + { + "epoch": 0.5187979181823269, + "grad_norm": 0.9405576966840509, + "learning_rate": 9.878190889599474e-06, + "loss": 0.8579, + "step": 5794 + }, + { + "epoch": 0.518887458727405, + "grad_norm": 0.9557382015855391, + "learning_rate": 9.875290821296942e-06, + "loss": 0.8435, + "step": 5795 + }, + { + "epoch": 0.5189769992724831, + "grad_norm": 0.9156785052087755, + "learning_rate": 9.872390763484538e-06, + "loss": 0.8649, + "step": 5796 + }, + { + "epoch": 0.5190665398175611, + "grad_norm": 1.2040477439596808, + "learning_rate": 9.869490716406206e-06, + "loss": 0.8434, + "step": 5797 + }, + { + "epoch": 0.5191560803626392, + "grad_norm": 0.958297624494633, + "learning_rate": 9.866590680305895e-06, + "loss": 0.7794, + "step": 5798 + }, + { + "epoch": 0.5192456209077173, + "grad_norm": 0.922798772163918, + "learning_rate": 9.86369065542754e-06, + "loss": 0.8695, + "step": 5799 + }, + { + "epoch": 0.5193351614527953, + "grad_norm": 0.8531889104717889, + "learning_rate": 9.860790642015082e-06, + "loss": 0.8483, + "step": 5800 + }, + { + "epoch": 0.5194247019978734, + "grad_norm": 0.9521186125760788, + "learning_rate": 9.85789064031246e-06, + "loss": 0.803, + "step": 5801 + }, + { + "epoch": 0.5195142425429515, + "grad_norm": 0.8869257286067888, + "learning_rate": 9.854990650563613e-06, + "loss": 0.8486, + "step": 5802 + }, + { + "epoch": 0.5196037830880296, + "grad_norm": 1.1014017692037756, + "learning_rate": 9.852090673012482e-06, + "loss": 0.822, + "step": 5803 + }, + { + "epoch": 0.5196933236331076, + "grad_norm": 1.0737055563651632, + "learning_rate": 9.849190707903007e-06, + "loss": 0.7752, + "step": 5804 + }, + { + "epoch": 0.5197828641781856, + "grad_norm": 0.9536781436060574, + "learning_rate": 9.84629075547911e-06, + "loss": 0.8319, + "step": 5805 + }, + { + "epoch": 0.5198724047232638, + "grad_norm": 0.9381833726928932, + "learning_rate": 9.843390815984737e-06, + "loss": 0.7517, + "step": 5806 + }, + { + "epoch": 0.5199619452683418, + "grad_norm": 0.8759706209252847, + "learning_rate": 9.840490889663817e-06, + "loss": 0.8317, + "step": 5807 + }, + { + "epoch": 0.5200514858134199, + "grad_norm": 0.9640580984642807, + "learning_rate": 9.837590976760283e-06, + "loss": 0.8835, + "step": 5808 + }, + { + "epoch": 0.5201410263584979, + "grad_norm": 1.009547746810493, + "learning_rate": 9.834691077518068e-06, + "loss": 0.8799, + "step": 5809 + }, + { + "epoch": 0.520230566903576, + "grad_norm": 1.1403178367916549, + "learning_rate": 9.831791192181107e-06, + "loss": 0.831, + "step": 5810 + }, + { + "epoch": 0.5203201074486541, + "grad_norm": 0.9709791692659347, + "learning_rate": 9.828891320993314e-06, + "loss": 0.8828, + "step": 5811 + }, + { + "epoch": 0.5204096479937321, + "grad_norm": 0.9492608794938069, + "learning_rate": 9.825991464198628e-06, + "loss": 0.7922, + "step": 5812 + }, + { + "epoch": 0.5204991885388103, + "grad_norm": 0.8908573527246928, + "learning_rate": 9.823091622040974e-06, + "loss": 0.8059, + "step": 5813 + }, + { + "epoch": 0.5205887290838883, + "grad_norm": 1.0320786474095176, + "learning_rate": 9.820191794764274e-06, + "loss": 0.8714, + "step": 5814 + }, + { + "epoch": 0.5206782696289664, + "grad_norm": 0.9610565202266272, + "learning_rate": 9.81729198261246e-06, + "loss": 0.8588, + "step": 5815 + }, + { + "epoch": 0.5207678101740444, + "grad_norm": 0.8562654924389672, + "learning_rate": 9.814392185829444e-06, + "loss": 0.8537, + "step": 5816 + }, + { + "epoch": 0.5208573507191225, + "grad_norm": 1.055423235434543, + "learning_rate": 9.81149240465915e-06, + "loss": 0.8416, + "step": 5817 + }, + { + "epoch": 0.5209468912642006, + "grad_norm": 0.9748861425554027, + "learning_rate": 9.808592639345504e-06, + "loss": 0.8368, + "step": 5818 + }, + { + "epoch": 0.5210364318092786, + "grad_norm": 0.9743042085775417, + "learning_rate": 9.805692890132423e-06, + "loss": 0.7703, + "step": 5819 + }, + { + "epoch": 0.5211259723543568, + "grad_norm": 0.9601745869020492, + "learning_rate": 9.802793157263821e-06, + "loss": 0.797, + "step": 5820 + }, + { + "epoch": 0.5212155128994348, + "grad_norm": 0.862573726985379, + "learning_rate": 9.79989344098362e-06, + "loss": 0.7494, + "step": 5821 + }, + { + "epoch": 0.5213050534445128, + "grad_norm": 1.0086230219854315, + "learning_rate": 9.796993741535726e-06, + "loss": 0.8229, + "step": 5822 + }, + { + "epoch": 0.5213945939895909, + "grad_norm": 0.9932146565246411, + "learning_rate": 9.794094059164056e-06, + "loss": 0.8176, + "step": 5823 + }, + { + "epoch": 0.521484134534669, + "grad_norm": 1.0233090281124761, + "learning_rate": 9.791194394112525e-06, + "loss": 0.8183, + "step": 5824 + }, + { + "epoch": 0.5215736750797471, + "grad_norm": 0.9047110649219527, + "learning_rate": 9.78829474662504e-06, + "loss": 0.7938, + "step": 5825 + }, + { + "epoch": 0.5216632156248251, + "grad_norm": 0.9643590634414291, + "learning_rate": 9.785395116945515e-06, + "loss": 0.8335, + "step": 5826 + }, + { + "epoch": 0.5217527561699031, + "grad_norm": 0.9109070172157157, + "learning_rate": 9.78249550531785e-06, + "loss": 0.8688, + "step": 5827 + }, + { + "epoch": 0.5218422967149813, + "grad_norm": 0.9280636625788184, + "learning_rate": 9.779595911985954e-06, + "loss": 0.8263, + "step": 5828 + }, + { + "epoch": 0.5219318372600593, + "grad_norm": 1.0010278639508368, + "learning_rate": 9.77669633719373e-06, + "loss": 0.8282, + "step": 5829 + }, + { + "epoch": 0.5220213778051374, + "grad_norm": 0.8771063715473473, + "learning_rate": 9.773796781185084e-06, + "loss": 0.8606, + "step": 5830 + }, + { + "epoch": 0.5221109183502155, + "grad_norm": 0.9673609818196243, + "learning_rate": 9.770897244203917e-06, + "loss": 0.7821, + "step": 5831 + }, + { + "epoch": 0.5222004588952935, + "grad_norm": 0.9669044391018786, + "learning_rate": 9.767997726494128e-06, + "loss": 0.8729, + "step": 5832 + }, + { + "epoch": 0.5222899994403716, + "grad_norm": 0.998191793887367, + "learning_rate": 9.765098228299613e-06, + "loss": 0.8338, + "step": 5833 + }, + { + "epoch": 0.5223795399854496, + "grad_norm": 0.9104302996897441, + "learning_rate": 9.76219874986427e-06, + "loss": 0.8369, + "step": 5834 + }, + { + "epoch": 0.5224690805305278, + "grad_norm": 0.938814262845783, + "learning_rate": 9.759299291431991e-06, + "loss": 0.8259, + "step": 5835 + }, + { + "epoch": 0.5225586210756058, + "grad_norm": 1.0108825982163623, + "learning_rate": 9.756399853246672e-06, + "loss": 0.8425, + "step": 5836 + }, + { + "epoch": 0.5226481616206838, + "grad_norm": 0.9187759251757708, + "learning_rate": 9.75350043555221e-06, + "loss": 0.8019, + "step": 5837 + }, + { + "epoch": 0.522737702165762, + "grad_norm": 0.962780516682919, + "learning_rate": 9.750601038592478e-06, + "loss": 0.8494, + "step": 5838 + }, + { + "epoch": 0.52282724271084, + "grad_norm": 0.9889256985992765, + "learning_rate": 9.74770166261138e-06, + "loss": 0.8476, + "step": 5839 + }, + { + "epoch": 0.5229167832559181, + "grad_norm": 0.8721242794662549, + "learning_rate": 9.744802307852794e-06, + "loss": 0.813, + "step": 5840 + }, + { + "epoch": 0.5230063238009961, + "grad_norm": 0.9829273370527312, + "learning_rate": 9.741902974560606e-06, + "loss": 0.8195, + "step": 5841 + }, + { + "epoch": 0.5230958643460742, + "grad_norm": 0.9267601283305458, + "learning_rate": 9.739003662978696e-06, + "loss": 0.8517, + "step": 5842 + }, + { + "epoch": 0.5231854048911523, + "grad_norm": 0.9356977703447937, + "learning_rate": 9.736104373350957e-06, + "loss": 0.8121, + "step": 5843 + }, + { + "epoch": 0.5232749454362303, + "grad_norm": 0.906517004014335, + "learning_rate": 9.733205105921249e-06, + "loss": 0.8461, + "step": 5844 + }, + { + "epoch": 0.5233644859813084, + "grad_norm": 1.071582804729008, + "learning_rate": 9.73030586093346e-06, + "loss": 0.8602, + "step": 5845 + }, + { + "epoch": 0.5234540265263865, + "grad_norm": 0.9396011870599469, + "learning_rate": 9.727406638631466e-06, + "loss": 0.8123, + "step": 5846 + }, + { + "epoch": 0.5235435670714645, + "grad_norm": 1.0834775431671524, + "learning_rate": 9.724507439259134e-06, + "loss": 0.7939, + "step": 5847 + }, + { + "epoch": 0.5236331076165426, + "grad_norm": 0.9895616449266376, + "learning_rate": 9.721608263060341e-06, + "loss": 0.8079, + "step": 5848 + }, + { + "epoch": 0.5237226481616207, + "grad_norm": 1.0284430091483427, + "learning_rate": 9.718709110278953e-06, + "loss": 0.8691, + "step": 5849 + }, + { + "epoch": 0.5238121887066988, + "grad_norm": 0.9378828482220959, + "learning_rate": 9.715809981158836e-06, + "loss": 0.8599, + "step": 5850 + }, + { + "epoch": 0.5239017292517768, + "grad_norm": 0.958264172084436, + "learning_rate": 9.712910875943858e-06, + "loss": 0.9014, + "step": 5851 + }, + { + "epoch": 0.5239912697968548, + "grad_norm": 0.9000173078012683, + "learning_rate": 9.710011794877883e-06, + "loss": 0.8595, + "step": 5852 + }, + { + "epoch": 0.524080810341933, + "grad_norm": 0.897967087837684, + "learning_rate": 9.707112738204769e-06, + "loss": 0.8385, + "step": 5853 + }, + { + "epoch": 0.524170350887011, + "grad_norm": 1.0923630971545393, + "learning_rate": 9.704213706168381e-06, + "loss": 0.8401, + "step": 5854 + }, + { + "epoch": 0.5242598914320891, + "grad_norm": 0.8980382154203161, + "learning_rate": 9.701314699012569e-06, + "loss": 0.7639, + "step": 5855 + }, + { + "epoch": 0.5243494319771672, + "grad_norm": 1.050974782470295, + "learning_rate": 9.69841571698119e-06, + "loss": 0.8238, + "step": 5856 + }, + { + "epoch": 0.5244389725222453, + "grad_norm": 0.9293012855746424, + "learning_rate": 9.6955167603181e-06, + "loss": 0.7849, + "step": 5857 + }, + { + "epoch": 0.5245285130673233, + "grad_norm": 0.9193257407579004, + "learning_rate": 9.692617829267147e-06, + "loss": 0.8078, + "step": 5858 + }, + { + "epoch": 0.5246180536124013, + "grad_norm": 0.9842900025812967, + "learning_rate": 9.689718924072184e-06, + "loss": 0.9049, + "step": 5859 + }, + { + "epoch": 0.5247075941574795, + "grad_norm": 0.8688706019357838, + "learning_rate": 9.68682004497705e-06, + "loss": 0.8015, + "step": 5860 + }, + { + "epoch": 0.5247971347025575, + "grad_norm": 0.8617228832212375, + "learning_rate": 9.683921192225596e-06, + "loss": 0.8389, + "step": 5861 + }, + { + "epoch": 0.5248866752476355, + "grad_norm": 1.0529376621541577, + "learning_rate": 9.681022366061659e-06, + "loss": 0.816, + "step": 5862 + }, + { + "epoch": 0.5249762157927136, + "grad_norm": 1.1120128795394109, + "learning_rate": 9.678123566729078e-06, + "loss": 0.8329, + "step": 5863 + }, + { + "epoch": 0.5250657563377917, + "grad_norm": 0.9781772771080847, + "learning_rate": 9.675224794471703e-06, + "loss": 0.8432, + "step": 5864 + }, + { + "epoch": 0.5251552968828698, + "grad_norm": 1.0737763735797068, + "learning_rate": 9.672326049533352e-06, + "loss": 0.8463, + "step": 5865 + }, + { + "epoch": 0.5252448374279478, + "grad_norm": 1.040466234950394, + "learning_rate": 9.669427332157868e-06, + "loss": 0.824, + "step": 5866 + }, + { + "epoch": 0.525334377973026, + "grad_norm": 0.991979661483553, + "learning_rate": 9.66652864258908e-06, + "loss": 0.8468, + "step": 5867 + }, + { + "epoch": 0.525423918518104, + "grad_norm": 0.9651207998820273, + "learning_rate": 9.663629981070815e-06, + "loss": 0.8446, + "step": 5868 + }, + { + "epoch": 0.525513459063182, + "grad_norm": 0.9339693636194671, + "learning_rate": 9.660731347846899e-06, + "loss": 0.8904, + "step": 5869 + }, + { + "epoch": 0.5256029996082601, + "grad_norm": 0.8727878749777708, + "learning_rate": 9.657832743161163e-06, + "loss": 0.8245, + "step": 5870 + }, + { + "epoch": 0.5256925401533382, + "grad_norm": 0.9374149933582777, + "learning_rate": 9.654934167257414e-06, + "loss": 0.8451, + "step": 5871 + }, + { + "epoch": 0.5257820806984163, + "grad_norm": 1.0209935149944833, + "learning_rate": 9.652035620379481e-06, + "loss": 0.8422, + "step": 5872 + }, + { + "epoch": 0.5258716212434943, + "grad_norm": 0.8385862080796269, + "learning_rate": 9.649137102771178e-06, + "loss": 0.813, + "step": 5873 + }, + { + "epoch": 0.5259611617885724, + "grad_norm": 1.0830530141041017, + "learning_rate": 9.646238614676317e-06, + "loss": 0.8091, + "step": 5874 + }, + { + "epoch": 0.5260507023336505, + "grad_norm": 1.0029460249718387, + "learning_rate": 9.643340156338715e-06, + "loss": 0.8123, + "step": 5875 + }, + { + "epoch": 0.5261402428787285, + "grad_norm": 0.9312124029916633, + "learning_rate": 9.640441728002174e-06, + "loss": 0.8922, + "step": 5876 + }, + { + "epoch": 0.5262297834238066, + "grad_norm": 0.9656688193923817, + "learning_rate": 9.637543329910502e-06, + "loss": 0.8671, + "step": 5877 + }, + { + "epoch": 0.5263193239688847, + "grad_norm": 0.9920643649023224, + "learning_rate": 9.634644962307504e-06, + "loss": 0.8126, + "step": 5878 + }, + { + "epoch": 0.5264088645139627, + "grad_norm": 0.9772624868750944, + "learning_rate": 9.631746625436982e-06, + "loss": 0.8031, + "step": 5879 + }, + { + "epoch": 0.5264984050590408, + "grad_norm": 1.0461560217261032, + "learning_rate": 9.628848319542735e-06, + "loss": 0.7995, + "step": 5880 + }, + { + "epoch": 0.5265879456041188, + "grad_norm": 0.9015005268891336, + "learning_rate": 9.625950044868559e-06, + "loss": 0.8713, + "step": 5881 + }, + { + "epoch": 0.526677486149197, + "grad_norm": 0.8757632478291026, + "learning_rate": 9.623051801658245e-06, + "loss": 0.765, + "step": 5882 + }, + { + "epoch": 0.526767026694275, + "grad_norm": 0.9170787962195963, + "learning_rate": 9.620153590155582e-06, + "loss": 0.851, + "step": 5883 + }, + { + "epoch": 0.526856567239353, + "grad_norm": 0.9564374513522406, + "learning_rate": 9.617255410604363e-06, + "loss": 0.8252, + "step": 5884 + }, + { + "epoch": 0.5269461077844312, + "grad_norm": 1.1994945033261033, + "learning_rate": 9.614357263248373e-06, + "loss": 0.849, + "step": 5885 + }, + { + "epoch": 0.5270356483295092, + "grad_norm": 1.0433561718584206, + "learning_rate": 9.611459148331394e-06, + "loss": 0.7924, + "step": 5886 + }, + { + "epoch": 0.5271251888745873, + "grad_norm": 1.0110916663792813, + "learning_rate": 9.608561066097204e-06, + "loss": 0.8193, + "step": 5887 + }, + { + "epoch": 0.5272147294196653, + "grad_norm": 1.0017813043442196, + "learning_rate": 9.605663016789583e-06, + "loss": 0.8262, + "step": 5888 + }, + { + "epoch": 0.5273042699647434, + "grad_norm": 0.977004953919621, + "learning_rate": 9.602765000652302e-06, + "loss": 0.9001, + "step": 5889 + }, + { + "epoch": 0.5273938105098215, + "grad_norm": 0.8933301301050861, + "learning_rate": 9.599867017929132e-06, + "loss": 0.8464, + "step": 5890 + }, + { + "epoch": 0.5274833510548995, + "grad_norm": 0.8873789637488516, + "learning_rate": 9.596969068863848e-06, + "loss": 0.8121, + "step": 5891 + }, + { + "epoch": 0.5275728915999777, + "grad_norm": 1.057371966520408, + "learning_rate": 9.594071153700214e-06, + "loss": 0.8781, + "step": 5892 + }, + { + "epoch": 0.5276624321450557, + "grad_norm": 0.879912330116897, + "learning_rate": 9.591173272681991e-06, + "loss": 0.8676, + "step": 5893 + }, + { + "epoch": 0.5277519726901337, + "grad_norm": 0.9142383452943076, + "learning_rate": 9.588275426052938e-06, + "loss": 0.8122, + "step": 5894 + }, + { + "epoch": 0.5278415132352118, + "grad_norm": 1.1722459101116416, + "learning_rate": 9.585377614056815e-06, + "loss": 0.8526, + "step": 5895 + }, + { + "epoch": 0.5279310537802899, + "grad_norm": 0.8721268557421681, + "learning_rate": 9.582479836937374e-06, + "loss": 0.8005, + "step": 5896 + }, + { + "epoch": 0.528020594325368, + "grad_norm": 1.2818764862468448, + "learning_rate": 9.579582094938376e-06, + "loss": 0.8596, + "step": 5897 + }, + { + "epoch": 0.528110134870446, + "grad_norm": 1.0004753610546644, + "learning_rate": 9.576684388303556e-06, + "loss": 0.7527, + "step": 5898 + }, + { + "epoch": 0.528199675415524, + "grad_norm": 1.001270208239588, + "learning_rate": 9.573786717276666e-06, + "loss": 0.8083, + "step": 5899 + }, + { + "epoch": 0.5282892159606022, + "grad_norm": 0.9370050809879644, + "learning_rate": 9.57088908210145e-06, + "loss": 0.8172, + "step": 5900 + }, + { + "epoch": 0.5283787565056802, + "grad_norm": 0.9054228452562488, + "learning_rate": 9.567991483021645e-06, + "loss": 0.8392, + "step": 5901 + }, + { + "epoch": 0.5284682970507583, + "grad_norm": 0.8555623272616262, + "learning_rate": 9.565093920280987e-06, + "loss": 0.7998, + "step": 5902 + }, + { + "epoch": 0.5285578375958364, + "grad_norm": 1.018713883126122, + "learning_rate": 9.562196394123218e-06, + "loss": 0.8316, + "step": 5903 + }, + { + "epoch": 0.5286473781409144, + "grad_norm": 0.9523901582592875, + "learning_rate": 9.559298904792054e-06, + "loss": 0.8373, + "step": 5904 + }, + { + "epoch": 0.5287369186859925, + "grad_norm": 0.8967443151989319, + "learning_rate": 9.556401452531233e-06, + "loss": 0.8583, + "step": 5905 + }, + { + "epoch": 0.5288264592310705, + "grad_norm": 0.9086604107382693, + "learning_rate": 9.553504037584477e-06, + "loss": 0.8283, + "step": 5906 + }, + { + "epoch": 0.5289159997761487, + "grad_norm": 1.0015736747287498, + "learning_rate": 9.550606660195505e-06, + "loss": 0.8727, + "step": 5907 + }, + { + "epoch": 0.5290055403212267, + "grad_norm": 1.0364730088975551, + "learning_rate": 9.54770932060804e-06, + "loss": 0.7718, + "step": 5908 + }, + { + "epoch": 0.5290950808663047, + "grad_norm": 0.8904222557705052, + "learning_rate": 9.544812019065788e-06, + "loss": 0.802, + "step": 5909 + }, + { + "epoch": 0.5291846214113829, + "grad_norm": 0.9847830813716536, + "learning_rate": 9.541914755812467e-06, + "loss": 0.8198, + "step": 5910 + }, + { + "epoch": 0.5292741619564609, + "grad_norm": 0.9178633612998542, + "learning_rate": 9.539017531091783e-06, + "loss": 0.8454, + "step": 5911 + }, + { + "epoch": 0.529363702501539, + "grad_norm": 1.073505987836565, + "learning_rate": 9.536120345147445e-06, + "loss": 0.7644, + "step": 5912 + }, + { + "epoch": 0.529453243046617, + "grad_norm": 0.9696948823977192, + "learning_rate": 9.53322319822315e-06, + "loss": 0.8664, + "step": 5913 + }, + { + "epoch": 0.5295427835916952, + "grad_norm": 0.9112097401699266, + "learning_rate": 9.530326090562601e-06, + "loss": 0.8097, + "step": 5914 + }, + { + "epoch": 0.5296323241367732, + "grad_norm": 1.0830901050727209, + "learning_rate": 9.52742902240949e-06, + "loss": 0.8251, + "step": 5915 + }, + { + "epoch": 0.5297218646818512, + "grad_norm": 0.8476665862605041, + "learning_rate": 9.524531994007507e-06, + "loss": 0.8284, + "step": 5916 + }, + { + "epoch": 0.5298114052269293, + "grad_norm": 1.2405957055038048, + "learning_rate": 9.521635005600344e-06, + "loss": 0.8194, + "step": 5917 + }, + { + "epoch": 0.5299009457720074, + "grad_norm": 0.8614393102738275, + "learning_rate": 9.518738057431686e-06, + "loss": 0.7579, + "step": 5918 + }, + { + "epoch": 0.5299904863170855, + "grad_norm": 0.9711279153362193, + "learning_rate": 9.515841149745217e-06, + "loss": 0.832, + "step": 5919 + }, + { + "epoch": 0.5300800268621635, + "grad_norm": 0.9264237769122139, + "learning_rate": 9.51294428278461e-06, + "loss": 0.8264, + "step": 5920 + }, + { + "epoch": 0.5301695674072416, + "grad_norm": 0.8799422181900238, + "learning_rate": 9.510047456793543e-06, + "loss": 0.8328, + "step": 5921 + }, + { + "epoch": 0.5302591079523197, + "grad_norm": 0.9281002726805655, + "learning_rate": 9.507150672015687e-06, + "loss": 0.834, + "step": 5922 + }, + { + "epoch": 0.5303486484973977, + "grad_norm": 0.9010245385258798, + "learning_rate": 9.504253928694709e-06, + "loss": 0.8858, + "step": 5923 + }, + { + "epoch": 0.5304381890424757, + "grad_norm": 0.9295371224915867, + "learning_rate": 9.50135722707428e-06, + "loss": 0.8543, + "step": 5924 + }, + { + "epoch": 0.5305277295875539, + "grad_norm": 1.1408579285553133, + "learning_rate": 9.498460567398052e-06, + "loss": 0.8506, + "step": 5925 + }, + { + "epoch": 0.5306172701326319, + "grad_norm": 0.9468427776598466, + "learning_rate": 9.495563949909688e-06, + "loss": 0.8362, + "step": 5926 + }, + { + "epoch": 0.53070681067771, + "grad_norm": 0.89914433013515, + "learning_rate": 9.49266737485284e-06, + "loss": 0.8723, + "step": 5927 + }, + { + "epoch": 0.5307963512227881, + "grad_norm": 0.8735474485756044, + "learning_rate": 9.489770842471158e-06, + "loss": 0.7985, + "step": 5928 + }, + { + "epoch": 0.5308858917678662, + "grad_norm": 0.8879425203951726, + "learning_rate": 9.48687435300829e-06, + "loss": 0.8036, + "step": 5929 + }, + { + "epoch": 0.5309754323129442, + "grad_norm": 1.000887088725653, + "learning_rate": 9.483977906707885e-06, + "loss": 0.8318, + "step": 5930 + }, + { + "epoch": 0.5310649728580222, + "grad_norm": 0.9204547605272929, + "learning_rate": 9.48108150381357e-06, + "loss": 0.8261, + "step": 5931 + }, + { + "epoch": 0.5311545134031004, + "grad_norm": 1.013985459865476, + "learning_rate": 9.478185144568992e-06, + "loss": 0.7753, + "step": 5932 + }, + { + "epoch": 0.5312440539481784, + "grad_norm": 0.9244743658158767, + "learning_rate": 9.475288829217779e-06, + "loss": 0.833, + "step": 5933 + }, + { + "epoch": 0.5313335944932565, + "grad_norm": 0.9694281714991287, + "learning_rate": 9.472392558003556e-06, + "loss": 0.8178, + "step": 5934 + }, + { + "epoch": 0.5314231350383345, + "grad_norm": 0.9276933295528008, + "learning_rate": 9.469496331169959e-06, + "loss": 0.812, + "step": 5935 + }, + { + "epoch": 0.5315126755834126, + "grad_norm": 0.8877859249764296, + "learning_rate": 9.466600148960597e-06, + "loss": 0.7791, + "step": 5936 + }, + { + "epoch": 0.5316022161284907, + "grad_norm": 0.9931187359424636, + "learning_rate": 9.46370401161909e-06, + "loss": 0.8104, + "step": 5937 + }, + { + "epoch": 0.5316917566735687, + "grad_norm": 0.9454492064923877, + "learning_rate": 9.460807919389056e-06, + "loss": 0.8412, + "step": 5938 + }, + { + "epoch": 0.5317812972186469, + "grad_norm": 0.9023761699647791, + "learning_rate": 9.457911872514102e-06, + "loss": 0.8394, + "step": 5939 + }, + { + "epoch": 0.5318708377637249, + "grad_norm": 0.9712189697710407, + "learning_rate": 9.455015871237836e-06, + "loss": 0.7986, + "step": 5940 + }, + { + "epoch": 0.5319603783088029, + "grad_norm": 0.9531808597072575, + "learning_rate": 9.452119915803863e-06, + "loss": 0.7965, + "step": 5941 + }, + { + "epoch": 0.532049918853881, + "grad_norm": 1.0028651978019683, + "learning_rate": 9.449224006455773e-06, + "loss": 0.7851, + "step": 5942 + }, + { + "epoch": 0.5321394593989591, + "grad_norm": 0.9838576945272512, + "learning_rate": 9.446328143437165e-06, + "loss": 0.8739, + "step": 5943 + }, + { + "epoch": 0.5322289999440372, + "grad_norm": 1.146795578743294, + "learning_rate": 9.443432326991627e-06, + "loss": 0.8112, + "step": 5944 + }, + { + "epoch": 0.5323185404891152, + "grad_norm": 0.9662979337446806, + "learning_rate": 9.44053655736275e-06, + "loss": 0.8503, + "step": 5945 + }, + { + "epoch": 0.5324080810341933, + "grad_norm": 0.8736412417807512, + "learning_rate": 9.437640834794118e-06, + "loss": 0.7599, + "step": 5946 + }, + { + "epoch": 0.5324976215792714, + "grad_norm": 1.1570262924970436, + "learning_rate": 9.434745159529302e-06, + "loss": 0.8406, + "step": 5947 + }, + { + "epoch": 0.5325871621243494, + "grad_norm": 0.9460882706711075, + "learning_rate": 9.431849531811883e-06, + "loss": 0.8448, + "step": 5948 + }, + { + "epoch": 0.5326767026694275, + "grad_norm": 0.8477959073111798, + "learning_rate": 9.42895395188543e-06, + "loss": 0.8371, + "step": 5949 + }, + { + "epoch": 0.5327662432145056, + "grad_norm": 0.9765876344319901, + "learning_rate": 9.426058419993507e-06, + "loss": 0.812, + "step": 5950 + }, + { + "epoch": 0.5328557837595836, + "grad_norm": 1.001455336352303, + "learning_rate": 9.423162936379681e-06, + "loss": 0.9003, + "step": 5951 + }, + { + "epoch": 0.5329453243046617, + "grad_norm": 0.8967252943651437, + "learning_rate": 9.420267501287512e-06, + "loss": 0.7933, + "step": 5952 + }, + { + "epoch": 0.5330348648497397, + "grad_norm": 0.9572983931016393, + "learning_rate": 9.41737211496055e-06, + "loss": 0.8932, + "step": 5953 + }, + { + "epoch": 0.5331244053948179, + "grad_norm": 0.9244813543203914, + "learning_rate": 9.414476777642347e-06, + "loss": 0.8539, + "step": 5954 + }, + { + "epoch": 0.5332139459398959, + "grad_norm": 0.910680283768178, + "learning_rate": 9.411581489576447e-06, + "loss": 0.8487, + "step": 5955 + }, + { + "epoch": 0.5333034864849739, + "grad_norm": 0.9249565045236668, + "learning_rate": 9.408686251006395e-06, + "loss": 0.8367, + "step": 5956 + }, + { + "epoch": 0.5333930270300521, + "grad_norm": 1.0795302881979438, + "learning_rate": 9.405791062175735e-06, + "loss": 0.8371, + "step": 5957 + }, + { + "epoch": 0.5334825675751301, + "grad_norm": 0.9819786441181229, + "learning_rate": 9.402895923327987e-06, + "loss": 0.8581, + "step": 5958 + }, + { + "epoch": 0.5335721081202082, + "grad_norm": 0.8953573174441338, + "learning_rate": 9.400000834706692e-06, + "loss": 0.8141, + "step": 5959 + }, + { + "epoch": 0.5336616486652862, + "grad_norm": 1.0973721942494425, + "learning_rate": 9.39710579655537e-06, + "loss": 0.8322, + "step": 5960 + }, + { + "epoch": 0.5337511892103644, + "grad_norm": 1.1538945971376044, + "learning_rate": 9.394210809117543e-06, + "loss": 0.8537, + "step": 5961 + }, + { + "epoch": 0.5338407297554424, + "grad_norm": 1.1898809745085779, + "learning_rate": 9.391315872636728e-06, + "loss": 0.8641, + "step": 5962 + }, + { + "epoch": 0.5339302703005204, + "grad_norm": 1.0622005854470915, + "learning_rate": 9.388420987356443e-06, + "loss": 0.8464, + "step": 5963 + }, + { + "epoch": 0.5340198108455986, + "grad_norm": 0.8516865198026251, + "learning_rate": 9.385526153520186e-06, + "loss": 0.8011, + "step": 5964 + }, + { + "epoch": 0.5341093513906766, + "grad_norm": 1.0475635214203323, + "learning_rate": 9.38263137137147e-06, + "loss": 0.8776, + "step": 5965 + }, + { + "epoch": 0.5341988919357546, + "grad_norm": 0.9767623830341828, + "learning_rate": 9.379736641153791e-06, + "loss": 0.8245, + "step": 5966 + }, + { + "epoch": 0.5342884324808327, + "grad_norm": 0.9102020121864909, + "learning_rate": 9.376841963110644e-06, + "loss": 0.8575, + "step": 5967 + }, + { + "epoch": 0.5343779730259108, + "grad_norm": 0.9261795506019623, + "learning_rate": 9.373947337485521e-06, + "loss": 0.8006, + "step": 5968 + }, + { + "epoch": 0.5344675135709889, + "grad_norm": 1.28416824632598, + "learning_rate": 9.371052764521907e-06, + "loss": 0.8332, + "step": 5969 + }, + { + "epoch": 0.5345570541160669, + "grad_norm": 0.9542747370790804, + "learning_rate": 9.368158244463286e-06, + "loss": 0.8321, + "step": 5970 + }, + { + "epoch": 0.534646594661145, + "grad_norm": 1.0603271293390129, + "learning_rate": 9.36526377755313e-06, + "loss": 0.9048, + "step": 5971 + }, + { + "epoch": 0.5347361352062231, + "grad_norm": 0.9778998649183257, + "learning_rate": 9.36236936403492e-06, + "loss": 0.8629, + "step": 5972 + }, + { + "epoch": 0.5348256757513011, + "grad_norm": 1.0174339162479573, + "learning_rate": 9.359475004152122e-06, + "loss": 0.8743, + "step": 5973 + }, + { + "epoch": 0.5349152162963792, + "grad_norm": 0.8805067028232537, + "learning_rate": 9.3565806981482e-06, + "loss": 0.8148, + "step": 5974 + }, + { + "epoch": 0.5350047568414573, + "grad_norm": 1.164120370745813, + "learning_rate": 9.353686446266611e-06, + "loss": 0.8059, + "step": 5975 + }, + { + "epoch": 0.5350942973865354, + "grad_norm": 1.169431984103252, + "learning_rate": 9.350792248750814e-06, + "loss": 0.8258, + "step": 5976 + }, + { + "epoch": 0.5351838379316134, + "grad_norm": 0.9313698513720441, + "learning_rate": 9.347898105844255e-06, + "loss": 0.7955, + "step": 5977 + }, + { + "epoch": 0.5352733784766914, + "grad_norm": 0.8731411992557386, + "learning_rate": 9.345004017790382e-06, + "loss": 0.8359, + "step": 5978 + }, + { + "epoch": 0.5353629190217696, + "grad_norm": 0.971084304185613, + "learning_rate": 9.34210998483264e-06, + "loss": 0.8077, + "step": 5979 + }, + { + "epoch": 0.5354524595668476, + "grad_norm": 0.8641044510659649, + "learning_rate": 9.339216007214462e-06, + "loss": 0.8119, + "step": 5980 + }, + { + "epoch": 0.5355420001119257, + "grad_norm": 0.949280292360375, + "learning_rate": 9.336322085179277e-06, + "loss": 0.8465, + "step": 5981 + }, + { + "epoch": 0.5356315406570038, + "grad_norm": 0.990935611199923, + "learning_rate": 9.333428218970517e-06, + "loss": 0.788, + "step": 5982 + }, + { + "epoch": 0.5357210812020818, + "grad_norm": 1.0069845958750356, + "learning_rate": 9.3305344088316e-06, + "loss": 0.799, + "step": 5983 + }, + { + "epoch": 0.5358106217471599, + "grad_norm": 0.9946052293714969, + "learning_rate": 9.327640655005951e-06, + "loss": 0.8509, + "step": 5984 + }, + { + "epoch": 0.5359001622922379, + "grad_norm": 0.9468533198482125, + "learning_rate": 9.32474695773698e-06, + "loss": 0.8135, + "step": 5985 + }, + { + "epoch": 0.5359897028373161, + "grad_norm": 0.8364696718689509, + "learning_rate": 9.32185331726809e-06, + "loss": 0.8379, + "step": 5986 + }, + { + "epoch": 0.5360792433823941, + "grad_norm": 0.9321307070844654, + "learning_rate": 9.318959733842692e-06, + "loss": 0.8512, + "step": 5987 + }, + { + "epoch": 0.5361687839274721, + "grad_norm": 0.9354559714736931, + "learning_rate": 9.316066207704184e-06, + "loss": 0.8322, + "step": 5988 + }, + { + "epoch": 0.5362583244725502, + "grad_norm": 0.8951707236626564, + "learning_rate": 9.313172739095951e-06, + "loss": 0.7512, + "step": 5989 + }, + { + "epoch": 0.5363478650176283, + "grad_norm": 0.8374592721818452, + "learning_rate": 9.310279328261399e-06, + "loss": 0.7794, + "step": 5990 + }, + { + "epoch": 0.5364374055627064, + "grad_norm": 0.9050864282223952, + "learning_rate": 9.307385975443893e-06, + "loss": 0.8814, + "step": 5991 + }, + { + "epoch": 0.5365269461077844, + "grad_norm": 0.9324966903121951, + "learning_rate": 9.304492680886825e-06, + "loss": 0.8098, + "step": 5992 + }, + { + "epoch": 0.5366164866528625, + "grad_norm": 0.9007864185018738, + "learning_rate": 9.301599444833567e-06, + "loss": 0.8965, + "step": 5993 + }, + { + "epoch": 0.5367060271979406, + "grad_norm": 1.0909618926944298, + "learning_rate": 9.298706267527487e-06, + "loss": 0.8201, + "step": 5994 + }, + { + "epoch": 0.5367955677430186, + "grad_norm": 0.9169705679735011, + "learning_rate": 9.295813149211954e-06, + "loss": 0.8238, + "step": 5995 + }, + { + "epoch": 0.5368851082880967, + "grad_norm": 1.0327180026288332, + "learning_rate": 9.292920090130321e-06, + "loss": 0.8059, + "step": 5996 + }, + { + "epoch": 0.5369746488331748, + "grad_norm": 0.8921533366183012, + "learning_rate": 9.290027090525945e-06, + "loss": 0.8144, + "step": 5997 + }, + { + "epoch": 0.5370641893782528, + "grad_norm": 0.9570832935594241, + "learning_rate": 9.287134150642175e-06, + "loss": 0.8778, + "step": 5998 + }, + { + "epoch": 0.5371537299233309, + "grad_norm": 1.0479740740578811, + "learning_rate": 9.284241270722359e-06, + "loss": 0.8456, + "step": 5999 + }, + { + "epoch": 0.537243270468409, + "grad_norm": 1.01345398155251, + "learning_rate": 9.281348451009837e-06, + "loss": 0.8433, + "step": 6000 + }, + { + "epoch": 0.5373328110134871, + "grad_norm": 0.8383155947726476, + "learning_rate": 9.27845569174794e-06, + "loss": 0.8402, + "step": 6001 + }, + { + "epoch": 0.5374223515585651, + "grad_norm": 0.9074713301212324, + "learning_rate": 9.275562993180001e-06, + "loss": 0.8262, + "step": 6002 + }, + { + "epoch": 0.5375118921036431, + "grad_norm": 0.8861145166620412, + "learning_rate": 9.272670355549338e-06, + "loss": 0.8326, + "step": 6003 + }, + { + "epoch": 0.5376014326487213, + "grad_norm": 0.9868744579591654, + "learning_rate": 9.269777779099276e-06, + "loss": 0.8334, + "step": 6004 + }, + { + "epoch": 0.5376909731937993, + "grad_norm": 0.9599648381030712, + "learning_rate": 9.266885264073128e-06, + "loss": 0.8421, + "step": 6005 + }, + { + "epoch": 0.5377805137388774, + "grad_norm": 0.9698199949636004, + "learning_rate": 9.263992810714203e-06, + "loss": 0.7773, + "step": 6006 + }, + { + "epoch": 0.5378700542839554, + "grad_norm": 0.836509847908596, + "learning_rate": 9.261100419265807e-06, + "loss": 0.8102, + "step": 6007 + }, + { + "epoch": 0.5379595948290335, + "grad_norm": 0.9083574463951704, + "learning_rate": 9.258208089971232e-06, + "loss": 0.8196, + "step": 6008 + }, + { + "epoch": 0.5380491353741116, + "grad_norm": 1.0146169089608352, + "learning_rate": 9.255315823073775e-06, + "loss": 0.7759, + "step": 6009 + }, + { + "epoch": 0.5381386759191896, + "grad_norm": 1.0770066218035734, + "learning_rate": 9.252423618816724e-06, + "loss": 0.8305, + "step": 6010 + }, + { + "epoch": 0.5382282164642678, + "grad_norm": 0.9674553879815466, + "learning_rate": 9.249531477443365e-06, + "loss": 0.8136, + "step": 6011 + }, + { + "epoch": 0.5383177570093458, + "grad_norm": 0.8719930878061914, + "learning_rate": 9.246639399196972e-06, + "loss": 0.8446, + "step": 6012 + }, + { + "epoch": 0.5384072975544238, + "grad_norm": 0.9843557122170272, + "learning_rate": 9.243747384320816e-06, + "loss": 0.831, + "step": 6013 + }, + { + "epoch": 0.5384968380995019, + "grad_norm": 1.0931369512169629, + "learning_rate": 9.240855433058166e-06, + "loss": 0.8147, + "step": 6014 + }, + { + "epoch": 0.53858637864458, + "grad_norm": 0.9026738447887179, + "learning_rate": 9.237963545652286e-06, + "loss": 0.8075, + "step": 6015 + }, + { + "epoch": 0.5386759191896581, + "grad_norm": 0.9153457022947674, + "learning_rate": 9.235071722346424e-06, + "loss": 0.8583, + "step": 6016 + }, + { + "epoch": 0.5387654597347361, + "grad_norm": 0.9809408440018338, + "learning_rate": 9.232179963383843e-06, + "loss": 0.8261, + "step": 6017 + }, + { + "epoch": 0.5388550002798143, + "grad_norm": 0.989652558914238, + "learning_rate": 9.229288269007776e-06, + "loss": 0.8018, + "step": 6018 + }, + { + "epoch": 0.5389445408248923, + "grad_norm": 1.0141192984038463, + "learning_rate": 9.226396639461468e-06, + "loss": 0.7657, + "step": 6019 + }, + { + "epoch": 0.5390340813699703, + "grad_norm": 1.010602187843883, + "learning_rate": 9.223505074988157e-06, + "loss": 0.8858, + "step": 6020 + }, + { + "epoch": 0.5391236219150484, + "grad_norm": 0.892782109658125, + "learning_rate": 9.220613575831066e-06, + "loss": 0.828, + "step": 6021 + }, + { + "epoch": 0.5392131624601265, + "grad_norm": 0.9867203714512734, + "learning_rate": 9.21772214223342e-06, + "loss": 0.8245, + "step": 6022 + }, + { + "epoch": 0.5393027030052046, + "grad_norm": 1.1217624986525767, + "learning_rate": 9.214830774438447e-06, + "loss": 0.7392, + "step": 6023 + }, + { + "epoch": 0.5393922435502826, + "grad_norm": 1.1171142759317856, + "learning_rate": 9.211939472689342e-06, + "loss": 0.8141, + "step": 6024 + }, + { + "epoch": 0.5394817840953606, + "grad_norm": 0.9035446392146811, + "learning_rate": 9.209048237229321e-06, + "loss": 0.8976, + "step": 6025 + }, + { + "epoch": 0.5395713246404388, + "grad_norm": 1.0852354666805286, + "learning_rate": 9.206157068301587e-06, + "loss": 0.8649, + "step": 6026 + }, + { + "epoch": 0.5396608651855168, + "grad_norm": 0.9175996699269234, + "learning_rate": 9.203265966149332e-06, + "loss": 0.8235, + "step": 6027 + }, + { + "epoch": 0.5397504057305949, + "grad_norm": 0.8985212666519329, + "learning_rate": 9.20037493101575e-06, + "loss": 0.7998, + "step": 6028 + }, + { + "epoch": 0.539839946275673, + "grad_norm": 0.9233585778380023, + "learning_rate": 9.197483963144024e-06, + "loss": 0.8538, + "step": 6029 + }, + { + "epoch": 0.539929486820751, + "grad_norm": 1.0046108348134133, + "learning_rate": 9.194593062777328e-06, + "loss": 0.8532, + "step": 6030 + }, + { + "epoch": 0.5400190273658291, + "grad_norm": 0.9342094258349481, + "learning_rate": 9.191702230158838e-06, + "loss": 0.7779, + "step": 6031 + }, + { + "epoch": 0.5401085679109071, + "grad_norm": 1.0025370734767913, + "learning_rate": 9.188811465531725e-06, + "loss": 0.8522, + "step": 6032 + }, + { + "epoch": 0.5401981084559853, + "grad_norm": 0.8850759096374533, + "learning_rate": 9.185920769139148e-06, + "loss": 0.835, + "step": 6033 + }, + { + "epoch": 0.5402876490010633, + "grad_norm": 0.8613278081126127, + "learning_rate": 9.183030141224265e-06, + "loss": 0.8205, + "step": 6034 + }, + { + "epoch": 0.5403771895461413, + "grad_norm": 0.9378977307033007, + "learning_rate": 9.180139582030222e-06, + "loss": 0.7789, + "step": 6035 + }, + { + "epoch": 0.5404667300912195, + "grad_norm": 0.9113057673799452, + "learning_rate": 9.177249091800167e-06, + "loss": 0.7987, + "step": 6036 + }, + { + "epoch": 0.5405562706362975, + "grad_norm": 1.0267154210330178, + "learning_rate": 9.174358670777232e-06, + "loss": 0.8308, + "step": 6037 + }, + { + "epoch": 0.5406458111813756, + "grad_norm": 0.9575922009271098, + "learning_rate": 9.17146831920456e-06, + "loss": 0.8408, + "step": 6038 + }, + { + "epoch": 0.5407353517264536, + "grad_norm": 1.014334853712665, + "learning_rate": 9.168578037325275e-06, + "loss": 0.8732, + "step": 6039 + }, + { + "epoch": 0.5408248922715317, + "grad_norm": 0.9568020936634541, + "learning_rate": 9.165687825382493e-06, + "loss": 0.856, + "step": 6040 + }, + { + "epoch": 0.5409144328166098, + "grad_norm": 0.9287275228688183, + "learning_rate": 9.162797683619333e-06, + "loss": 0.8664, + "step": 6041 + }, + { + "epoch": 0.5410039733616878, + "grad_norm": 1.0345732045531393, + "learning_rate": 9.159907612278904e-06, + "loss": 0.8845, + "step": 6042 + }, + { + "epoch": 0.5410935139067659, + "grad_norm": 0.9456855050235818, + "learning_rate": 9.157017611604306e-06, + "loss": 0.7896, + "step": 6043 + }, + { + "epoch": 0.541183054451844, + "grad_norm": 1.1644985646671988, + "learning_rate": 9.154127681838642e-06, + "loss": 0.867, + "step": 6044 + }, + { + "epoch": 0.541272594996922, + "grad_norm": 1.0316801563374332, + "learning_rate": 9.151237823225004e-06, + "loss": 0.8065, + "step": 6045 + }, + { + "epoch": 0.5413621355420001, + "grad_norm": 0.9379106499281991, + "learning_rate": 9.14834803600647e-06, + "loss": 0.8701, + "step": 6046 + }, + { + "epoch": 0.5414516760870782, + "grad_norm": 0.9439221009556342, + "learning_rate": 9.145458320426126e-06, + "loss": 0.7924, + "step": 6047 + }, + { + "epoch": 0.5415412166321563, + "grad_norm": 0.958022645054481, + "learning_rate": 9.142568676727043e-06, + "loss": 0.8598, + "step": 6048 + }, + { + "epoch": 0.5416307571772343, + "grad_norm": 0.9371390650033266, + "learning_rate": 9.139679105152285e-06, + "loss": 0.8891, + "step": 6049 + }, + { + "epoch": 0.5417202977223123, + "grad_norm": 1.0467191447126114, + "learning_rate": 9.136789605944926e-06, + "loss": 0.8046, + "step": 6050 + }, + { + "epoch": 0.5418098382673905, + "grad_norm": 1.0179290967763104, + "learning_rate": 9.133900179348008e-06, + "loss": 0.8553, + "step": 6051 + }, + { + "epoch": 0.5418993788124685, + "grad_norm": 1.0165602746373275, + "learning_rate": 9.131010825604581e-06, + "loss": 0.831, + "step": 6052 + }, + { + "epoch": 0.5419889193575466, + "grad_norm": 0.8956327535125366, + "learning_rate": 9.128121544957694e-06, + "loss": 0.8407, + "step": 6053 + }, + { + "epoch": 0.5420784599026247, + "grad_norm": 0.9574699122065526, + "learning_rate": 9.125232337650382e-06, + "loss": 0.8089, + "step": 6054 + }, + { + "epoch": 0.5421680004477027, + "grad_norm": 0.8962931259112521, + "learning_rate": 9.122343203925674e-06, + "loss": 0.82, + "step": 6055 + }, + { + "epoch": 0.5422575409927808, + "grad_norm": 0.9417108963585707, + "learning_rate": 9.1194541440266e-06, + "loss": 0.8307, + "step": 6056 + }, + { + "epoch": 0.5423470815378588, + "grad_norm": 1.0121605947568275, + "learning_rate": 9.11656515819617e-06, + "loss": 0.8371, + "step": 6057 + }, + { + "epoch": 0.542436622082937, + "grad_norm": 0.8890636147088912, + "learning_rate": 9.113676246677397e-06, + "loss": 0.7889, + "step": 6058 + }, + { + "epoch": 0.542526162628015, + "grad_norm": 1.0230472478080912, + "learning_rate": 9.110787409713295e-06, + "loss": 0.8751, + "step": 6059 + }, + { + "epoch": 0.542615703173093, + "grad_norm": 1.7828499583886108, + "learning_rate": 9.107898647546855e-06, + "loss": 0.8069, + "step": 6060 + }, + { + "epoch": 0.5427052437181711, + "grad_norm": 0.8784478988492977, + "learning_rate": 9.105009960421078e-06, + "loss": 0.7716, + "step": 6061 + }, + { + "epoch": 0.5427947842632492, + "grad_norm": 0.8500551213183383, + "learning_rate": 9.102121348578945e-06, + "loss": 0.7995, + "step": 6062 + }, + { + "epoch": 0.5428843248083273, + "grad_norm": 0.9684694095905027, + "learning_rate": 9.099232812263436e-06, + "loss": 0.8419, + "step": 6063 + }, + { + "epoch": 0.5429738653534053, + "grad_norm": 1.0055519255021597, + "learning_rate": 9.096344351717528e-06, + "loss": 0.8136, + "step": 6064 + }, + { + "epoch": 0.5430634058984835, + "grad_norm": 1.0303591059031552, + "learning_rate": 9.093455967184188e-06, + "loss": 0.7835, + "step": 6065 + }, + { + "epoch": 0.5431529464435615, + "grad_norm": 0.9206225357158364, + "learning_rate": 9.090567658906381e-06, + "loss": 0.8127, + "step": 6066 + }, + { + "epoch": 0.5432424869886395, + "grad_norm": 1.5089140014009896, + "learning_rate": 9.087679427127059e-06, + "loss": 0.8357, + "step": 6067 + }, + { + "epoch": 0.5433320275337176, + "grad_norm": 0.88387917478891, + "learning_rate": 9.084791272089167e-06, + "loss": 0.7903, + "step": 6068 + }, + { + "epoch": 0.5434215680787957, + "grad_norm": 1.2478442414487725, + "learning_rate": 9.081903194035653e-06, + "loss": 0.8463, + "step": 6069 + }, + { + "epoch": 0.5435111086238738, + "grad_norm": 0.9586143254105307, + "learning_rate": 9.079015193209447e-06, + "loss": 0.8077, + "step": 6070 + }, + { + "epoch": 0.5436006491689518, + "grad_norm": 0.918830581257915, + "learning_rate": 9.076127269853486e-06, + "loss": 0.7762, + "step": 6071 + }, + { + "epoch": 0.5436901897140299, + "grad_norm": 0.9791065848298622, + "learning_rate": 9.07323942421069e-06, + "loss": 0.8571, + "step": 6072 + }, + { + "epoch": 0.543779730259108, + "grad_norm": 1.1067430162198335, + "learning_rate": 9.07035165652397e-06, + "loss": 0.8555, + "step": 6073 + }, + { + "epoch": 0.543869270804186, + "grad_norm": 0.9142661318842814, + "learning_rate": 9.06746396703624e-06, + "loss": 0.8131, + "step": 6074 + }, + { + "epoch": 0.543958811349264, + "grad_norm": 0.8827728075773811, + "learning_rate": 9.064576355990401e-06, + "loss": 0.7949, + "step": 6075 + }, + { + "epoch": 0.5440483518943422, + "grad_norm": 0.9554625020502936, + "learning_rate": 9.06168882362935e-06, + "loss": 0.7611, + "step": 6076 + }, + { + "epoch": 0.5441378924394202, + "grad_norm": 1.16519233349128, + "learning_rate": 9.058801370195985e-06, + "loss": 0.8029, + "step": 6077 + }, + { + "epoch": 0.5442274329844983, + "grad_norm": 0.9267329252653302, + "learning_rate": 9.055913995933174e-06, + "loss": 0.838, + "step": 6078 + }, + { + "epoch": 0.5443169735295763, + "grad_norm": 1.0075344199258005, + "learning_rate": 9.053026701083801e-06, + "loss": 0.783, + "step": 6079 + }, + { + "epoch": 0.5444065140746545, + "grad_norm": 1.0423944995912053, + "learning_rate": 9.050139485890738e-06, + "loss": 0.8357, + "step": 6080 + }, + { + "epoch": 0.5444960546197325, + "grad_norm": 1.132718910259074, + "learning_rate": 9.047252350596846e-06, + "loss": 0.8228, + "step": 6081 + }, + { + "epoch": 0.5445855951648105, + "grad_norm": 0.9703651213886199, + "learning_rate": 9.044365295444982e-06, + "loss": 0.7845, + "step": 6082 + }, + { + "epoch": 0.5446751357098887, + "grad_norm": 0.9247358938486525, + "learning_rate": 9.041478320677998e-06, + "loss": 0.8411, + "step": 6083 + }, + { + "epoch": 0.5447646762549667, + "grad_norm": 0.8687925445298574, + "learning_rate": 9.03859142653873e-06, + "loss": 0.8731, + "step": 6084 + }, + { + "epoch": 0.5448542168000448, + "grad_norm": 1.00217629126635, + "learning_rate": 9.035704613270017e-06, + "loss": 0.8484, + "step": 6085 + }, + { + "epoch": 0.5449437573451228, + "grad_norm": 0.9221122411670781, + "learning_rate": 9.032817881114693e-06, + "loss": 0.866, + "step": 6086 + }, + { + "epoch": 0.5450332978902009, + "grad_norm": 0.880489882005139, + "learning_rate": 9.029931230315576e-06, + "loss": 0.8278, + "step": 6087 + }, + { + "epoch": 0.545122838435279, + "grad_norm": 1.1401667376112792, + "learning_rate": 9.027044661115486e-06, + "loss": 0.8377, + "step": 6088 + }, + { + "epoch": 0.545212378980357, + "grad_norm": 0.9991133873198594, + "learning_rate": 9.024158173757224e-06, + "loss": 0.788, + "step": 6089 + }, + { + "epoch": 0.5453019195254352, + "grad_norm": 0.9579178704542471, + "learning_rate": 9.021271768483598e-06, + "loss": 0.8386, + "step": 6090 + }, + { + "epoch": 0.5453914600705132, + "grad_norm": 0.9786053192302293, + "learning_rate": 9.018385445537398e-06, + "loss": 0.7855, + "step": 6091 + }, + { + "epoch": 0.5454810006155912, + "grad_norm": 0.9813045172794426, + "learning_rate": 9.01549920516142e-06, + "loss": 0.8037, + "step": 6092 + }, + { + "epoch": 0.5455705411606693, + "grad_norm": 0.9362038553652263, + "learning_rate": 9.012613047598438e-06, + "loss": 0.8303, + "step": 6093 + }, + { + "epoch": 0.5456600817057474, + "grad_norm": 0.9616343493600813, + "learning_rate": 9.009726973091234e-06, + "loss": 0.835, + "step": 6094 + }, + { + "epoch": 0.5457496222508255, + "grad_norm": 0.8928570254426087, + "learning_rate": 9.006840981882565e-06, + "loss": 0.8472, + "step": 6095 + }, + { + "epoch": 0.5458391627959035, + "grad_norm": 0.9172940273859472, + "learning_rate": 9.003955074215198e-06, + "loss": 0.8819, + "step": 6096 + }, + { + "epoch": 0.5459287033409815, + "grad_norm": 0.891450200365495, + "learning_rate": 9.001069250331881e-06, + "loss": 0.8112, + "step": 6097 + }, + { + "epoch": 0.5460182438860597, + "grad_norm": 0.8892763216395327, + "learning_rate": 8.998183510475366e-06, + "loss": 0.8281, + "step": 6098 + }, + { + "epoch": 0.5461077844311377, + "grad_norm": 1.134286937055993, + "learning_rate": 8.995297854888394e-06, + "loss": 0.8206, + "step": 6099 + }, + { + "epoch": 0.5461973249762158, + "grad_norm": 0.9333884074444031, + "learning_rate": 8.992412283813688e-06, + "loss": 0.778, + "step": 6100 + }, + { + "epoch": 0.5462868655212939, + "grad_norm": 0.9858286755603527, + "learning_rate": 8.989526797493977e-06, + "loss": 0.8396, + "step": 6101 + }, + { + "epoch": 0.546376406066372, + "grad_norm": 1.035325237236071, + "learning_rate": 8.986641396171978e-06, + "loss": 0.8274, + "step": 6102 + }, + { + "epoch": 0.54646594661145, + "grad_norm": 0.9934779067972035, + "learning_rate": 8.983756080090402e-06, + "loss": 0.8527, + "step": 6103 + }, + { + "epoch": 0.546555487156528, + "grad_norm": 0.9183399284842207, + "learning_rate": 8.980870849491955e-06, + "loss": 0.8117, + "step": 6104 + }, + { + "epoch": 0.5466450277016062, + "grad_norm": 0.9335294561635452, + "learning_rate": 8.977985704619334e-06, + "loss": 0.8342, + "step": 6105 + }, + { + "epoch": 0.5467345682466842, + "grad_norm": 1.2339940146158423, + "learning_rate": 8.975100645715221e-06, + "loss": 0.8056, + "step": 6106 + }, + { + "epoch": 0.5468241087917622, + "grad_norm": 0.9915305601950564, + "learning_rate": 8.972215673022303e-06, + "loss": 0.7813, + "step": 6107 + }, + { + "epoch": 0.5469136493368404, + "grad_norm": 0.9385719164843029, + "learning_rate": 8.969330786783253e-06, + "loss": 0.7597, + "step": 6108 + }, + { + "epoch": 0.5470031898819184, + "grad_norm": 0.9087642302529276, + "learning_rate": 8.966445987240738e-06, + "loss": 0.821, + "step": 6109 + }, + { + "epoch": 0.5470927304269965, + "grad_norm": 0.9145735034292245, + "learning_rate": 8.963561274637423e-06, + "loss": 0.8396, + "step": 6110 + }, + { + "epoch": 0.5471822709720745, + "grad_norm": 0.9826819093462108, + "learning_rate": 8.960676649215951e-06, + "loss": 0.824, + "step": 6111 + }, + { + "epoch": 0.5472718115171527, + "grad_norm": 1.1327670985795641, + "learning_rate": 8.95779211121897e-06, + "loss": 0.813, + "step": 6112 + }, + { + "epoch": 0.5473613520622307, + "grad_norm": 0.890713563932156, + "learning_rate": 8.954907660889126e-06, + "loss": 0.7882, + "step": 6113 + }, + { + "epoch": 0.5474508926073087, + "grad_norm": 1.0619352154870587, + "learning_rate": 8.952023298469042e-06, + "loss": 0.8295, + "step": 6114 + }, + { + "epoch": 0.5475404331523868, + "grad_norm": 0.9567964901525606, + "learning_rate": 8.949139024201343e-06, + "loss": 0.8062, + "step": 6115 + }, + { + "epoch": 0.5476299736974649, + "grad_norm": 0.927551938283949, + "learning_rate": 8.946254838328647e-06, + "loss": 0.8098, + "step": 6116 + }, + { + "epoch": 0.547719514242543, + "grad_norm": 1.006534327834802, + "learning_rate": 8.943370741093558e-06, + "loss": 0.7956, + "step": 6117 + }, + { + "epoch": 0.547809054787621, + "grad_norm": 0.9596685327015084, + "learning_rate": 8.940486732738677e-06, + "loss": 0.8554, + "step": 6118 + }, + { + "epoch": 0.5478985953326991, + "grad_norm": 1.1857216365890464, + "learning_rate": 8.937602813506602e-06, + "loss": 0.8046, + "step": 6119 + }, + { + "epoch": 0.5479881358777772, + "grad_norm": 1.0159856478786566, + "learning_rate": 8.934718983639916e-06, + "loss": 0.8431, + "step": 6120 + }, + { + "epoch": 0.5480776764228552, + "grad_norm": 0.8572100177979363, + "learning_rate": 8.9318352433812e-06, + "loss": 0.8124, + "step": 6121 + }, + { + "epoch": 0.5481672169679332, + "grad_norm": 0.9531498731708228, + "learning_rate": 8.928951592973019e-06, + "loss": 0.8534, + "step": 6122 + }, + { + "epoch": 0.5482567575130114, + "grad_norm": 0.9002591951125026, + "learning_rate": 8.926068032657941e-06, + "loss": 0.8072, + "step": 6123 + }, + { + "epoch": 0.5483462980580894, + "grad_norm": 1.0402074850858871, + "learning_rate": 8.923184562678518e-06, + "loss": 0.8228, + "step": 6124 + }, + { + "epoch": 0.5484358386031675, + "grad_norm": 0.8654098910589669, + "learning_rate": 8.920301183277302e-06, + "loss": 0.7496, + "step": 6125 + }, + { + "epoch": 0.5485253791482456, + "grad_norm": 0.920346943428762, + "learning_rate": 8.917417894696836e-06, + "loss": 0.7711, + "step": 6126 + }, + { + "epoch": 0.5486149196933237, + "grad_norm": 0.9643760138678554, + "learning_rate": 8.914534697179645e-06, + "loss": 0.7897, + "step": 6127 + }, + { + "epoch": 0.5487044602384017, + "grad_norm": 0.9221495857476754, + "learning_rate": 8.911651590968259e-06, + "loss": 0.8137, + "step": 6128 + }, + { + "epoch": 0.5487940007834797, + "grad_norm": 1.4247809736387251, + "learning_rate": 8.908768576305194e-06, + "loss": 0.8431, + "step": 6129 + }, + { + "epoch": 0.5488835413285579, + "grad_norm": 0.9022339320391835, + "learning_rate": 8.905885653432958e-06, + "loss": 0.7817, + "step": 6130 + }, + { + "epoch": 0.5489730818736359, + "grad_norm": 0.9327807027686045, + "learning_rate": 8.90300282259406e-06, + "loss": 0.7895, + "step": 6131 + }, + { + "epoch": 0.549062622418714, + "grad_norm": 1.0316982796621155, + "learning_rate": 8.90012008403099e-06, + "loss": 0.8055, + "step": 6132 + }, + { + "epoch": 0.549152162963792, + "grad_norm": 0.956859619071835, + "learning_rate": 8.897237437986232e-06, + "loss": 0.8247, + "step": 6133 + }, + { + "epoch": 0.5492417035088701, + "grad_norm": 1.0195351839694258, + "learning_rate": 8.894354884702266e-06, + "loss": 0.8206, + "step": 6134 + }, + { + "epoch": 0.5493312440539482, + "grad_norm": 1.0926993323248415, + "learning_rate": 8.891472424421567e-06, + "loss": 0.833, + "step": 6135 + }, + { + "epoch": 0.5494207845990262, + "grad_norm": 0.9933041596725648, + "learning_rate": 8.888590057386593e-06, + "loss": 0.8707, + "step": 6136 + }, + { + "epoch": 0.5495103251441044, + "grad_norm": 1.0408213093660634, + "learning_rate": 8.885707783839805e-06, + "loss": 0.8288, + "step": 6137 + }, + { + "epoch": 0.5495998656891824, + "grad_norm": 0.9655884580923807, + "learning_rate": 8.882825604023644e-06, + "loss": 0.8717, + "step": 6138 + }, + { + "epoch": 0.5496894062342604, + "grad_norm": 0.9274310023582122, + "learning_rate": 8.879943518180551e-06, + "loss": 0.8129, + "step": 6139 + }, + { + "epoch": 0.5497789467793385, + "grad_norm": 0.9744971834880503, + "learning_rate": 8.877061526552961e-06, + "loss": 0.8403, + "step": 6140 + }, + { + "epoch": 0.5498684873244166, + "grad_norm": 0.9567821253355189, + "learning_rate": 8.874179629383298e-06, + "loss": 0.8345, + "step": 6141 + }, + { + "epoch": 0.5499580278694947, + "grad_norm": 0.8831138620077232, + "learning_rate": 8.871297826913974e-06, + "loss": 0.8022, + "step": 6142 + }, + { + "epoch": 0.5500475684145727, + "grad_norm": 0.9677391175527981, + "learning_rate": 8.8684161193874e-06, + "loss": 0.8022, + "step": 6143 + }, + { + "epoch": 0.5501371089596508, + "grad_norm": 0.8662411398480176, + "learning_rate": 8.865534507045974e-06, + "loss": 0.809, + "step": 6144 + }, + { + "epoch": 0.5502266495047289, + "grad_norm": 0.9449368851220822, + "learning_rate": 8.862652990132085e-06, + "loss": 0.8265, + "step": 6145 + }, + { + "epoch": 0.5503161900498069, + "grad_norm": 0.8688978157837339, + "learning_rate": 8.859771568888126e-06, + "loss": 0.8304, + "step": 6146 + }, + { + "epoch": 0.550405730594885, + "grad_norm": 0.924076373047901, + "learning_rate": 8.856890243556463e-06, + "loss": 0.7413, + "step": 6147 + }, + { + "epoch": 0.5504952711399631, + "grad_norm": 1.170850785514499, + "learning_rate": 8.854009014379472e-06, + "loss": 0.8439, + "step": 6148 + }, + { + "epoch": 0.5505848116850411, + "grad_norm": 0.9227805288993206, + "learning_rate": 8.851127881599504e-06, + "loss": 0.8131, + "step": 6149 + }, + { + "epoch": 0.5506743522301192, + "grad_norm": 0.9903403612308835, + "learning_rate": 8.848246845458915e-06, + "loss": 0.8405, + "step": 6150 + }, + { + "epoch": 0.5507638927751972, + "grad_norm": 1.0264125070402255, + "learning_rate": 8.845365906200048e-06, + "loss": 0.8616, + "step": 6151 + }, + { + "epoch": 0.5508534333202754, + "grad_norm": 1.0278846394831378, + "learning_rate": 8.842485064065238e-06, + "loss": 0.838, + "step": 6152 + }, + { + "epoch": 0.5509429738653534, + "grad_norm": 0.9603266249808516, + "learning_rate": 8.839604319296815e-06, + "loss": 0.8271, + "step": 6153 + }, + { + "epoch": 0.5510325144104314, + "grad_norm": 0.8748500258920642, + "learning_rate": 8.836723672137096e-06, + "loss": 0.8221, + "step": 6154 + }, + { + "epoch": 0.5511220549555096, + "grad_norm": 0.9306339854890584, + "learning_rate": 8.833843122828388e-06, + "loss": 0.7819, + "step": 6155 + }, + { + "epoch": 0.5512115955005876, + "grad_norm": 0.9823302735405507, + "learning_rate": 8.830962671612998e-06, + "loss": 0.851, + "step": 6156 + }, + { + "epoch": 0.5513011360456657, + "grad_norm": 0.8791709851271489, + "learning_rate": 8.828082318733216e-06, + "loss": 0.8188, + "step": 6157 + }, + { + "epoch": 0.5513906765907437, + "grad_norm": 0.9929130025992706, + "learning_rate": 8.825202064431332e-06, + "loss": 0.8408, + "step": 6158 + }, + { + "epoch": 0.5514802171358218, + "grad_norm": 0.9532564623484906, + "learning_rate": 8.822321908949627e-06, + "loss": 0.8232, + "step": 6159 + }, + { + "epoch": 0.5515697576808999, + "grad_norm": 0.959490306887631, + "learning_rate": 8.819441852530358e-06, + "loss": 0.859, + "step": 6160 + }, + { + "epoch": 0.5516592982259779, + "grad_norm": 0.9786472754942536, + "learning_rate": 8.816561895415796e-06, + "loss": 0.8591, + "step": 6161 + }, + { + "epoch": 0.5517488387710561, + "grad_norm": 0.9461115139049723, + "learning_rate": 8.81368203784819e-06, + "loss": 0.7565, + "step": 6162 + }, + { + "epoch": 0.5518383793161341, + "grad_norm": 0.978793636802868, + "learning_rate": 8.810802280069786e-06, + "loss": 0.829, + "step": 6163 + }, + { + "epoch": 0.5519279198612121, + "grad_norm": 0.9396127601080151, + "learning_rate": 8.807922622322817e-06, + "loss": 0.8325, + "step": 6164 + }, + { + "epoch": 0.5520174604062902, + "grad_norm": 0.9049368968935767, + "learning_rate": 8.805043064849519e-06, + "loss": 0.7863, + "step": 6165 + }, + { + "epoch": 0.5521070009513683, + "grad_norm": 0.9931101610609135, + "learning_rate": 8.802163607892098e-06, + "loss": 0.8186, + "step": 6166 + }, + { + "epoch": 0.5521965414964464, + "grad_norm": 0.9630011474588609, + "learning_rate": 8.79928425169277e-06, + "loss": 0.8679, + "step": 6167 + }, + { + "epoch": 0.5522860820415244, + "grad_norm": 1.1174275411614434, + "learning_rate": 8.79640499649374e-06, + "loss": 0.8462, + "step": 6168 + }, + { + "epoch": 0.5523756225866024, + "grad_norm": 1.0085656191663102, + "learning_rate": 8.793525842537201e-06, + "loss": 0.8418, + "step": 6169 + }, + { + "epoch": 0.5524651631316806, + "grad_norm": 0.8877752143694859, + "learning_rate": 8.790646790065337e-06, + "loss": 0.85, + "step": 6170 + }, + { + "epoch": 0.5525547036767586, + "grad_norm": 0.9303797202738328, + "learning_rate": 8.787767839320323e-06, + "loss": 0.7623, + "step": 6171 + }, + { + "epoch": 0.5526442442218367, + "grad_norm": 1.1451139285953147, + "learning_rate": 8.784888990544327e-06, + "loss": 0.8153, + "step": 6172 + }, + { + "epoch": 0.5527337847669148, + "grad_norm": 1.2084127994541511, + "learning_rate": 8.78201024397951e-06, + "loss": 0.7856, + "step": 6173 + }, + { + "epoch": 0.5528233253119929, + "grad_norm": 0.9025103880629155, + "learning_rate": 8.779131599868022e-06, + "loss": 0.8725, + "step": 6174 + }, + { + "epoch": 0.5529128658570709, + "grad_norm": 0.9286201240276614, + "learning_rate": 8.776253058452006e-06, + "loss": 0.8151, + "step": 6175 + }, + { + "epoch": 0.5530024064021489, + "grad_norm": 0.926513286270532, + "learning_rate": 8.773374619973598e-06, + "loss": 0.8742, + "step": 6176 + }, + { + "epoch": 0.5530919469472271, + "grad_norm": 0.8748821873801832, + "learning_rate": 8.770496284674915e-06, + "loss": 0.8237, + "step": 6177 + }, + { + "epoch": 0.5531814874923051, + "grad_norm": 1.1027547928068657, + "learning_rate": 8.767618052798077e-06, + "loss": 0.8009, + "step": 6178 + }, + { + "epoch": 0.5532710280373832, + "grad_norm": 1.076919625435243, + "learning_rate": 8.764739924585194e-06, + "loss": 0.7971, + "step": 6179 + }, + { + "epoch": 0.5533605685824613, + "grad_norm": 1.1749975923790266, + "learning_rate": 8.761861900278365e-06, + "loss": 0.8377, + "step": 6180 + }, + { + "epoch": 0.5534501091275393, + "grad_norm": 1.010278443904513, + "learning_rate": 8.75898398011968e-06, + "loss": 0.842, + "step": 6181 + }, + { + "epoch": 0.5535396496726174, + "grad_norm": 0.8683879065811744, + "learning_rate": 8.756106164351214e-06, + "loss": 0.825, + "step": 6182 + }, + { + "epoch": 0.5536291902176954, + "grad_norm": 0.956779918576646, + "learning_rate": 8.753228453215047e-06, + "loss": 0.8426, + "step": 6183 + }, + { + "epoch": 0.5537187307627736, + "grad_norm": 0.9092970863369139, + "learning_rate": 8.750350846953235e-06, + "loss": 0.8432, + "step": 6184 + }, + { + "epoch": 0.5538082713078516, + "grad_norm": 0.9309671617713405, + "learning_rate": 8.747473345807841e-06, + "loss": 0.8066, + "step": 6185 + }, + { + "epoch": 0.5538978118529296, + "grad_norm": 0.9785680066165925, + "learning_rate": 8.744595950020907e-06, + "loss": 0.8724, + "step": 6186 + }, + { + "epoch": 0.5539873523980077, + "grad_norm": 0.8164713560957905, + "learning_rate": 8.741718659834474e-06, + "loss": 0.8189, + "step": 6187 + }, + { + "epoch": 0.5540768929430858, + "grad_norm": 1.0056619059372478, + "learning_rate": 8.738841475490563e-06, + "loss": 0.8976, + "step": 6188 + }, + { + "epoch": 0.5541664334881639, + "grad_norm": 0.882164065857934, + "learning_rate": 8.735964397231199e-06, + "loss": 0.7703, + "step": 6189 + }, + { + "epoch": 0.5542559740332419, + "grad_norm": 1.1138187036940759, + "learning_rate": 8.73308742529839e-06, + "loss": 0.8019, + "step": 6190 + }, + { + "epoch": 0.55434551457832, + "grad_norm": 0.9142994305137074, + "learning_rate": 8.730210559934137e-06, + "loss": 0.8373, + "step": 6191 + }, + { + "epoch": 0.5544350551233981, + "grad_norm": 0.8813696840477887, + "learning_rate": 8.72733380138044e-06, + "loss": 0.8239, + "step": 6192 + }, + { + "epoch": 0.5545245956684761, + "grad_norm": 0.9571352757648829, + "learning_rate": 8.724457149879268e-06, + "loss": 0.8438, + "step": 6193 + }, + { + "epoch": 0.5546141362135542, + "grad_norm": 0.972279501527995, + "learning_rate": 8.721580605672608e-06, + "loss": 0.7665, + "step": 6194 + }, + { + "epoch": 0.5547036767586323, + "grad_norm": 0.8714358931234844, + "learning_rate": 8.71870416900242e-06, + "loss": 0.8473, + "step": 6195 + }, + { + "epoch": 0.5547932173037103, + "grad_norm": 0.8164731871718228, + "learning_rate": 8.715827840110665e-06, + "loss": 0.837, + "step": 6196 + }, + { + "epoch": 0.5548827578487884, + "grad_norm": 0.9220563929238569, + "learning_rate": 8.712951619239288e-06, + "loss": 0.8068, + "step": 6197 + }, + { + "epoch": 0.5549722983938665, + "grad_norm": 1.0476642672712828, + "learning_rate": 8.710075506630223e-06, + "loss": 0.8184, + "step": 6198 + }, + { + "epoch": 0.5550618389389446, + "grad_norm": 0.9375961096878558, + "learning_rate": 8.7071995025254e-06, + "loss": 0.8266, + "step": 6199 + }, + { + "epoch": 0.5551513794840226, + "grad_norm": 0.9012721110369738, + "learning_rate": 8.704323607166747e-06, + "loss": 0.807, + "step": 6200 + }, + { + "epoch": 0.5552409200291006, + "grad_norm": 0.9201837888685435, + "learning_rate": 8.701447820796169e-06, + "loss": 0.862, + "step": 6201 + }, + { + "epoch": 0.5553304605741788, + "grad_norm": 1.0076213703126056, + "learning_rate": 8.698572143655568e-06, + "loss": 0.8602, + "step": 6202 + }, + { + "epoch": 0.5554200011192568, + "grad_norm": 0.9482457601212124, + "learning_rate": 8.69569657598684e-06, + "loss": 0.8085, + "step": 6203 + }, + { + "epoch": 0.5555095416643349, + "grad_norm": 0.9478277847660875, + "learning_rate": 8.692821118031864e-06, + "loss": 0.8223, + "step": 6204 + }, + { + "epoch": 0.5555990822094129, + "grad_norm": 0.9002180666735875, + "learning_rate": 8.689945770032514e-06, + "loss": 0.8501, + "step": 6205 + }, + { + "epoch": 0.555688622754491, + "grad_norm": 0.9412683268785947, + "learning_rate": 8.687070532230657e-06, + "loss": 0.7888, + "step": 6206 + }, + { + "epoch": 0.5557781632995691, + "grad_norm": 0.9272483580666643, + "learning_rate": 8.684195404868149e-06, + "loss": 0.8159, + "step": 6207 + }, + { + "epoch": 0.5558677038446471, + "grad_norm": 0.9922701102619413, + "learning_rate": 8.68132038818684e-06, + "loss": 0.8347, + "step": 6208 + }, + { + "epoch": 0.5559572443897253, + "grad_norm": 0.8911024837830945, + "learning_rate": 8.67844548242856e-06, + "loss": 0.8031, + "step": 6209 + }, + { + "epoch": 0.5560467849348033, + "grad_norm": 0.8782596279670537, + "learning_rate": 8.675570687835138e-06, + "loss": 0.8612, + "step": 6210 + }, + { + "epoch": 0.5561363254798813, + "grad_norm": 1.0878373284880813, + "learning_rate": 8.672696004648391e-06, + "loss": 0.7436, + "step": 6211 + }, + { + "epoch": 0.5562258660249594, + "grad_norm": 1.0790367172382063, + "learning_rate": 8.669821433110133e-06, + "loss": 0.819, + "step": 6212 + }, + { + "epoch": 0.5563154065700375, + "grad_norm": 0.9120162340914998, + "learning_rate": 8.666946973462163e-06, + "loss": 0.8582, + "step": 6213 + }, + { + "epoch": 0.5564049471151156, + "grad_norm": 0.9198809554701761, + "learning_rate": 8.664072625946271e-06, + "loss": 0.8324, + "step": 6214 + }, + { + "epoch": 0.5564944876601936, + "grad_norm": 0.9342727041133677, + "learning_rate": 8.661198390804235e-06, + "loss": 0.8583, + "step": 6215 + }, + { + "epoch": 0.5565840282052718, + "grad_norm": 0.9073260590909366, + "learning_rate": 8.658324268277827e-06, + "loss": 0.8095, + "step": 6216 + }, + { + "epoch": 0.5566735687503498, + "grad_norm": 1.0042041463652132, + "learning_rate": 8.65545025860881e-06, + "loss": 0.7842, + "step": 6217 + }, + { + "epoch": 0.5567631092954278, + "grad_norm": 0.915306347297924, + "learning_rate": 8.652576362038933e-06, + "loss": 0.7842, + "step": 6218 + }, + { + "epoch": 0.5568526498405059, + "grad_norm": 0.8691734379417024, + "learning_rate": 8.649702578809948e-06, + "loss": 0.8226, + "step": 6219 + }, + { + "epoch": 0.556942190385584, + "grad_norm": 0.9779780690046866, + "learning_rate": 8.646828909163574e-06, + "loss": 0.7953, + "step": 6220 + }, + { + "epoch": 0.557031730930662, + "grad_norm": 1.0478814875529516, + "learning_rate": 8.643955353341546e-06, + "loss": 0.8635, + "step": 6221 + }, + { + "epoch": 0.5571212714757401, + "grad_norm": 0.8883695514944274, + "learning_rate": 8.641081911585576e-06, + "loss": 0.8042, + "step": 6222 + }, + { + "epoch": 0.5572108120208181, + "grad_norm": 0.8839468462801209, + "learning_rate": 8.638208584137366e-06, + "loss": 0.7905, + "step": 6223 + }, + { + "epoch": 0.5573003525658963, + "grad_norm": 1.0447527429385743, + "learning_rate": 8.63533537123861e-06, + "loss": 0.8512, + "step": 6224 + }, + { + "epoch": 0.5573898931109743, + "grad_norm": 0.9852439677192617, + "learning_rate": 8.632462273131002e-06, + "loss": 0.8749, + "step": 6225 + }, + { + "epoch": 0.5574794336560523, + "grad_norm": 0.9084443950532312, + "learning_rate": 8.629589290056207e-06, + "loss": 0.795, + "step": 6226 + }, + { + "epoch": 0.5575689742011305, + "grad_norm": 0.9132888277667458, + "learning_rate": 8.626716422255894e-06, + "loss": 0.798, + "step": 6227 + }, + { + "epoch": 0.5576585147462085, + "grad_norm": 0.9670570095211392, + "learning_rate": 8.62384366997172e-06, + "loss": 0.8315, + "step": 6228 + }, + { + "epoch": 0.5577480552912866, + "grad_norm": 0.9864812394570586, + "learning_rate": 8.620971033445335e-06, + "loss": 0.7924, + "step": 6229 + }, + { + "epoch": 0.5578375958363646, + "grad_norm": 0.980799412429873, + "learning_rate": 8.618098512918373e-06, + "loss": 0.8291, + "step": 6230 + }, + { + "epoch": 0.5579271363814428, + "grad_norm": 0.884826647902106, + "learning_rate": 8.615226108632461e-06, + "loss": 0.8397, + "step": 6231 + }, + { + "epoch": 0.5580166769265208, + "grad_norm": 1.1153769429476674, + "learning_rate": 8.612353820829211e-06, + "loss": 0.838, + "step": 6232 + }, + { + "epoch": 0.5581062174715988, + "grad_norm": 1.0957122488552455, + "learning_rate": 8.60948164975024e-06, + "loss": 0.8462, + "step": 6233 + }, + { + "epoch": 0.558195758016677, + "grad_norm": 0.9341638784553586, + "learning_rate": 8.60660959563714e-06, + "loss": 0.818, + "step": 6234 + }, + { + "epoch": 0.558285298561755, + "grad_norm": 1.0499033901854964, + "learning_rate": 8.6037376587315e-06, + "loss": 0.765, + "step": 6235 + }, + { + "epoch": 0.558374839106833, + "grad_norm": 0.947506906884927, + "learning_rate": 8.600865839274902e-06, + "loss": 0.7735, + "step": 6236 + }, + { + "epoch": 0.5584643796519111, + "grad_norm": 0.9733665251533825, + "learning_rate": 8.597994137508907e-06, + "loss": 0.8701, + "step": 6237 + }, + { + "epoch": 0.5585539201969892, + "grad_norm": 1.0607018295729944, + "learning_rate": 8.595122553675075e-06, + "loss": 0.8507, + "step": 6238 + }, + { + "epoch": 0.5586434607420673, + "grad_norm": 1.0020744151736605, + "learning_rate": 8.592251088014956e-06, + "loss": 0.8464, + "step": 6239 + }, + { + "epoch": 0.5587330012871453, + "grad_norm": 1.1974872131823473, + "learning_rate": 8.589379740770091e-06, + "loss": 0.8381, + "step": 6240 + }, + { + "epoch": 0.5588225418322234, + "grad_norm": 0.989551388006751, + "learning_rate": 8.586508512182006e-06, + "loss": 0.8429, + "step": 6241 + }, + { + "epoch": 0.5589120823773015, + "grad_norm": 1.011662099827941, + "learning_rate": 8.583637402492216e-06, + "loss": 0.8557, + "step": 6242 + }, + { + "epoch": 0.5590016229223795, + "grad_norm": 0.9977999435781696, + "learning_rate": 8.580766411942232e-06, + "loss": 0.8312, + "step": 6243 + }, + { + "epoch": 0.5590911634674576, + "grad_norm": 1.048007158168493, + "learning_rate": 8.577895540773553e-06, + "loss": 0.8197, + "step": 6244 + }, + { + "epoch": 0.5591807040125357, + "grad_norm": 1.1161325246222016, + "learning_rate": 8.575024789227666e-06, + "loss": 0.854, + "step": 6245 + }, + { + "epoch": 0.5592702445576138, + "grad_norm": 0.8877063141808497, + "learning_rate": 8.572154157546051e-06, + "loss": 0.7914, + "step": 6246 + }, + { + "epoch": 0.5593597851026918, + "grad_norm": 0.9166527406783664, + "learning_rate": 8.569283645970178e-06, + "loss": 0.8468, + "step": 6247 + }, + { + "epoch": 0.5594493256477698, + "grad_norm": 0.920340771529597, + "learning_rate": 8.5664132547415e-06, + "loss": 0.8366, + "step": 6248 + }, + { + "epoch": 0.559538866192848, + "grad_norm": 0.9708546225007653, + "learning_rate": 8.563542984101467e-06, + "loss": 0.8107, + "step": 6249 + }, + { + "epoch": 0.559628406737926, + "grad_norm": 1.325946252370619, + "learning_rate": 8.560672834291518e-06, + "loss": 0.853, + "step": 6250 + }, + { + "epoch": 0.5597179472830041, + "grad_norm": 0.9623276638039914, + "learning_rate": 8.557802805553076e-06, + "loss": 0.7945, + "step": 6251 + }, + { + "epoch": 0.5598074878280822, + "grad_norm": 0.8937795643793636, + "learning_rate": 8.554932898127571e-06, + "loss": 0.8265, + "step": 6252 + }, + { + "epoch": 0.5598970283731602, + "grad_norm": 0.9130919495370106, + "learning_rate": 8.552063112256395e-06, + "loss": 0.8442, + "step": 6253 + }, + { + "epoch": 0.5599865689182383, + "grad_norm": 0.995423876481945, + "learning_rate": 8.549193448180952e-06, + "loss": 0.8191, + "step": 6254 + }, + { + "epoch": 0.5600761094633163, + "grad_norm": 0.8570026182790849, + "learning_rate": 8.546323906142631e-06, + "loss": 0.8437, + "step": 6255 + }, + { + "epoch": 0.5601656500083945, + "grad_norm": 0.9476637818961786, + "learning_rate": 8.543454486382803e-06, + "loss": 0.7945, + "step": 6256 + }, + { + "epoch": 0.5602551905534725, + "grad_norm": 0.9342135221862148, + "learning_rate": 8.540585189142836e-06, + "loss": 0.8631, + "step": 6257 + }, + { + "epoch": 0.5603447310985505, + "grad_norm": 1.2577540954382154, + "learning_rate": 8.537716014664095e-06, + "loss": 0.8573, + "step": 6258 + }, + { + "epoch": 0.5604342716436286, + "grad_norm": 0.8428549564493989, + "learning_rate": 8.53484696318791e-06, + "loss": 0.8216, + "step": 6259 + }, + { + "epoch": 0.5605238121887067, + "grad_norm": 1.086904038516366, + "learning_rate": 8.531978034955625e-06, + "loss": 0.8018, + "step": 6260 + }, + { + "epoch": 0.5606133527337848, + "grad_norm": 1.0124644505079914, + "learning_rate": 8.529109230208565e-06, + "loss": 0.8526, + "step": 6261 + }, + { + "epoch": 0.5607028932788628, + "grad_norm": 0.8748819294738786, + "learning_rate": 8.526240549188044e-06, + "loss": 0.8389, + "step": 6262 + }, + { + "epoch": 0.560792433823941, + "grad_norm": 0.9262398437097885, + "learning_rate": 8.523371992135367e-06, + "loss": 0.8036, + "step": 6263 + }, + { + "epoch": 0.560881974369019, + "grad_norm": 0.9650725213494799, + "learning_rate": 8.520503559291824e-06, + "loss": 0.8757, + "step": 6264 + }, + { + "epoch": 0.560971514914097, + "grad_norm": 0.9676504460598785, + "learning_rate": 8.517635250898698e-06, + "loss": 0.8239, + "step": 6265 + }, + { + "epoch": 0.5610610554591751, + "grad_norm": 1.0244553865905783, + "learning_rate": 8.514767067197267e-06, + "loss": 0.866, + "step": 6266 + }, + { + "epoch": 0.5611505960042532, + "grad_norm": 1.0292286637759693, + "learning_rate": 8.511899008428789e-06, + "loss": 0.9125, + "step": 6267 + }, + { + "epoch": 0.5612401365493312, + "grad_norm": 1.0202115555546305, + "learning_rate": 8.50903107483452e-06, + "loss": 0.7988, + "step": 6268 + }, + { + "epoch": 0.5613296770944093, + "grad_norm": 0.9343298931208839, + "learning_rate": 8.506163266655696e-06, + "loss": 0.8864, + "step": 6269 + }, + { + "epoch": 0.5614192176394874, + "grad_norm": 0.9522285698390794, + "learning_rate": 8.503295584133551e-06, + "loss": 0.7618, + "step": 6270 + }, + { + "epoch": 0.5615087581845655, + "grad_norm": 1.051380972133942, + "learning_rate": 8.500428027509303e-06, + "loss": 0.7719, + "step": 6271 + }, + { + "epoch": 0.5615982987296435, + "grad_norm": 0.9333289788582795, + "learning_rate": 8.497560597024161e-06, + "loss": 0.7471, + "step": 6272 + }, + { + "epoch": 0.5616878392747215, + "grad_norm": 0.9668336778699221, + "learning_rate": 8.494693292919329e-06, + "loss": 0.8639, + "step": 6273 + }, + { + "epoch": 0.5617773798197997, + "grad_norm": 1.054468513323391, + "learning_rate": 8.491826115435991e-06, + "loss": 0.8597, + "step": 6274 + }, + { + "epoch": 0.5618669203648777, + "grad_norm": 0.9438055834324189, + "learning_rate": 8.488959064815326e-06, + "loss": 0.8212, + "step": 6275 + }, + { + "epoch": 0.5619564609099558, + "grad_norm": 0.8877640981945504, + "learning_rate": 8.486092141298499e-06, + "loss": 0.7586, + "step": 6276 + }, + { + "epoch": 0.5620460014550338, + "grad_norm": 0.9028159078681367, + "learning_rate": 8.483225345126668e-06, + "loss": 0.8336, + "step": 6277 + }, + { + "epoch": 0.562135542000112, + "grad_norm": 0.9892478788835701, + "learning_rate": 8.480358676540976e-06, + "loss": 0.85, + "step": 6278 + }, + { + "epoch": 0.56222508254519, + "grad_norm": 0.8815015426588725, + "learning_rate": 8.477492135782567e-06, + "loss": 0.8169, + "step": 6279 + }, + { + "epoch": 0.562314623090268, + "grad_norm": 0.961130718681417, + "learning_rate": 8.47462572309255e-06, + "loss": 0.8402, + "step": 6280 + }, + { + "epoch": 0.5624041636353462, + "grad_norm": 0.8992772068149755, + "learning_rate": 8.471759438712052e-06, + "loss": 0.7792, + "step": 6281 + }, + { + "epoch": 0.5624937041804242, + "grad_norm": 1.1618372639309393, + "learning_rate": 8.468893282882167e-06, + "loss": 0.8317, + "step": 6282 + }, + { + "epoch": 0.5625832447255023, + "grad_norm": 1.1293455553953806, + "learning_rate": 8.466027255843991e-06, + "loss": 0.7772, + "step": 6283 + }, + { + "epoch": 0.5626727852705803, + "grad_norm": 0.919329280776228, + "learning_rate": 8.4631613578386e-06, + "loss": 0.7939, + "step": 6284 + }, + { + "epoch": 0.5627623258156584, + "grad_norm": 1.1266022537183649, + "learning_rate": 8.460295589107075e-06, + "loss": 0.7935, + "step": 6285 + }, + { + "epoch": 0.5628518663607365, + "grad_norm": 0.9923958928527661, + "learning_rate": 8.457429949890463e-06, + "loss": 0.8228, + "step": 6286 + }, + { + "epoch": 0.5629414069058145, + "grad_norm": 1.1803432317636555, + "learning_rate": 8.454564440429816e-06, + "loss": 0.9026, + "step": 6287 + }, + { + "epoch": 0.5630309474508927, + "grad_norm": 1.0214736351306875, + "learning_rate": 8.451699060966174e-06, + "loss": 0.8211, + "step": 6288 + }, + { + "epoch": 0.5631204879959707, + "grad_norm": 1.0469931734583096, + "learning_rate": 8.44883381174056e-06, + "loss": 0.826, + "step": 6289 + }, + { + "epoch": 0.5632100285410487, + "grad_norm": 0.9813633606361105, + "learning_rate": 8.445968692993993e-06, + "loss": 0.765, + "step": 6290 + }, + { + "epoch": 0.5632995690861268, + "grad_norm": 0.8924360160421672, + "learning_rate": 8.443103704967474e-06, + "loss": 0.8062, + "step": 6291 + }, + { + "epoch": 0.5633891096312049, + "grad_norm": 1.069047030585701, + "learning_rate": 8.440238847901996e-06, + "loss": 0.8474, + "step": 6292 + }, + { + "epoch": 0.563478650176283, + "grad_norm": 1.155684157588797, + "learning_rate": 8.437374122038546e-06, + "loss": 0.8194, + "step": 6293 + }, + { + "epoch": 0.563568190721361, + "grad_norm": 1.0725241323363837, + "learning_rate": 8.434509527618092e-06, + "loss": 0.8584, + "step": 6294 + }, + { + "epoch": 0.563657731266439, + "grad_norm": 1.2565606695097087, + "learning_rate": 8.431645064881594e-06, + "loss": 0.8313, + "step": 6295 + }, + { + "epoch": 0.5637472718115172, + "grad_norm": 1.0805780074786737, + "learning_rate": 8.428780734070006e-06, + "loss": 0.8334, + "step": 6296 + }, + { + "epoch": 0.5638368123565952, + "grad_norm": 0.8878792445544832, + "learning_rate": 8.42591653542426e-06, + "loss": 0.806, + "step": 6297 + }, + { + "epoch": 0.5639263529016733, + "grad_norm": 0.9256005444527914, + "learning_rate": 8.423052469185286e-06, + "loss": 0.8193, + "step": 6298 + }, + { + "epoch": 0.5640158934467514, + "grad_norm": 0.9034716500111684, + "learning_rate": 8.420188535593996e-06, + "loss": 0.8269, + "step": 6299 + }, + { + "epoch": 0.5641054339918294, + "grad_norm": 1.0594733404489611, + "learning_rate": 8.417324734891301e-06, + "loss": 0.8821, + "step": 6300 + }, + { + "epoch": 0.5641949745369075, + "grad_norm": 0.8624414916053894, + "learning_rate": 8.414461067318095e-06, + "loss": 0.8026, + "step": 6301 + }, + { + "epoch": 0.5642845150819855, + "grad_norm": 0.9839236386878734, + "learning_rate": 8.411597533115254e-06, + "loss": 0.8079, + "step": 6302 + }, + { + "epoch": 0.5643740556270637, + "grad_norm": 0.9478835720582433, + "learning_rate": 8.408734132523652e-06, + "loss": 0.766, + "step": 6303 + }, + { + "epoch": 0.5644635961721417, + "grad_norm": 0.9419887145719844, + "learning_rate": 8.405870865784151e-06, + "loss": 0.7744, + "step": 6304 + }, + { + "epoch": 0.5645531367172197, + "grad_norm": 1.0145689506221294, + "learning_rate": 8.403007733137594e-06, + "loss": 0.7575, + "step": 6305 + }, + { + "epoch": 0.5646426772622979, + "grad_norm": 1.1383161605710237, + "learning_rate": 8.400144734824826e-06, + "loss": 0.8169, + "step": 6306 + }, + { + "epoch": 0.5647322178073759, + "grad_norm": 0.9659362464312885, + "learning_rate": 8.39728187108667e-06, + "loss": 0.8482, + "step": 6307 + }, + { + "epoch": 0.564821758352454, + "grad_norm": 0.9642635440547264, + "learning_rate": 8.394419142163939e-06, + "loss": 0.8089, + "step": 6308 + }, + { + "epoch": 0.564911298897532, + "grad_norm": 0.879275208492966, + "learning_rate": 8.391556548297436e-06, + "loss": 0.8406, + "step": 6309 + }, + { + "epoch": 0.5650008394426101, + "grad_norm": 0.8536728031521994, + "learning_rate": 8.388694089727959e-06, + "loss": 0.7758, + "step": 6310 + }, + { + "epoch": 0.5650903799876882, + "grad_norm": 0.9331503864789821, + "learning_rate": 8.385831766696279e-06, + "loss": 0.8159, + "step": 6311 + }, + { + "epoch": 0.5651799205327662, + "grad_norm": 0.8629547036750387, + "learning_rate": 8.382969579443177e-06, + "loss": 0.8261, + "step": 6312 + }, + { + "epoch": 0.5652694610778443, + "grad_norm": 0.9001896629068947, + "learning_rate": 8.380107528209399e-06, + "loss": 0.8106, + "step": 6313 + }, + { + "epoch": 0.5653590016229224, + "grad_norm": 0.9906884456529951, + "learning_rate": 8.377245613235699e-06, + "loss": 0.7837, + "step": 6314 + }, + { + "epoch": 0.5654485421680004, + "grad_norm": 0.9728225599627576, + "learning_rate": 8.374383834762808e-06, + "loss": 0.8855, + "step": 6315 + }, + { + "epoch": 0.5655380827130785, + "grad_norm": 0.9609543119900488, + "learning_rate": 8.371522193031454e-06, + "loss": 0.8275, + "step": 6316 + }, + { + "epoch": 0.5656276232581566, + "grad_norm": 0.8921145513052312, + "learning_rate": 8.368660688282345e-06, + "loss": 0.8588, + "step": 6317 + }, + { + "epoch": 0.5657171638032347, + "grad_norm": 0.8935251161290556, + "learning_rate": 8.365799320756187e-06, + "loss": 0.8146, + "step": 6318 + }, + { + "epoch": 0.5658067043483127, + "grad_norm": 0.9750701636409439, + "learning_rate": 8.362938090693659e-06, + "loss": 0.8457, + "step": 6319 + }, + { + "epoch": 0.5658962448933907, + "grad_norm": 0.9602093286477318, + "learning_rate": 8.360076998335447e-06, + "loss": 0.8957, + "step": 6320 + }, + { + "epoch": 0.5659857854384689, + "grad_norm": 1.0545457341150943, + "learning_rate": 8.357216043922213e-06, + "loss": 0.8902, + "step": 6321 + }, + { + "epoch": 0.5660753259835469, + "grad_norm": 0.9668876559946807, + "learning_rate": 8.354355227694612e-06, + "loss": 0.8031, + "step": 6322 + }, + { + "epoch": 0.566164866528625, + "grad_norm": 1.0449311481568286, + "learning_rate": 8.35149454989329e-06, + "loss": 0.8825, + "step": 6323 + }, + { + "epoch": 0.5662544070737031, + "grad_norm": 1.065080049911013, + "learning_rate": 8.34863401075887e-06, + "loss": 0.8464, + "step": 6324 + }, + { + "epoch": 0.5663439476187812, + "grad_norm": 0.9333666840118511, + "learning_rate": 8.345773610531977e-06, + "loss": 0.8079, + "step": 6325 + }, + { + "epoch": 0.5664334881638592, + "grad_norm": 0.9358923170069114, + "learning_rate": 8.342913349453215e-06, + "loss": 0.8982, + "step": 6326 + }, + { + "epoch": 0.5665230287089372, + "grad_norm": 0.9468538845201266, + "learning_rate": 8.340053227763185e-06, + "loss": 0.8641, + "step": 6327 + }, + { + "epoch": 0.5666125692540154, + "grad_norm": 0.9664123754273294, + "learning_rate": 8.33719324570247e-06, + "loss": 0.8562, + "step": 6328 + }, + { + "epoch": 0.5667021097990934, + "grad_norm": 1.028823625710351, + "learning_rate": 8.334333403511639e-06, + "loss": 0.8183, + "step": 6329 + }, + { + "epoch": 0.5667916503441714, + "grad_norm": 0.8809140045975414, + "learning_rate": 8.331473701431252e-06, + "loss": 0.8283, + "step": 6330 + }, + { + "epoch": 0.5668811908892495, + "grad_norm": 0.9489945447787314, + "learning_rate": 8.328614139701862e-06, + "loss": 0.7886, + "step": 6331 + }, + { + "epoch": 0.5669707314343276, + "grad_norm": 0.8947527328509491, + "learning_rate": 8.325754718564e-06, + "loss": 0.781, + "step": 6332 + }, + { + "epoch": 0.5670602719794057, + "grad_norm": 0.9308975391859056, + "learning_rate": 8.322895438258199e-06, + "loss": 0.8244, + "step": 6333 + }, + { + "epoch": 0.5671498125244837, + "grad_norm": 0.8941890182477599, + "learning_rate": 8.32003629902497e-06, + "loss": 0.781, + "step": 6334 + }, + { + "epoch": 0.5672393530695619, + "grad_norm": 0.9445626037486022, + "learning_rate": 8.317177301104811e-06, + "loss": 0.8162, + "step": 6335 + }, + { + "epoch": 0.5673288936146399, + "grad_norm": 0.9364256485348648, + "learning_rate": 8.314318444738215e-06, + "loss": 0.8367, + "step": 6336 + }, + { + "epoch": 0.5674184341597179, + "grad_norm": 1.0186646115429732, + "learning_rate": 8.311459730165656e-06, + "loss": 0.8073, + "step": 6337 + }, + { + "epoch": 0.567507974704796, + "grad_norm": 0.9269379907016525, + "learning_rate": 8.308601157627602e-06, + "loss": 0.857, + "step": 6338 + }, + { + "epoch": 0.5675975152498741, + "grad_norm": 1.1458419880019848, + "learning_rate": 8.305742727364513e-06, + "loss": 0.7925, + "step": 6339 + }, + { + "epoch": 0.5676870557949522, + "grad_norm": 0.9873054946086383, + "learning_rate": 8.302884439616816e-06, + "loss": 0.8747, + "step": 6340 + }, + { + "epoch": 0.5677765963400302, + "grad_norm": 0.8765078432984779, + "learning_rate": 8.300026294624954e-06, + "loss": 0.8141, + "step": 6341 + }, + { + "epoch": 0.5678661368851083, + "grad_norm": 0.9078290125772962, + "learning_rate": 8.29716829262934e-06, + "loss": 0.8448, + "step": 6342 + }, + { + "epoch": 0.5679556774301864, + "grad_norm": 0.927880998843783, + "learning_rate": 8.29431043387038e-06, + "loss": 0.7881, + "step": 6343 + }, + { + "epoch": 0.5680452179752644, + "grad_norm": 1.1669227884019917, + "learning_rate": 8.291452718588463e-06, + "loss": 0.7835, + "step": 6344 + }, + { + "epoch": 0.5681347585203425, + "grad_norm": 0.9554323050690641, + "learning_rate": 8.288595147023986e-06, + "loss": 0.7974, + "step": 6345 + }, + { + "epoch": 0.5682242990654206, + "grad_norm": 0.966222410846061, + "learning_rate": 8.2857377194173e-06, + "loss": 0.8178, + "step": 6346 + }, + { + "epoch": 0.5683138396104986, + "grad_norm": 1.0177312919330403, + "learning_rate": 8.282880436008775e-06, + "loss": 0.8235, + "step": 6347 + }, + { + "epoch": 0.5684033801555767, + "grad_norm": 0.9381770554222061, + "learning_rate": 8.280023297038749e-06, + "loss": 0.8336, + "step": 6348 + }, + { + "epoch": 0.5684929207006547, + "grad_norm": 0.9366471872765141, + "learning_rate": 8.277166302747561e-06, + "loss": 0.791, + "step": 6349 + }, + { + "epoch": 0.5685824612457329, + "grad_norm": 0.9228847464402782, + "learning_rate": 8.274309453375531e-06, + "loss": 0.8157, + "step": 6350 + }, + { + "epoch": 0.5686720017908109, + "grad_norm": 0.9729525529110813, + "learning_rate": 8.271452749162963e-06, + "loss": 0.8396, + "step": 6351 + }, + { + "epoch": 0.5687615423358889, + "grad_norm": 1.0205362211932345, + "learning_rate": 8.268596190350158e-06, + "loss": 0.821, + "step": 6352 + }, + { + "epoch": 0.5688510828809671, + "grad_norm": 0.974124744068781, + "learning_rate": 8.265739777177396e-06, + "loss": 0.8805, + "step": 6353 + }, + { + "epoch": 0.5689406234260451, + "grad_norm": 0.9701716927333254, + "learning_rate": 8.262883509884956e-06, + "loss": 0.8155, + "step": 6354 + }, + { + "epoch": 0.5690301639711232, + "grad_norm": 0.9705558159976604, + "learning_rate": 8.260027388713094e-06, + "loss": 0.8059, + "step": 6355 + }, + { + "epoch": 0.5691197045162012, + "grad_norm": 0.9356401565289704, + "learning_rate": 8.257171413902059e-06, + "loss": 0.8524, + "step": 6356 + }, + { + "epoch": 0.5692092450612793, + "grad_norm": 0.9322176060700326, + "learning_rate": 8.254315585692084e-06, + "loss": 0.8478, + "step": 6357 + }, + { + "epoch": 0.5692987856063574, + "grad_norm": 0.9408689083239092, + "learning_rate": 8.251459904323393e-06, + "loss": 0.8268, + "step": 6358 + }, + { + "epoch": 0.5693883261514354, + "grad_norm": 0.8957832704443067, + "learning_rate": 8.248604370036196e-06, + "loss": 0.7986, + "step": 6359 + }, + { + "epoch": 0.5694778666965136, + "grad_norm": 0.9490471795327067, + "learning_rate": 8.245748983070693e-06, + "loss": 0.8214, + "step": 6360 + }, + { + "epoch": 0.5695674072415916, + "grad_norm": 0.9403271910691102, + "learning_rate": 8.242893743667072e-06, + "loss": 0.7984, + "step": 6361 + }, + { + "epoch": 0.5696569477866696, + "grad_norm": 0.902707532529254, + "learning_rate": 8.2400386520655e-06, + "loss": 0.8711, + "step": 6362 + }, + { + "epoch": 0.5697464883317477, + "grad_norm": 1.0091644067047132, + "learning_rate": 8.237183708506143e-06, + "loss": 0.8626, + "step": 6363 + }, + { + "epoch": 0.5698360288768258, + "grad_norm": 1.053468676280152, + "learning_rate": 8.234328913229146e-06, + "loss": 0.8611, + "step": 6364 + }, + { + "epoch": 0.5699255694219039, + "grad_norm": 1.1687070452933956, + "learning_rate": 8.231474266474645e-06, + "loss": 0.8012, + "step": 6365 + }, + { + "epoch": 0.5700151099669819, + "grad_norm": 0.8917133144247367, + "learning_rate": 8.228619768482769e-06, + "loss": 0.8001, + "step": 6366 + }, + { + "epoch": 0.5701046505120599, + "grad_norm": 1.0808158463700963, + "learning_rate": 8.225765419493627e-06, + "loss": 0.8764, + "step": 6367 + }, + { + "epoch": 0.5701941910571381, + "grad_norm": 0.96984628550912, + "learning_rate": 8.222911219747317e-06, + "loss": 0.8085, + "step": 6368 + }, + { + "epoch": 0.5702837316022161, + "grad_norm": 0.929311773688592, + "learning_rate": 8.22005716948392e-06, + "loss": 0.8144, + "step": 6369 + }, + { + "epoch": 0.5703732721472942, + "grad_norm": 0.8930937783614732, + "learning_rate": 8.217203268943516e-06, + "loss": 0.8003, + "step": 6370 + }, + { + "epoch": 0.5704628126923723, + "grad_norm": 0.9166396903722628, + "learning_rate": 8.21434951836616e-06, + "loss": 0.8428, + "step": 6371 + }, + { + "epoch": 0.5705523532374503, + "grad_norm": 0.959572916067849, + "learning_rate": 8.21149591799191e-06, + "loss": 0.863, + "step": 6372 + }, + { + "epoch": 0.5706418937825284, + "grad_norm": 0.9501301822664973, + "learning_rate": 8.208642468060792e-06, + "loss": 0.8455, + "step": 6373 + }, + { + "epoch": 0.5707314343276064, + "grad_norm": 0.9964438343989324, + "learning_rate": 8.20578916881283e-06, + "loss": 0.8216, + "step": 6374 + }, + { + "epoch": 0.5708209748726846, + "grad_norm": 0.9232752955271403, + "learning_rate": 8.202936020488037e-06, + "loss": 0.8515, + "step": 6375 + }, + { + "epoch": 0.5709105154177626, + "grad_norm": 0.9249316687707083, + "learning_rate": 8.200083023326411e-06, + "loss": 0.7889, + "step": 6376 + }, + { + "epoch": 0.5710000559628406, + "grad_norm": 0.9297897788584465, + "learning_rate": 8.197230177567934e-06, + "loss": 0.8087, + "step": 6377 + }, + { + "epoch": 0.5710895965079188, + "grad_norm": 0.9190141912176004, + "learning_rate": 8.194377483452585e-06, + "loss": 0.876, + "step": 6378 + }, + { + "epoch": 0.5711791370529968, + "grad_norm": 0.9488146510555675, + "learning_rate": 8.191524941220314e-06, + "loss": 0.7971, + "step": 6379 + }, + { + "epoch": 0.5712686775980749, + "grad_norm": 0.9492160511809153, + "learning_rate": 8.188672551111069e-06, + "loss": 0.8126, + "step": 6380 + }, + { + "epoch": 0.5713582181431529, + "grad_norm": 0.9828175792235969, + "learning_rate": 8.18582031336479e-06, + "loss": 0.8504, + "step": 6381 + }, + { + "epoch": 0.5714477586882311, + "grad_norm": 0.9493665086304246, + "learning_rate": 8.182968228221395e-06, + "loss": 0.8504, + "step": 6382 + }, + { + "epoch": 0.5715372992333091, + "grad_norm": 0.8942004582800138, + "learning_rate": 8.180116295920791e-06, + "loss": 0.8655, + "step": 6383 + }, + { + "epoch": 0.5716268397783871, + "grad_norm": 1.1245025791386143, + "learning_rate": 8.177264516702875e-06, + "loss": 0.8007, + "step": 6384 + }, + { + "epoch": 0.5717163803234652, + "grad_norm": 0.9423437924309437, + "learning_rate": 8.174412890807526e-06, + "loss": 0.804, + "step": 6385 + }, + { + "epoch": 0.5718059208685433, + "grad_norm": 1.1063026202946518, + "learning_rate": 8.171561418474611e-06, + "loss": 0.8352, + "step": 6386 + }, + { + "epoch": 0.5718954614136214, + "grad_norm": 0.9132765398672845, + "learning_rate": 8.168710099943997e-06, + "loss": 0.7676, + "step": 6387 + }, + { + "epoch": 0.5719850019586994, + "grad_norm": 1.0723400965339867, + "learning_rate": 8.16585893545552e-06, + "loss": 0.8585, + "step": 6388 + }, + { + "epoch": 0.5720745425037775, + "grad_norm": 1.0152464257254932, + "learning_rate": 8.163007925249015e-06, + "loss": 0.8333, + "step": 6389 + }, + { + "epoch": 0.5721640830488556, + "grad_norm": 0.9333039063551101, + "learning_rate": 8.160157069564296e-06, + "loss": 0.8457, + "step": 6390 + }, + { + "epoch": 0.5722536235939336, + "grad_norm": 1.0402027545695234, + "learning_rate": 8.157306368641167e-06, + "loss": 0.8335, + "step": 6391 + }, + { + "epoch": 0.5723431641390117, + "grad_norm": 0.9721077719071174, + "learning_rate": 8.15445582271942e-06, + "loss": 0.7654, + "step": 6392 + }, + { + "epoch": 0.5724327046840898, + "grad_norm": 0.8410843717096093, + "learning_rate": 8.151605432038838e-06, + "loss": 0.8538, + "step": 6393 + }, + { + "epoch": 0.5725222452291678, + "grad_norm": 0.9166532596877174, + "learning_rate": 8.148755196839186e-06, + "loss": 0.8486, + "step": 6394 + }, + { + "epoch": 0.5726117857742459, + "grad_norm": 0.9765252647307026, + "learning_rate": 8.145905117360211e-06, + "loss": 0.876, + "step": 6395 + }, + { + "epoch": 0.572701326319324, + "grad_norm": 0.9196803160494078, + "learning_rate": 8.143055193841656e-06, + "loss": 0.8126, + "step": 6396 + }, + { + "epoch": 0.5727908668644021, + "grad_norm": 0.9798055534653657, + "learning_rate": 8.140205426523247e-06, + "loss": 0.8051, + "step": 6397 + }, + { + "epoch": 0.5728804074094801, + "grad_norm": 0.8965282644553115, + "learning_rate": 8.137355815644694e-06, + "loss": 0.7987, + "step": 6398 + }, + { + "epoch": 0.5729699479545581, + "grad_norm": 1.1298951301128226, + "learning_rate": 8.134506361445706e-06, + "loss": 0.831, + "step": 6399 + }, + { + "epoch": 0.5730594884996363, + "grad_norm": 0.9125273256387578, + "learning_rate": 8.131657064165962e-06, + "loss": 0.7493, + "step": 6400 + }, + { + "epoch": 0.5731490290447143, + "grad_norm": 0.9229129690648799, + "learning_rate": 8.128807924045134e-06, + "loss": 0.833, + "step": 6401 + }, + { + "epoch": 0.5732385695897924, + "grad_norm": 0.972788484064051, + "learning_rate": 8.125958941322886e-06, + "loss": 0.908, + "step": 6402 + }, + { + "epoch": 0.5733281101348704, + "grad_norm": 0.9556157937056855, + "learning_rate": 8.123110116238868e-06, + "loss": 0.8068, + "step": 6403 + }, + { + "epoch": 0.5734176506799485, + "grad_norm": 0.9523184605473805, + "learning_rate": 8.120261449032707e-06, + "loss": 0.8038, + "step": 6404 + }, + { + "epoch": 0.5735071912250266, + "grad_norm": 0.9856344743866243, + "learning_rate": 8.117412939944034e-06, + "loss": 0.8833, + "step": 6405 + }, + { + "epoch": 0.5735967317701046, + "grad_norm": 0.8931507032660019, + "learning_rate": 8.114564589212446e-06, + "loss": 0.8244, + "step": 6406 + }, + { + "epoch": 0.5736862723151828, + "grad_norm": 0.9919698173016027, + "learning_rate": 8.111716397077539e-06, + "loss": 0.8333, + "step": 6407 + }, + { + "epoch": 0.5737758128602608, + "grad_norm": 0.9469042309268327, + "learning_rate": 8.108868363778894e-06, + "loss": 0.8647, + "step": 6408 + }, + { + "epoch": 0.5738653534053388, + "grad_norm": 0.915613720385012, + "learning_rate": 8.106020489556083e-06, + "loss": 0.768, + "step": 6409 + }, + { + "epoch": 0.5739548939504169, + "grad_norm": 0.8861685913117677, + "learning_rate": 8.103172774648658e-06, + "loss": 0.7898, + "step": 6410 + }, + { + "epoch": 0.574044434495495, + "grad_norm": 1.0054692895449444, + "learning_rate": 8.100325219296155e-06, + "loss": 0.8109, + "step": 6411 + }, + { + "epoch": 0.5741339750405731, + "grad_norm": 1.1020898335691662, + "learning_rate": 8.097477823738105e-06, + "loss": 0.8545, + "step": 6412 + }, + { + "epoch": 0.5742235155856511, + "grad_norm": 0.933284281829491, + "learning_rate": 8.094630588214018e-06, + "loss": 0.7864, + "step": 6413 + }, + { + "epoch": 0.5743130561307292, + "grad_norm": 1.0150261148943502, + "learning_rate": 8.0917835129634e-06, + "loss": 0.8852, + "step": 6414 + }, + { + "epoch": 0.5744025966758073, + "grad_norm": 0.8763502477388453, + "learning_rate": 8.088936598225733e-06, + "loss": 0.8007, + "step": 6415 + }, + { + "epoch": 0.5744921372208853, + "grad_norm": 1.017271770795491, + "learning_rate": 8.086089844240495e-06, + "loss": 0.8185, + "step": 6416 + }, + { + "epoch": 0.5745816777659634, + "grad_norm": 0.8606119400167056, + "learning_rate": 8.08324325124714e-06, + "loss": 0.816, + "step": 6417 + }, + { + "epoch": 0.5746712183110415, + "grad_norm": 0.8028210954214167, + "learning_rate": 8.080396819485117e-06, + "loss": 0.8223, + "step": 6418 + }, + { + "epoch": 0.5747607588561195, + "grad_norm": 0.8999896038255069, + "learning_rate": 8.077550549193856e-06, + "loss": 0.7793, + "step": 6419 + }, + { + "epoch": 0.5748502994011976, + "grad_norm": 1.0418254285132305, + "learning_rate": 8.07470444061278e-06, + "loss": 0.8541, + "step": 6420 + }, + { + "epoch": 0.5749398399462756, + "grad_norm": 1.1736254697129083, + "learning_rate": 8.071858493981293e-06, + "loss": 0.8359, + "step": 6421 + }, + { + "epoch": 0.5750293804913538, + "grad_norm": 0.8641004437980728, + "learning_rate": 8.069012709538786e-06, + "loss": 0.8174, + "step": 6422 + }, + { + "epoch": 0.5751189210364318, + "grad_norm": 0.9273547965900395, + "learning_rate": 8.066167087524637e-06, + "loss": 0.8892, + "step": 6423 + }, + { + "epoch": 0.5752084615815098, + "grad_norm": 0.9911392613874068, + "learning_rate": 8.063321628178211e-06, + "loss": 0.7688, + "step": 6424 + }, + { + "epoch": 0.575298002126588, + "grad_norm": 0.9121099453851654, + "learning_rate": 8.060476331738856e-06, + "loss": 0.8545, + "step": 6425 + }, + { + "epoch": 0.575387542671666, + "grad_norm": 0.893294219833341, + "learning_rate": 8.057631198445915e-06, + "loss": 0.8352, + "step": 6426 + }, + { + "epoch": 0.5754770832167441, + "grad_norm": 0.927612744048782, + "learning_rate": 8.05478622853871e-06, + "loss": 0.8077, + "step": 6427 + }, + { + "epoch": 0.5755666237618221, + "grad_norm": 1.083147704610812, + "learning_rate": 8.051941422256545e-06, + "loss": 0.8447, + "step": 6428 + }, + { + "epoch": 0.5756561643069003, + "grad_norm": 0.985976398837955, + "learning_rate": 8.04909677983872e-06, + "loss": 0.8281, + "step": 6429 + }, + { + "epoch": 0.5757457048519783, + "grad_norm": 1.324972808071582, + "learning_rate": 8.046252301524515e-06, + "loss": 0.8585, + "step": 6430 + }, + { + "epoch": 0.5758352453970563, + "grad_norm": 0.8813350433492376, + "learning_rate": 8.043407987553198e-06, + "loss": 0.8635, + "step": 6431 + }, + { + "epoch": 0.5759247859421345, + "grad_norm": 0.8977041449262854, + "learning_rate": 8.040563838164034e-06, + "loss": 0.9122, + "step": 6432 + }, + { + "epoch": 0.5760143264872125, + "grad_norm": 0.8833341800490374, + "learning_rate": 8.03771985359625e-06, + "loss": 0.7945, + "step": 6433 + }, + { + "epoch": 0.5761038670322906, + "grad_norm": 1.0429128547361064, + "learning_rate": 8.034876034089072e-06, + "loss": 0.8227, + "step": 6434 + }, + { + "epoch": 0.5761934075773686, + "grad_norm": 0.9408627580945907, + "learning_rate": 8.032032379881723e-06, + "loss": 0.8359, + "step": 6435 + }, + { + "epoch": 0.5762829481224467, + "grad_norm": 0.9356627139783498, + "learning_rate": 8.029188891213398e-06, + "loss": 0.8658, + "step": 6436 + }, + { + "epoch": 0.5763724886675248, + "grad_norm": 0.8854871291210523, + "learning_rate": 8.02634556832328e-06, + "loss": 0.8381, + "step": 6437 + }, + { + "epoch": 0.5764620292126028, + "grad_norm": 0.9822465113106529, + "learning_rate": 8.023502411450543e-06, + "loss": 0.8306, + "step": 6438 + }, + { + "epoch": 0.5765515697576808, + "grad_norm": 1.011816271212423, + "learning_rate": 8.020659420834341e-06, + "loss": 0.8017, + "step": 6439 + }, + { + "epoch": 0.576641110302759, + "grad_norm": 0.8772504311750633, + "learning_rate": 8.017816596713815e-06, + "loss": 0.8144, + "step": 6440 + }, + { + "epoch": 0.576730650847837, + "grad_norm": 0.9226348972623325, + "learning_rate": 8.0149739393281e-06, + "loss": 0.8433, + "step": 6441 + }, + { + "epoch": 0.5768201913929151, + "grad_norm": 0.9778638608023535, + "learning_rate": 8.012131448916309e-06, + "loss": 0.8229, + "step": 6442 + }, + { + "epoch": 0.5769097319379932, + "grad_norm": 0.9459635919096719, + "learning_rate": 8.009289125717546e-06, + "loss": 0.8086, + "step": 6443 + }, + { + "epoch": 0.5769992724830713, + "grad_norm": 0.93327348591905, + "learning_rate": 8.006446969970892e-06, + "loss": 0.9015, + "step": 6444 + }, + { + "epoch": 0.5770888130281493, + "grad_norm": 0.9880004412820398, + "learning_rate": 8.00360498191542e-06, + "loss": 0.8342, + "step": 6445 + }, + { + "epoch": 0.5771783535732273, + "grad_norm": 0.9422495703148925, + "learning_rate": 8.000763161790191e-06, + "loss": 0.8364, + "step": 6446 + }, + { + "epoch": 0.5772678941183055, + "grad_norm": 0.8795069728102327, + "learning_rate": 7.997921509834253e-06, + "loss": 0.7863, + "step": 6447 + }, + { + "epoch": 0.5773574346633835, + "grad_norm": 0.943865611030886, + "learning_rate": 7.995080026286632e-06, + "loss": 0.8032, + "step": 6448 + }, + { + "epoch": 0.5774469752084616, + "grad_norm": 0.9511911084077231, + "learning_rate": 7.992238711386348e-06, + "loss": 0.8403, + "step": 6449 + }, + { + "epoch": 0.5775365157535397, + "grad_norm": 0.9308580558202565, + "learning_rate": 7.9893975653724e-06, + "loss": 0.8824, + "step": 6450 + }, + { + "epoch": 0.5776260562986177, + "grad_norm": 0.9608729100307624, + "learning_rate": 7.986556588483776e-06, + "loss": 0.8445, + "step": 6451 + }, + { + "epoch": 0.5777155968436958, + "grad_norm": 0.9172710655616992, + "learning_rate": 7.983715780959448e-06, + "loss": 0.7698, + "step": 6452 + }, + { + "epoch": 0.5778051373887738, + "grad_norm": 1.3098724098321528, + "learning_rate": 7.980875143038381e-06, + "loss": 0.8138, + "step": 6453 + }, + { + "epoch": 0.577894677933852, + "grad_norm": 0.9238457182182461, + "learning_rate": 7.97803467495952e-06, + "loss": 0.8468, + "step": 6454 + }, + { + "epoch": 0.57798421847893, + "grad_norm": 1.0245239461000697, + "learning_rate": 7.975194376961788e-06, + "loss": 0.8694, + "step": 6455 + }, + { + "epoch": 0.578073759024008, + "grad_norm": 1.0220135423769703, + "learning_rate": 7.972354249284108e-06, + "loss": 0.8636, + "step": 6456 + }, + { + "epoch": 0.5781632995690861, + "grad_norm": 1.0211911329064685, + "learning_rate": 7.969514292165383e-06, + "loss": 0.8201, + "step": 6457 + }, + { + "epoch": 0.5782528401141642, + "grad_norm": 0.9262164975198456, + "learning_rate": 7.966674505844497e-06, + "loss": 0.7861, + "step": 6458 + }, + { + "epoch": 0.5783423806592423, + "grad_norm": 0.9313697274232522, + "learning_rate": 7.963834890560325e-06, + "loss": 0.8033, + "step": 6459 + }, + { + "epoch": 0.5784319212043203, + "grad_norm": 0.873137817051088, + "learning_rate": 7.960995446551733e-06, + "loss": 0.8247, + "step": 6460 + }, + { + "epoch": 0.5785214617493984, + "grad_norm": 0.9750954985854806, + "learning_rate": 7.958156174057552e-06, + "loss": 0.8028, + "step": 6461 + }, + { + "epoch": 0.5786110022944765, + "grad_norm": 0.9167504155995849, + "learning_rate": 7.955317073316622e-06, + "loss": 0.8212, + "step": 6462 + }, + { + "epoch": 0.5787005428395545, + "grad_norm": 0.9747949818731226, + "learning_rate": 7.952478144567757e-06, + "loss": 0.8006, + "step": 6463 + }, + { + "epoch": 0.5787900833846326, + "grad_norm": 1.0470035388965684, + "learning_rate": 7.949639388049758e-06, + "loss": 0.8177, + "step": 6464 + }, + { + "epoch": 0.5788796239297107, + "grad_norm": 0.9125953701278784, + "learning_rate": 7.946800804001415e-06, + "loss": 0.8712, + "step": 6465 + }, + { + "epoch": 0.5789691644747887, + "grad_norm": 0.9367846908157579, + "learning_rate": 7.943962392661494e-06, + "loss": 0.8458, + "step": 6466 + }, + { + "epoch": 0.5790587050198668, + "grad_norm": 1.0526166378394979, + "learning_rate": 7.941124154268757e-06, + "loss": 0.847, + "step": 6467 + }, + { + "epoch": 0.5791482455649449, + "grad_norm": 1.0490506524031435, + "learning_rate": 7.938286089061948e-06, + "loss": 0.7942, + "step": 6468 + }, + { + "epoch": 0.579237786110023, + "grad_norm": 0.9596918034821302, + "learning_rate": 7.935448197279794e-06, + "loss": 0.8194, + "step": 6469 + }, + { + "epoch": 0.579327326655101, + "grad_norm": 0.8490260695587314, + "learning_rate": 7.932610479161012e-06, + "loss": 0.7803, + "step": 6470 + }, + { + "epoch": 0.579416867200179, + "grad_norm": 0.9551718615986595, + "learning_rate": 7.929772934944298e-06, + "loss": 0.7898, + "step": 6471 + }, + { + "epoch": 0.5795064077452572, + "grad_norm": 1.0487460697841804, + "learning_rate": 7.926935564868338e-06, + "loss": 0.8114, + "step": 6472 + }, + { + "epoch": 0.5795959482903352, + "grad_norm": 0.9234694604258941, + "learning_rate": 7.9240983691718e-06, + "loss": 0.7906, + "step": 6473 + }, + { + "epoch": 0.5796854888354133, + "grad_norm": 0.8535202562732565, + "learning_rate": 7.921261348093346e-06, + "loss": 0.6869, + "step": 6474 + }, + { + "epoch": 0.5797750293804913, + "grad_norm": 1.0002062016364197, + "learning_rate": 7.918424501871613e-06, + "loss": 0.8363, + "step": 6475 + }, + { + "epoch": 0.5798645699255695, + "grad_norm": 1.1356524774197536, + "learning_rate": 7.915587830745229e-06, + "loss": 0.7282, + "step": 6476 + }, + { + "epoch": 0.5799541104706475, + "grad_norm": 1.038139873624416, + "learning_rate": 7.912751334952803e-06, + "loss": 0.8015, + "step": 6477 + }, + { + "epoch": 0.5800436510157255, + "grad_norm": 0.8986751948493565, + "learning_rate": 7.909915014732932e-06, + "loss": 0.8199, + "step": 6478 + }, + { + "epoch": 0.5801331915608037, + "grad_norm": 0.9738098402958514, + "learning_rate": 7.907078870324197e-06, + "loss": 0.8661, + "step": 6479 + }, + { + "epoch": 0.5802227321058817, + "grad_norm": 1.3008857274170373, + "learning_rate": 7.904242901965171e-06, + "loss": 0.789, + "step": 6480 + }, + { + "epoch": 0.5803122726509597, + "grad_norm": 0.986083315281657, + "learning_rate": 7.901407109894406e-06, + "loss": 0.8518, + "step": 6481 + }, + { + "epoch": 0.5804018131960378, + "grad_norm": 0.9380068620334621, + "learning_rate": 7.898571494350429e-06, + "loss": 0.8424, + "step": 6482 + }, + { + "epoch": 0.5804913537411159, + "grad_norm": 0.8927072984860644, + "learning_rate": 7.895736055571771e-06, + "loss": 0.8523, + "step": 6483 + }, + { + "epoch": 0.580580894286194, + "grad_norm": 1.0035839803547761, + "learning_rate": 7.892900793796942e-06, + "loss": 0.7784, + "step": 6484 + }, + { + "epoch": 0.580670434831272, + "grad_norm": 0.9005322808047742, + "learning_rate": 7.890065709264428e-06, + "loss": 0.7741, + "step": 6485 + }, + { + "epoch": 0.5807599753763502, + "grad_norm": 0.9113774279138676, + "learning_rate": 7.887230802212714e-06, + "loss": 0.8099, + "step": 6486 + }, + { + "epoch": 0.5808495159214282, + "grad_norm": 0.9053044789014115, + "learning_rate": 7.884396072880262e-06, + "loss": 0.762, + "step": 6487 + }, + { + "epoch": 0.5809390564665062, + "grad_norm": 0.9767837015772131, + "learning_rate": 7.881561521505515e-06, + "loss": 0.83, + "step": 6488 + }, + { + "epoch": 0.5810285970115843, + "grad_norm": 0.9567417666481594, + "learning_rate": 7.878727148326908e-06, + "loss": 0.8582, + "step": 6489 + }, + { + "epoch": 0.5811181375566624, + "grad_norm": 0.8781653500168903, + "learning_rate": 7.875892953582862e-06, + "loss": 0.8291, + "step": 6490 + }, + { + "epoch": 0.5812076781017405, + "grad_norm": 1.1064947378322958, + "learning_rate": 7.873058937511781e-06, + "loss": 0.8636, + "step": 6491 + }, + { + "epoch": 0.5812972186468185, + "grad_norm": 1.0285956385870236, + "learning_rate": 7.870225100352052e-06, + "loss": 0.9082, + "step": 6492 + }, + { + "epoch": 0.5813867591918965, + "grad_norm": 0.993031976140912, + "learning_rate": 7.867391442342044e-06, + "loss": 0.8146, + "step": 6493 + }, + { + "epoch": 0.5814762997369747, + "grad_norm": 0.9430822387795121, + "learning_rate": 7.864557963720116e-06, + "loss": 0.7642, + "step": 6494 + }, + { + "epoch": 0.5815658402820527, + "grad_norm": 0.8970087812352168, + "learning_rate": 7.861724664724617e-06, + "loss": 0.7885, + "step": 6495 + }, + { + "epoch": 0.5816553808271308, + "grad_norm": 1.0270269115861046, + "learning_rate": 7.858891545593871e-06, + "loss": 0.8346, + "step": 6496 + }, + { + "epoch": 0.5817449213722089, + "grad_norm": 1.033156520873014, + "learning_rate": 7.85605860656619e-06, + "loss": 0.8279, + "step": 6497 + }, + { + "epoch": 0.5818344619172869, + "grad_norm": 0.9731242629229762, + "learning_rate": 7.853225847879875e-06, + "loss": 0.8459, + "step": 6498 + }, + { + "epoch": 0.581924002462365, + "grad_norm": 0.9049429967492776, + "learning_rate": 7.850393269773205e-06, + "loss": 0.774, + "step": 6499 + }, + { + "epoch": 0.582013543007443, + "grad_norm": 0.9130349754118905, + "learning_rate": 7.847560872484444e-06, + "loss": 0.8409, + "step": 6500 + }, + { + "epoch": 0.5821030835525212, + "grad_norm": 1.0792733107916725, + "learning_rate": 7.844728656251852e-06, + "loss": 0.8298, + "step": 6501 + }, + { + "epoch": 0.5821926240975992, + "grad_norm": 1.0025652996532626, + "learning_rate": 7.841896621313662e-06, + "loss": 0.8518, + "step": 6502 + }, + { + "epoch": 0.5822821646426772, + "grad_norm": 0.985825961955646, + "learning_rate": 7.839064767908097e-06, + "loss": 0.8403, + "step": 6503 + }, + { + "epoch": 0.5823717051877554, + "grad_norm": 0.9400057664501444, + "learning_rate": 7.83623309627336e-06, + "loss": 0.8043, + "step": 6504 + }, + { + "epoch": 0.5824612457328334, + "grad_norm": 0.9606753748617977, + "learning_rate": 7.833401606647644e-06, + "loss": 0.8153, + "step": 6505 + }, + { + "epoch": 0.5825507862779115, + "grad_norm": 0.9326425624792472, + "learning_rate": 7.830570299269123e-06, + "loss": 0.7684, + "step": 6506 + }, + { + "epoch": 0.5826403268229895, + "grad_norm": 1.3163131549117357, + "learning_rate": 7.827739174375959e-06, + "loss": 0.8561, + "step": 6507 + }, + { + "epoch": 0.5827298673680676, + "grad_norm": 0.8572810905846464, + "learning_rate": 7.824908232206299e-06, + "loss": 0.7907, + "step": 6508 + }, + { + "epoch": 0.5828194079131457, + "grad_norm": 0.9435299220457629, + "learning_rate": 7.822077472998271e-06, + "loss": 0.8369, + "step": 6509 + }, + { + "epoch": 0.5829089484582237, + "grad_norm": 0.9467162466302117, + "learning_rate": 7.819246896989989e-06, + "loss": 0.7816, + "step": 6510 + }, + { + "epoch": 0.5829984890033018, + "grad_norm": 1.0073229335728897, + "learning_rate": 7.816416504419549e-06, + "loss": 0.8768, + "step": 6511 + }, + { + "epoch": 0.5830880295483799, + "grad_norm": 0.9844796030669847, + "learning_rate": 7.81358629552504e-06, + "loss": 0.8806, + "step": 6512 + }, + { + "epoch": 0.5831775700934579, + "grad_norm": 0.9864634159572417, + "learning_rate": 7.810756270544522e-06, + "loss": 0.8214, + "step": 6513 + }, + { + "epoch": 0.583267110638536, + "grad_norm": 1.128980745728833, + "learning_rate": 7.80792642971606e-06, + "loss": 0.8028, + "step": 6514 + }, + { + "epoch": 0.5833566511836141, + "grad_norm": 0.9273665232179712, + "learning_rate": 7.805096773277677e-06, + "loss": 0.8192, + "step": 6515 + }, + { + "epoch": 0.5834461917286922, + "grad_norm": 0.9271952357233152, + "learning_rate": 7.802267301467401e-06, + "loss": 0.7855, + "step": 6516 + }, + { + "epoch": 0.5835357322737702, + "grad_norm": 0.9739860436020333, + "learning_rate": 7.799438014523241e-06, + "loss": 0.8071, + "step": 6517 + }, + { + "epoch": 0.5836252728188482, + "grad_norm": 0.8924882977585086, + "learning_rate": 7.796608912683182e-06, + "loss": 0.8319, + "step": 6518 + }, + { + "epoch": 0.5837148133639264, + "grad_norm": 1.0414374688833659, + "learning_rate": 7.793779996185201e-06, + "loss": 0.8345, + "step": 6519 + }, + { + "epoch": 0.5838043539090044, + "grad_norm": 0.9258732752281499, + "learning_rate": 7.790951265267261e-06, + "loss": 0.8539, + "step": 6520 + }, + { + "epoch": 0.5838938944540825, + "grad_norm": 1.017117219658151, + "learning_rate": 7.788122720167298e-06, + "loss": 0.8369, + "step": 6521 + }, + { + "epoch": 0.5839834349991606, + "grad_norm": 0.9179593805442967, + "learning_rate": 7.785294361123244e-06, + "loss": 0.7987, + "step": 6522 + }, + { + "epoch": 0.5840729755442386, + "grad_norm": 0.9464236419664835, + "learning_rate": 7.782466188373013e-06, + "loss": 0.858, + "step": 6523 + }, + { + "epoch": 0.5841625160893167, + "grad_norm": 1.0876593481477803, + "learning_rate": 7.779638202154499e-06, + "loss": 0.8192, + "step": 6524 + }, + { + "epoch": 0.5842520566343947, + "grad_norm": 1.0477459710207044, + "learning_rate": 7.776810402705586e-06, + "loss": 0.8673, + "step": 6525 + }, + { + "epoch": 0.5843415971794729, + "grad_norm": 0.9166272871051644, + "learning_rate": 7.773982790264136e-06, + "loss": 0.8423, + "step": 6526 + }, + { + "epoch": 0.5844311377245509, + "grad_norm": 0.9351455763214804, + "learning_rate": 7.771155365067996e-06, + "loss": 0.7638, + "step": 6527 + }, + { + "epoch": 0.584520678269629, + "grad_norm": 0.9139307395077264, + "learning_rate": 7.768328127355008e-06, + "loss": 0.8371, + "step": 6528 + }, + { + "epoch": 0.584610218814707, + "grad_norm": 0.9134923663957756, + "learning_rate": 7.765501077362985e-06, + "loss": 0.8163, + "step": 6529 + }, + { + "epoch": 0.5846997593597851, + "grad_norm": 1.0035874345575289, + "learning_rate": 7.762674215329729e-06, + "loss": 0.8271, + "step": 6530 + }, + { + "epoch": 0.5847892999048632, + "grad_norm": 0.9569251843374329, + "learning_rate": 7.759847541493028e-06, + "loss": 0.8346, + "step": 6531 + }, + { + "epoch": 0.5848788404499412, + "grad_norm": 0.9479052696463844, + "learning_rate": 7.757021056090652e-06, + "loss": 0.8051, + "step": 6532 + }, + { + "epoch": 0.5849683809950194, + "grad_norm": 0.9111167163791011, + "learning_rate": 7.754194759360353e-06, + "loss": 0.8326, + "step": 6533 + }, + { + "epoch": 0.5850579215400974, + "grad_norm": 1.0209096740325037, + "learning_rate": 7.751368651539875e-06, + "loss": 0.8456, + "step": 6534 + }, + { + "epoch": 0.5851474620851754, + "grad_norm": 1.0542473094057696, + "learning_rate": 7.748542732866937e-06, + "loss": 0.8434, + "step": 6535 + }, + { + "epoch": 0.5852370026302535, + "grad_norm": 0.9153273199910147, + "learning_rate": 7.745717003579249e-06, + "loss": 0.8424, + "step": 6536 + }, + { + "epoch": 0.5853265431753316, + "grad_norm": 0.8816081227294614, + "learning_rate": 7.742891463914501e-06, + "loss": 0.8173, + "step": 6537 + }, + { + "epoch": 0.5854160837204097, + "grad_norm": 0.9069138966185126, + "learning_rate": 7.740066114110365e-06, + "loss": 0.8031, + "step": 6538 + }, + { + "epoch": 0.5855056242654877, + "grad_norm": 0.9351886346572181, + "learning_rate": 7.737240954404506e-06, + "loss": 0.7647, + "step": 6539 + }, + { + "epoch": 0.5855951648105658, + "grad_norm": 0.9419244196572438, + "learning_rate": 7.73441598503456e-06, + "loss": 0.8174, + "step": 6540 + }, + { + "epoch": 0.5856847053556439, + "grad_norm": 0.9256638253441095, + "learning_rate": 7.731591206238166e-06, + "loss": 0.841, + "step": 6541 + }, + { + "epoch": 0.5857742459007219, + "grad_norm": 0.8859346176872049, + "learning_rate": 7.728766618252921e-06, + "loss": 0.7971, + "step": 6542 + }, + { + "epoch": 0.5858637864458, + "grad_norm": 0.9077510648784982, + "learning_rate": 7.725942221316428e-06, + "loss": 0.8859, + "step": 6543 + }, + { + "epoch": 0.5859533269908781, + "grad_norm": 1.0515475937348417, + "learning_rate": 7.723118015666266e-06, + "loss": 0.8045, + "step": 6544 + }, + { + "epoch": 0.5860428675359561, + "grad_norm": 0.9256529641755565, + "learning_rate": 7.720294001539996e-06, + "loss": 0.7842, + "step": 6545 + }, + { + "epoch": 0.5861324080810342, + "grad_norm": 0.8595442360291764, + "learning_rate": 7.717470179175164e-06, + "loss": 0.8309, + "step": 6546 + }, + { + "epoch": 0.5862219486261122, + "grad_norm": 1.2250932395170544, + "learning_rate": 7.714646548809309e-06, + "loss": 0.7827, + "step": 6547 + }, + { + "epoch": 0.5863114891711904, + "grad_norm": 0.9690867562603219, + "learning_rate": 7.711823110679933e-06, + "loss": 0.8023, + "step": 6548 + }, + { + "epoch": 0.5864010297162684, + "grad_norm": 0.9103584777312022, + "learning_rate": 7.708999865024541e-06, + "loss": 0.7929, + "step": 6549 + }, + { + "epoch": 0.5864905702613464, + "grad_norm": 0.9742186744014101, + "learning_rate": 7.706176812080616e-06, + "loss": 0.8751, + "step": 6550 + }, + { + "epoch": 0.5865801108064246, + "grad_norm": 0.9601507606348049, + "learning_rate": 7.703353952085622e-06, + "loss": 0.7875, + "step": 6551 + }, + { + "epoch": 0.5866696513515026, + "grad_norm": 0.9199750658989079, + "learning_rate": 7.700531285277012e-06, + "loss": 0.8012, + "step": 6552 + }, + { + "epoch": 0.5867591918965807, + "grad_norm": 1.4820086786098718, + "learning_rate": 7.697708811892214e-06, + "loss": 0.7707, + "step": 6553 + }, + { + "epoch": 0.5868487324416587, + "grad_norm": 0.9792661465131891, + "learning_rate": 7.694886532168649e-06, + "loss": 0.8054, + "step": 6554 + }, + { + "epoch": 0.5869382729867368, + "grad_norm": 0.9310413611926751, + "learning_rate": 7.692064446343717e-06, + "loss": 0.8559, + "step": 6555 + }, + { + "epoch": 0.5870278135318149, + "grad_norm": 0.9599698243040112, + "learning_rate": 7.689242554654801e-06, + "loss": 0.8214, + "step": 6556 + }, + { + "epoch": 0.5871173540768929, + "grad_norm": 0.9910594408304109, + "learning_rate": 7.686420857339274e-06, + "loss": 0.8551, + "step": 6557 + }, + { + "epoch": 0.5872068946219711, + "grad_norm": 0.978620586844061, + "learning_rate": 7.683599354634488e-06, + "loss": 0.8161, + "step": 6558 + }, + { + "epoch": 0.5872964351670491, + "grad_norm": 0.9575334617658113, + "learning_rate": 7.680778046777771e-06, + "loss": 0.8348, + "step": 6559 + }, + { + "epoch": 0.5873859757121271, + "grad_norm": 0.8698630229875397, + "learning_rate": 7.677956934006447e-06, + "loss": 0.8298, + "step": 6560 + }, + { + "epoch": 0.5874755162572052, + "grad_norm": 0.8907208647401973, + "learning_rate": 7.675136016557821e-06, + "loss": 0.7853, + "step": 6561 + }, + { + "epoch": 0.5875650568022833, + "grad_norm": 0.9846409857100126, + "learning_rate": 7.672315294669176e-06, + "loss": 0.8031, + "step": 6562 + }, + { + "epoch": 0.5876545973473614, + "grad_norm": 1.0249112021708875, + "learning_rate": 7.669494768577786e-06, + "loss": 0.8438, + "step": 6563 + }, + { + "epoch": 0.5877441378924394, + "grad_norm": 1.3690566969401612, + "learning_rate": 7.6666744385209e-06, + "loss": 0.8579, + "step": 6564 + }, + { + "epoch": 0.5878336784375174, + "grad_norm": 0.8134557783595218, + "learning_rate": 7.663854304735756e-06, + "loss": 0.8096, + "step": 6565 + }, + { + "epoch": 0.5879232189825956, + "grad_norm": 0.9140859010134188, + "learning_rate": 7.661034367459574e-06, + "loss": 0.8743, + "step": 6566 + }, + { + "epoch": 0.5880127595276736, + "grad_norm": 0.9802241986350292, + "learning_rate": 7.65821462692956e-06, + "loss": 0.8385, + "step": 6567 + }, + { + "epoch": 0.5881023000727517, + "grad_norm": 0.9339292607956735, + "learning_rate": 7.6553950833829e-06, + "loss": 0.8375, + "step": 6568 + }, + { + "epoch": 0.5881918406178298, + "grad_norm": 0.9329896670811443, + "learning_rate": 7.652575737056766e-06, + "loss": 0.8057, + "step": 6569 + }, + { + "epoch": 0.5882813811629078, + "grad_norm": 0.9600981929218849, + "learning_rate": 7.649756588188312e-06, + "loss": 0.7864, + "step": 6570 + }, + { + "epoch": 0.5883709217079859, + "grad_norm": 0.8888557952450733, + "learning_rate": 7.646937637014674e-06, + "loss": 0.8099, + "step": 6571 + }, + { + "epoch": 0.5884604622530639, + "grad_norm": 1.0498738590788856, + "learning_rate": 7.644118883772975e-06, + "loss": 0.8472, + "step": 6572 + }, + { + "epoch": 0.5885500027981421, + "grad_norm": 0.9882924258730189, + "learning_rate": 7.641300328700314e-06, + "loss": 0.7891, + "step": 6573 + }, + { + "epoch": 0.5886395433432201, + "grad_norm": 0.990703206817161, + "learning_rate": 7.638481972033792e-06, + "loss": 0.8337, + "step": 6574 + }, + { + "epoch": 0.5887290838882981, + "grad_norm": 1.0976528913213919, + "learning_rate": 7.635663814010464e-06, + "loss": 0.8589, + "step": 6575 + }, + { + "epoch": 0.5888186244333763, + "grad_norm": 0.9187144225746039, + "learning_rate": 7.632845854867393e-06, + "loss": 0.7801, + "step": 6576 + }, + { + "epoch": 0.5889081649784543, + "grad_norm": 0.9524297820233272, + "learning_rate": 7.630028094841615e-06, + "loss": 0.7885, + "step": 6577 + }, + { + "epoch": 0.5889977055235324, + "grad_norm": 1.024816718414577, + "learning_rate": 7.627210534170149e-06, + "loss": 0.7966, + "step": 6578 + }, + { + "epoch": 0.5890872460686104, + "grad_norm": 1.0772812865675907, + "learning_rate": 7.624393173090001e-06, + "loss": 0.8591, + "step": 6579 + }, + { + "epoch": 0.5891767866136886, + "grad_norm": 0.8780474771131742, + "learning_rate": 7.621576011838163e-06, + "loss": 0.7758, + "step": 6580 + }, + { + "epoch": 0.5892663271587666, + "grad_norm": 0.9261027670092598, + "learning_rate": 7.618759050651594e-06, + "loss": 0.8416, + "step": 6581 + }, + { + "epoch": 0.5893558677038446, + "grad_norm": 0.9577012711410549, + "learning_rate": 7.615942289767257e-06, + "loss": 0.8043, + "step": 6582 + }, + { + "epoch": 0.5894454082489227, + "grad_norm": 0.9866846058374945, + "learning_rate": 7.613125729422084e-06, + "loss": 0.8264, + "step": 6583 + }, + { + "epoch": 0.5895349487940008, + "grad_norm": 0.9347165768098294, + "learning_rate": 7.610309369852997e-06, + "loss": 0.8518, + "step": 6584 + }, + { + "epoch": 0.5896244893390788, + "grad_norm": 1.058519527651719, + "learning_rate": 7.607493211296902e-06, + "loss": 0.8343, + "step": 6585 + }, + { + "epoch": 0.5897140298841569, + "grad_norm": 0.9374464299727447, + "learning_rate": 7.604677253990678e-06, + "loss": 0.821, + "step": 6586 + }, + { + "epoch": 0.589803570429235, + "grad_norm": 1.0949965730405946, + "learning_rate": 7.601861498171197e-06, + "loss": 0.812, + "step": 6587 + }, + { + "epoch": 0.5898931109743131, + "grad_norm": 0.9141566656520829, + "learning_rate": 7.599045944075312e-06, + "loss": 0.8112, + "step": 6588 + }, + { + "epoch": 0.5899826515193911, + "grad_norm": 0.9371639507897345, + "learning_rate": 7.596230591939859e-06, + "loss": 0.762, + "step": 6589 + }, + { + "epoch": 0.5900721920644691, + "grad_norm": 0.9132152418441872, + "learning_rate": 7.593415442001657e-06, + "loss": 0.8568, + "step": 6590 + }, + { + "epoch": 0.5901617326095473, + "grad_norm": 0.9313319111733054, + "learning_rate": 7.590600494497507e-06, + "loss": 0.8421, + "step": 6591 + }, + { + "epoch": 0.5902512731546253, + "grad_norm": 0.8835951660845978, + "learning_rate": 7.5877857496641885e-06, + "loss": 0.8216, + "step": 6592 + }, + { + "epoch": 0.5903408136997034, + "grad_norm": 1.0009783689524365, + "learning_rate": 7.584971207738473e-06, + "loss": 0.8697, + "step": 6593 + }, + { + "epoch": 0.5904303542447815, + "grad_norm": 0.9959506517717879, + "learning_rate": 7.582156868957106e-06, + "loss": 0.8044, + "step": 6594 + }, + { + "epoch": 0.5905198947898596, + "grad_norm": 0.9080331391788492, + "learning_rate": 7.57934273355683e-06, + "loss": 0.819, + "step": 6595 + }, + { + "epoch": 0.5906094353349376, + "grad_norm": 1.0180685387012558, + "learning_rate": 7.576528801774354e-06, + "loss": 0.7967, + "step": 6596 + }, + { + "epoch": 0.5906989758800156, + "grad_norm": 0.8637798463607022, + "learning_rate": 7.5737150738463764e-06, + "loss": 0.7979, + "step": 6597 + }, + { + "epoch": 0.5907885164250938, + "grad_norm": 0.9856224075049617, + "learning_rate": 7.5709015500095805e-06, + "loss": 0.8151, + "step": 6598 + }, + { + "epoch": 0.5908780569701718, + "grad_norm": 1.04226107780226, + "learning_rate": 7.56808823050063e-06, + "loss": 0.8121, + "step": 6599 + }, + { + "epoch": 0.5909675975152499, + "grad_norm": 0.8948428969388661, + "learning_rate": 7.565275115556171e-06, + "loss": 0.7475, + "step": 6600 + }, + { + "epoch": 0.5910571380603279, + "grad_norm": 0.9752955154662264, + "learning_rate": 7.562462205412841e-06, + "loss": 0.8382, + "step": 6601 + }, + { + "epoch": 0.591146678605406, + "grad_norm": 1.0173754421185708, + "learning_rate": 7.5596495003072426e-06, + "loss": 0.8164, + "step": 6602 + }, + { + "epoch": 0.5912362191504841, + "grad_norm": 1.0882351641410581, + "learning_rate": 7.556837000475976e-06, + "loss": 0.7666, + "step": 6603 + }, + { + "epoch": 0.5913257596955621, + "grad_norm": 1.0796334098674405, + "learning_rate": 7.554024706155621e-06, + "loss": 0.8109, + "step": 6604 + }, + { + "epoch": 0.5914153002406403, + "grad_norm": 1.0328346127183168, + "learning_rate": 7.551212617582735e-06, + "loss": 0.7747, + "step": 6605 + }, + { + "epoch": 0.5915048407857183, + "grad_norm": 1.034656528708423, + "learning_rate": 7.548400734993863e-06, + "loss": 0.8313, + "step": 6606 + }, + { + "epoch": 0.5915943813307963, + "grad_norm": 1.0502832269977334, + "learning_rate": 7.545589058625537e-06, + "loss": 0.8804, + "step": 6607 + }, + { + "epoch": 0.5916839218758744, + "grad_norm": 0.971353790024091, + "learning_rate": 7.542777588714256e-06, + "loss": 0.8595, + "step": 6608 + }, + { + "epoch": 0.5917734624209525, + "grad_norm": 1.0060084915729497, + "learning_rate": 7.539966325496519e-06, + "loss": 0.8414, + "step": 6609 + }, + { + "epoch": 0.5918630029660306, + "grad_norm": 1.0547995092521565, + "learning_rate": 7.537155269208799e-06, + "loss": 0.8137, + "step": 6610 + }, + { + "epoch": 0.5919525435111086, + "grad_norm": 0.9629636976761035, + "learning_rate": 7.534344420087552e-06, + "loss": 0.8485, + "step": 6611 + }, + { + "epoch": 0.5920420840561867, + "grad_norm": 0.9220577037706273, + "learning_rate": 7.5315337783692176e-06, + "loss": 0.8281, + "step": 6612 + }, + { + "epoch": 0.5921316246012648, + "grad_norm": 0.9431706916344231, + "learning_rate": 7.528723344290218e-06, + "loss": 0.8414, + "step": 6613 + }, + { + "epoch": 0.5922211651463428, + "grad_norm": 1.1325729741379715, + "learning_rate": 7.525913118086954e-06, + "loss": 0.8066, + "step": 6614 + }, + { + "epoch": 0.5923107056914209, + "grad_norm": 0.9693362756352698, + "learning_rate": 7.523103099995818e-06, + "loss": 0.8248, + "step": 6615 + }, + { + "epoch": 0.592400246236499, + "grad_norm": 0.9243909930039331, + "learning_rate": 7.520293290253178e-06, + "loss": 0.8153, + "step": 6616 + }, + { + "epoch": 0.592489786781577, + "grad_norm": 1.065544866218688, + "learning_rate": 7.517483689095386e-06, + "loss": 0.8501, + "step": 6617 + }, + { + "epoch": 0.5925793273266551, + "grad_norm": 1.0177646318500573, + "learning_rate": 7.514674296758779e-06, + "loss": 0.8582, + "step": 6618 + }, + { + "epoch": 0.5926688678717331, + "grad_norm": 1.0279589796450326, + "learning_rate": 7.511865113479668e-06, + "loss": 0.7605, + "step": 6619 + }, + { + "epoch": 0.5927584084168113, + "grad_norm": 0.8331584710905736, + "learning_rate": 7.509056139494357e-06, + "loss": 0.7925, + "step": 6620 + }, + { + "epoch": 0.5928479489618893, + "grad_norm": 0.9247971416921925, + "learning_rate": 7.506247375039123e-06, + "loss": 0.7744, + "step": 6621 + }, + { + "epoch": 0.5929374895069673, + "grad_norm": 1.0188921667513617, + "learning_rate": 7.503438820350236e-06, + "loss": 0.8375, + "step": 6622 + }, + { + "epoch": 0.5930270300520455, + "grad_norm": 0.9837046396693102, + "learning_rate": 7.500630475663941e-06, + "loss": 0.8269, + "step": 6623 + }, + { + "epoch": 0.5931165705971235, + "grad_norm": 0.9483604334552367, + "learning_rate": 7.497822341216465e-06, + "loss": 0.7799, + "step": 6624 + }, + { + "epoch": 0.5932061111422016, + "grad_norm": 0.8952056460498599, + "learning_rate": 7.4950144172440195e-06, + "loss": 0.8665, + "step": 6625 + }, + { + "epoch": 0.5932956516872796, + "grad_norm": 0.9165907640280305, + "learning_rate": 7.492206703982798e-06, + "loss": 0.8057, + "step": 6626 + }, + { + "epoch": 0.5933851922323577, + "grad_norm": 0.8811658502082405, + "learning_rate": 7.4893992016689745e-06, + "loss": 0.8174, + "step": 6627 + }, + { + "epoch": 0.5934747327774358, + "grad_norm": 1.1397267300945662, + "learning_rate": 7.4865919105387105e-06, + "loss": 0.7778, + "step": 6628 + }, + { + "epoch": 0.5935642733225138, + "grad_norm": 0.9572251559124834, + "learning_rate": 7.483784830828147e-06, + "loss": 0.8369, + "step": 6629 + }, + { + "epoch": 0.593653813867592, + "grad_norm": 1.026993803232246, + "learning_rate": 7.4809779627734016e-06, + "loss": 0.7854, + "step": 6630 + }, + { + "epoch": 0.59374335441267, + "grad_norm": 0.961356987297155, + "learning_rate": 7.478171306610582e-06, + "loss": 0.8637, + "step": 6631 + }, + { + "epoch": 0.593832894957748, + "grad_norm": 0.9777332229615109, + "learning_rate": 7.4753648625757735e-06, + "loss": 0.8366, + "step": 6632 + }, + { + "epoch": 0.5939224355028261, + "grad_norm": 1.0506171660220092, + "learning_rate": 7.472558630905043e-06, + "loss": 0.8419, + "step": 6633 + }, + { + "epoch": 0.5940119760479042, + "grad_norm": 0.9638614869840575, + "learning_rate": 7.469752611834451e-06, + "loss": 0.8343, + "step": 6634 + }, + { + "epoch": 0.5941015165929823, + "grad_norm": 1.2795868767348604, + "learning_rate": 7.466946805600019e-06, + "loss": 0.8001, + "step": 6635 + }, + { + "epoch": 0.5941910571380603, + "grad_norm": 1.21051507582244, + "learning_rate": 7.464141212437768e-06, + "loss": 0.8571, + "step": 6636 + }, + { + "epoch": 0.5942805976831383, + "grad_norm": 0.8602868087258023, + "learning_rate": 7.461335832583695e-06, + "loss": 0.8389, + "step": 6637 + }, + { + "epoch": 0.5943701382282165, + "grad_norm": 0.950213010689888, + "learning_rate": 7.458530666273779e-06, + "loss": 0.791, + "step": 6638 + }, + { + "epoch": 0.5944596787732945, + "grad_norm": 0.9833956455630151, + "learning_rate": 7.455725713743979e-06, + "loss": 0.8218, + "step": 6639 + }, + { + "epoch": 0.5945492193183726, + "grad_norm": 1.1059489021895281, + "learning_rate": 7.452920975230247e-06, + "loss": 0.7433, + "step": 6640 + }, + { + "epoch": 0.5946387598634507, + "grad_norm": 0.8681071021260057, + "learning_rate": 7.450116450968497e-06, + "loss": 0.8182, + "step": 6641 + }, + { + "epoch": 0.5947283004085288, + "grad_norm": 1.0024667623804866, + "learning_rate": 7.447312141194643e-06, + "loss": 0.8157, + "step": 6642 + }, + { + "epoch": 0.5948178409536068, + "grad_norm": 0.9719622416623019, + "learning_rate": 7.444508046144574e-06, + "loss": 0.8695, + "step": 6643 + }, + { + "epoch": 0.5949073814986848, + "grad_norm": 0.9294176887348778, + "learning_rate": 7.44170416605416e-06, + "loss": 0.8214, + "step": 6644 + }, + { + "epoch": 0.594996922043763, + "grad_norm": 0.9718671340228515, + "learning_rate": 7.4389005011592575e-06, + "loss": 0.823, + "step": 6645 + }, + { + "epoch": 0.595086462588841, + "grad_norm": 0.9437341618383176, + "learning_rate": 7.436097051695696e-06, + "loss": 0.8371, + "step": 6646 + }, + { + "epoch": 0.595176003133919, + "grad_norm": 0.9651042742065485, + "learning_rate": 7.433293817899296e-06, + "loss": 0.7833, + "step": 6647 + }, + { + "epoch": 0.5952655436789972, + "grad_norm": 1.0371490080918673, + "learning_rate": 7.430490800005854e-06, + "loss": 0.8364, + "step": 6648 + }, + { + "epoch": 0.5953550842240752, + "grad_norm": 1.0919618658274939, + "learning_rate": 7.427687998251155e-06, + "loss": 0.8315, + "step": 6649 + }, + { + "epoch": 0.5954446247691533, + "grad_norm": 0.9848350557440565, + "learning_rate": 7.424885412870959e-06, + "loss": 0.8417, + "step": 6650 + }, + { + "epoch": 0.5955341653142313, + "grad_norm": 0.9944695833333687, + "learning_rate": 7.422083044101012e-06, + "loss": 0.8116, + "step": 6651 + }, + { + "epoch": 0.5956237058593095, + "grad_norm": 0.9530477781466355, + "learning_rate": 7.419280892177037e-06, + "loss": 0.808, + "step": 6652 + }, + { + "epoch": 0.5957132464043875, + "grad_norm": 0.9184209224358462, + "learning_rate": 7.416478957334743e-06, + "loss": 0.7818, + "step": 6653 + }, + { + "epoch": 0.5958027869494655, + "grad_norm": 0.9256800079559844, + "learning_rate": 7.41367723980982e-06, + "loss": 0.8011, + "step": 6654 + }, + { + "epoch": 0.5958923274945436, + "grad_norm": 1.1317921681695022, + "learning_rate": 7.410875739837939e-06, + "loss": 0.8058, + "step": 6655 + }, + { + "epoch": 0.5959818680396217, + "grad_norm": 1.0354288676675154, + "learning_rate": 7.408074457654757e-06, + "loss": 0.8077, + "step": 6656 + }, + { + "epoch": 0.5960714085846998, + "grad_norm": 0.8750470024579546, + "learning_rate": 7.405273393495904e-06, + "loss": 0.8982, + "step": 6657 + }, + { + "epoch": 0.5961609491297778, + "grad_norm": 0.9690781573025311, + "learning_rate": 7.402472547596996e-06, + "loss": 0.8708, + "step": 6658 + }, + { + "epoch": 0.5962504896748559, + "grad_norm": 1.052874930621147, + "learning_rate": 7.399671920193634e-06, + "loss": 0.8308, + "step": 6659 + }, + { + "epoch": 0.596340030219934, + "grad_norm": 0.9086861232804438, + "learning_rate": 7.396871511521393e-06, + "loss": 0.8532, + "step": 6660 + }, + { + "epoch": 0.596429570765012, + "grad_norm": 0.9358289297314465, + "learning_rate": 7.3940713218158415e-06, + "loss": 0.7629, + "step": 6661 + }, + { + "epoch": 0.59651911131009, + "grad_norm": 0.9562086191653743, + "learning_rate": 7.3912713513125185e-06, + "loss": 0.8101, + "step": 6662 + }, + { + "epoch": 0.5966086518551682, + "grad_norm": 0.92783742408096, + "learning_rate": 7.388471600246948e-06, + "loss": 0.7502, + "step": 6663 + }, + { + "epoch": 0.5966981924002462, + "grad_norm": 0.9655393488611334, + "learning_rate": 7.385672068854636e-06, + "loss": 0.8647, + "step": 6664 + }, + { + "epoch": 0.5967877329453243, + "grad_norm": 0.9608357231144287, + "learning_rate": 7.382872757371069e-06, + "loss": 0.8135, + "step": 6665 + }, + { + "epoch": 0.5968772734904024, + "grad_norm": 1.0700632918641717, + "learning_rate": 7.380073666031717e-06, + "loss": 0.8134, + "step": 6666 + }, + { + "epoch": 0.5969668140354805, + "grad_norm": 0.9087431165462603, + "learning_rate": 7.377274795072036e-06, + "loss": 0.8256, + "step": 6667 + }, + { + "epoch": 0.5970563545805585, + "grad_norm": 0.9564177881585979, + "learning_rate": 7.374476144727446e-06, + "loss": 0.8152, + "step": 6668 + }, + { + "epoch": 0.5971458951256365, + "grad_norm": 0.9914061198177218, + "learning_rate": 7.371677715233369e-06, + "loss": 0.7979, + "step": 6669 + }, + { + "epoch": 0.5972354356707147, + "grad_norm": 0.8803631437245757, + "learning_rate": 7.368879506825197e-06, + "loss": 0.7826, + "step": 6670 + }, + { + "epoch": 0.5973249762157927, + "grad_norm": 0.9476148650530133, + "learning_rate": 7.366081519738309e-06, + "loss": 0.8275, + "step": 6671 + }, + { + "epoch": 0.5974145167608708, + "grad_norm": 0.918048481029053, + "learning_rate": 7.363283754208061e-06, + "loss": 0.827, + "step": 6672 + }, + { + "epoch": 0.5975040573059488, + "grad_norm": 0.907303951395112, + "learning_rate": 7.36048621046979e-06, + "loss": 0.8025, + "step": 6673 + }, + { + "epoch": 0.597593597851027, + "grad_norm": 1.0078204047292332, + "learning_rate": 7.357688888758816e-06, + "loss": 0.8475, + "step": 6674 + }, + { + "epoch": 0.597683138396105, + "grad_norm": 0.9428722770124248, + "learning_rate": 7.354891789310441e-06, + "loss": 0.8173, + "step": 6675 + }, + { + "epoch": 0.597772678941183, + "grad_norm": 0.946691591417038, + "learning_rate": 7.352094912359951e-06, + "loss": 0.7932, + "step": 6676 + }, + { + "epoch": 0.5978622194862612, + "grad_norm": 0.943795253530749, + "learning_rate": 7.34929825814261e-06, + "loss": 0.8224, + "step": 6677 + }, + { + "epoch": 0.5979517600313392, + "grad_norm": 0.9063418757229791, + "learning_rate": 7.346501826893662e-06, + "loss": 0.8324, + "step": 6678 + }, + { + "epoch": 0.5980413005764172, + "grad_norm": 0.9873556412072985, + "learning_rate": 7.343705618848331e-06, + "loss": 0.8447, + "step": 6679 + }, + { + "epoch": 0.5981308411214953, + "grad_norm": 0.9258455842112123, + "learning_rate": 7.340909634241827e-06, + "loss": 0.818, + "step": 6680 + }, + { + "epoch": 0.5982203816665734, + "grad_norm": 0.8572335827649304, + "learning_rate": 7.338113873309338e-06, + "loss": 0.838, + "step": 6681 + }, + { + "epoch": 0.5983099222116515, + "grad_norm": 0.9954530222602024, + "learning_rate": 7.335318336286038e-06, + "loss": 0.8436, + "step": 6682 + }, + { + "epoch": 0.5983994627567295, + "grad_norm": 0.9041859453918185, + "learning_rate": 7.332523023407079e-06, + "loss": 0.7962, + "step": 6683 + }, + { + "epoch": 0.5984890033018077, + "grad_norm": 0.8860385183541469, + "learning_rate": 7.329727934907587e-06, + "loss": 0.8275, + "step": 6684 + }, + { + "epoch": 0.5985785438468857, + "grad_norm": 0.8931839929902914, + "learning_rate": 7.3269330710226805e-06, + "loss": 0.8256, + "step": 6685 + }, + { + "epoch": 0.5986680843919637, + "grad_norm": 0.9604929691741774, + "learning_rate": 7.324138431987453e-06, + "loss": 0.8283, + "step": 6686 + }, + { + "epoch": 0.5987576249370418, + "grad_norm": 0.9843119965776497, + "learning_rate": 7.321344018036978e-06, + "loss": 0.77, + "step": 6687 + }, + { + "epoch": 0.5988471654821199, + "grad_norm": 0.9563474242461167, + "learning_rate": 7.318549829406318e-06, + "loss": 0.7943, + "step": 6688 + }, + { + "epoch": 0.598936706027198, + "grad_norm": 1.1590892639588533, + "learning_rate": 7.3157558663305115e-06, + "loss": 0.8356, + "step": 6689 + }, + { + "epoch": 0.599026246572276, + "grad_norm": 1.0970422858005777, + "learning_rate": 7.31296212904457e-06, + "loss": 0.8649, + "step": 6690 + }, + { + "epoch": 0.599115787117354, + "grad_norm": 0.8863977322658771, + "learning_rate": 7.3101686177834994e-06, + "loss": 0.8064, + "step": 6691 + }, + { + "epoch": 0.5992053276624322, + "grad_norm": 0.8702991587939508, + "learning_rate": 7.307375332782279e-06, + "loss": 0.8127, + "step": 6692 + }, + { + "epoch": 0.5992948682075102, + "grad_norm": 0.9648807291822504, + "learning_rate": 7.3045822742758695e-06, + "loss": 0.8397, + "step": 6693 + }, + { + "epoch": 0.5993844087525882, + "grad_norm": 0.9349920075668192, + "learning_rate": 7.301789442499222e-06, + "loss": 0.7727, + "step": 6694 + }, + { + "epoch": 0.5994739492976664, + "grad_norm": 0.9305387311643484, + "learning_rate": 7.298996837687246e-06, + "loss": 0.8084, + "step": 6695 + }, + { + "epoch": 0.5995634898427444, + "grad_norm": 0.9995157712927442, + "learning_rate": 7.2962044600748584e-06, + "loss": 0.8876, + "step": 6696 + }, + { + "epoch": 0.5996530303878225, + "grad_norm": 0.9479955580250966, + "learning_rate": 7.293412309896939e-06, + "loss": 0.8695, + "step": 6697 + }, + { + "epoch": 0.5997425709329005, + "grad_norm": 0.8919622355662048, + "learning_rate": 7.2906203873883575e-06, + "loss": 0.851, + "step": 6698 + }, + { + "epoch": 0.5998321114779787, + "grad_norm": 1.0292728865159777, + "learning_rate": 7.287828692783957e-06, + "loss": 0.8357, + "step": 6699 + }, + { + "epoch": 0.5999216520230567, + "grad_norm": 1.0104647615684283, + "learning_rate": 7.285037226318576e-06, + "loss": 0.8509, + "step": 6700 + }, + { + "epoch": 0.6000111925681347, + "grad_norm": 1.0808336523098174, + "learning_rate": 7.282245988227011e-06, + "loss": 0.8396, + "step": 6701 + }, + { + "epoch": 0.6001007331132129, + "grad_norm": 1.0342034904317794, + "learning_rate": 7.279454978744055e-06, + "loss": 0.8498, + "step": 6702 + }, + { + "epoch": 0.6001902736582909, + "grad_norm": 0.9691680708797978, + "learning_rate": 7.2766641981044824e-06, + "loss": 0.8723, + "step": 6703 + }, + { + "epoch": 0.600279814203369, + "grad_norm": 0.9707257010299679, + "learning_rate": 7.273873646543044e-06, + "loss": 0.8498, + "step": 6704 + }, + { + "epoch": 0.600369354748447, + "grad_norm": 0.9691527262924255, + "learning_rate": 7.2710833242944725e-06, + "loss": 0.7999, + "step": 6705 + }, + { + "epoch": 0.6004588952935251, + "grad_norm": 0.9178934345650496, + "learning_rate": 7.268293231593477e-06, + "loss": 0.8249, + "step": 6706 + }, + { + "epoch": 0.6005484358386032, + "grad_norm": 1.4312256263869274, + "learning_rate": 7.265503368674754e-06, + "loss": 0.8669, + "step": 6707 + }, + { + "epoch": 0.6006379763836812, + "grad_norm": 0.9462345880915896, + "learning_rate": 7.262713735772973e-06, + "loss": 0.8166, + "step": 6708 + }, + { + "epoch": 0.6007275169287593, + "grad_norm": 0.9028460380832712, + "learning_rate": 7.259924333122795e-06, + "loss": 0.8125, + "step": 6709 + }, + { + "epoch": 0.6008170574738374, + "grad_norm": 0.9816289605610599, + "learning_rate": 7.257135160958854e-06, + "loss": 0.8665, + "step": 6710 + }, + { + "epoch": 0.6009065980189154, + "grad_norm": 0.8754134057317976, + "learning_rate": 7.254346219515766e-06, + "loss": 0.7611, + "step": 6711 + }, + { + "epoch": 0.6009961385639935, + "grad_norm": 1.0598595090404133, + "learning_rate": 7.251557509028125e-06, + "loss": 0.8248, + "step": 6712 + }, + { + "epoch": 0.6010856791090716, + "grad_norm": 0.8642784349827424, + "learning_rate": 7.24876902973051e-06, + "loss": 0.8018, + "step": 6713 + }, + { + "epoch": 0.6011752196541497, + "grad_norm": 0.9907867942271675, + "learning_rate": 7.245980781857477e-06, + "loss": 0.8709, + "step": 6714 + }, + { + "epoch": 0.6012647601992277, + "grad_norm": 0.8646124239626344, + "learning_rate": 7.2431927656435674e-06, + "loss": 0.7726, + "step": 6715 + }, + { + "epoch": 0.6013543007443057, + "grad_norm": 0.9684102420119395, + "learning_rate": 7.240404981323301e-06, + "loss": 0.8754, + "step": 6716 + }, + { + "epoch": 0.6014438412893839, + "grad_norm": 1.2274486156391375, + "learning_rate": 7.2376174291311745e-06, + "loss": 0.8328, + "step": 6717 + }, + { + "epoch": 0.6015333818344619, + "grad_norm": 0.8972417097653106, + "learning_rate": 7.234830109301667e-06, + "loss": 0.8228, + "step": 6718 + }, + { + "epoch": 0.60162292237954, + "grad_norm": 0.8762515413788429, + "learning_rate": 7.23204302206924e-06, + "loss": 0.8035, + "step": 6719 + }, + { + "epoch": 0.6017124629246181, + "grad_norm": 0.9617789857605489, + "learning_rate": 7.2292561676683305e-06, + "loss": 0.8427, + "step": 6720 + }, + { + "epoch": 0.6018020034696961, + "grad_norm": 0.88656612031784, + "learning_rate": 7.2264695463333655e-06, + "loss": 0.8557, + "step": 6721 + }, + { + "epoch": 0.6018915440147742, + "grad_norm": 1.016314347631598, + "learning_rate": 7.223683158298748e-06, + "loss": 0.8501, + "step": 6722 + }, + { + "epoch": 0.6019810845598522, + "grad_norm": 1.041439772847646, + "learning_rate": 7.220897003798852e-06, + "loss": 0.8437, + "step": 6723 + }, + { + "epoch": 0.6020706251049304, + "grad_norm": 0.9659979101272343, + "learning_rate": 7.218111083068045e-06, + "loss": 0.8442, + "step": 6724 + }, + { + "epoch": 0.6021601656500084, + "grad_norm": 1.0182127079013046, + "learning_rate": 7.215325396340669e-06, + "loss": 0.8592, + "step": 6725 + }, + { + "epoch": 0.6022497061950864, + "grad_norm": 0.8979152169909671, + "learning_rate": 7.2125399438510425e-06, + "loss": 0.8807, + "step": 6726 + }, + { + "epoch": 0.6023392467401645, + "grad_norm": 1.1356164789921348, + "learning_rate": 7.2097547258334795e-06, + "loss": 0.8422, + "step": 6727 + }, + { + "epoch": 0.6024287872852426, + "grad_norm": 0.8513699427146872, + "learning_rate": 7.206969742522252e-06, + "loss": 0.7909, + "step": 6728 + }, + { + "epoch": 0.6025183278303207, + "grad_norm": 0.9632939873460633, + "learning_rate": 7.2041849941516265e-06, + "loss": 0.8544, + "step": 6729 + }, + { + "epoch": 0.6026078683753987, + "grad_norm": 0.8382926913068143, + "learning_rate": 7.201400480955849e-06, + "loss": 0.8008, + "step": 6730 + }, + { + "epoch": 0.6026974089204769, + "grad_norm": 0.9032306498260338, + "learning_rate": 7.1986162031691444e-06, + "loss": 0.8471, + "step": 6731 + }, + { + "epoch": 0.6027869494655549, + "grad_norm": 0.883267776133902, + "learning_rate": 7.195832161025717e-06, + "loss": 0.7989, + "step": 6732 + }, + { + "epoch": 0.6028764900106329, + "grad_norm": 1.2702912102214474, + "learning_rate": 7.193048354759751e-06, + "loss": 0.8532, + "step": 6733 + }, + { + "epoch": 0.602966030555711, + "grad_norm": 0.8571704404845609, + "learning_rate": 7.190264784605409e-06, + "loss": 0.7914, + "step": 6734 + }, + { + "epoch": 0.6030555711007891, + "grad_norm": 0.9251162783703075, + "learning_rate": 7.187481450796834e-06, + "loss": 0.8157, + "step": 6735 + }, + { + "epoch": 0.6031451116458671, + "grad_norm": 0.865788056813636, + "learning_rate": 7.184698353568157e-06, + "loss": 0.846, + "step": 6736 + }, + { + "epoch": 0.6032346521909452, + "grad_norm": 0.9089876256676758, + "learning_rate": 7.181915493153481e-06, + "loss": 0.8036, + "step": 6737 + }, + { + "epoch": 0.6033241927360233, + "grad_norm": 0.9595590509752535, + "learning_rate": 7.179132869786891e-06, + "loss": 0.8487, + "step": 6738 + }, + { + "epoch": 0.6034137332811014, + "grad_norm": 1.1187982975234714, + "learning_rate": 7.17635048370245e-06, + "loss": 0.8491, + "step": 6739 + }, + { + "epoch": 0.6035032738261794, + "grad_norm": 0.9533087926917494, + "learning_rate": 7.173568335134206e-06, + "loss": 0.8214, + "step": 6740 + }, + { + "epoch": 0.6035928143712574, + "grad_norm": 1.0862523658901713, + "learning_rate": 7.17078642431618e-06, + "loss": 0.8743, + "step": 6741 + }, + { + "epoch": 0.6036823549163356, + "grad_norm": 0.915870231184967, + "learning_rate": 7.1680047514823825e-06, + "loss": 0.8061, + "step": 6742 + }, + { + "epoch": 0.6037718954614136, + "grad_norm": 0.9560657262175546, + "learning_rate": 7.165223316866798e-06, + "loss": 0.8323, + "step": 6743 + }, + { + "epoch": 0.6038614360064917, + "grad_norm": 0.8920262930261265, + "learning_rate": 7.16244212070339e-06, + "loss": 0.8416, + "step": 6744 + }, + { + "epoch": 0.6039509765515697, + "grad_norm": 1.08993823761268, + "learning_rate": 7.159661163226104e-06, + "loss": 0.8375, + "step": 6745 + }, + { + "epoch": 0.6040405170966479, + "grad_norm": 0.8851160925570674, + "learning_rate": 7.1568804446688645e-06, + "loss": 0.8261, + "step": 6746 + }, + { + "epoch": 0.6041300576417259, + "grad_norm": 1.011993412186414, + "learning_rate": 7.154099965265575e-06, + "loss": 0.8684, + "step": 6747 + }, + { + "epoch": 0.6042195981868039, + "grad_norm": 1.023509137951365, + "learning_rate": 7.1513197252501245e-06, + "loss": 0.8432, + "step": 6748 + }, + { + "epoch": 0.6043091387318821, + "grad_norm": 0.8692464832146128, + "learning_rate": 7.148539724856378e-06, + "loss": 0.8312, + "step": 6749 + }, + { + "epoch": 0.6043986792769601, + "grad_norm": 1.0411707740387286, + "learning_rate": 7.1457599643181755e-06, + "loss": 0.7863, + "step": 6750 + }, + { + "epoch": 0.6044882198220382, + "grad_norm": 0.9524598571762559, + "learning_rate": 7.1429804438693425e-06, + "loss": 0.8633, + "step": 6751 + }, + { + "epoch": 0.6045777603671162, + "grad_norm": 1.0453501650349868, + "learning_rate": 7.140201163743686e-06, + "loss": 0.8619, + "step": 6752 + }, + { + "epoch": 0.6046673009121943, + "grad_norm": 1.0209115641420439, + "learning_rate": 7.137422124174987e-06, + "loss": 0.7627, + "step": 6753 + }, + { + "epoch": 0.6047568414572724, + "grad_norm": 0.9259015777856562, + "learning_rate": 7.134643325397015e-06, + "loss": 0.8034, + "step": 6754 + }, + { + "epoch": 0.6048463820023504, + "grad_norm": 0.9958054353112362, + "learning_rate": 7.131864767643506e-06, + "loss": 0.8359, + "step": 6755 + }, + { + "epoch": 0.6049359225474286, + "grad_norm": 1.1006165283885907, + "learning_rate": 7.1290864511481835e-06, + "loss": 0.8368, + "step": 6756 + }, + { + "epoch": 0.6050254630925066, + "grad_norm": 0.9276107694961492, + "learning_rate": 7.126308376144756e-06, + "loss": 0.8007, + "step": 6757 + }, + { + "epoch": 0.6051150036375846, + "grad_norm": 0.9314082658021962, + "learning_rate": 7.123530542866903e-06, + "loss": 0.7508, + "step": 6758 + }, + { + "epoch": 0.6052045441826627, + "grad_norm": 0.90920871652135, + "learning_rate": 7.120752951548288e-06, + "loss": 0.767, + "step": 6759 + }, + { + "epoch": 0.6052940847277408, + "grad_norm": 0.9170420341977984, + "learning_rate": 7.117975602422553e-06, + "loss": 0.8014, + "step": 6760 + }, + { + "epoch": 0.6053836252728189, + "grad_norm": 1.0240022312453534, + "learning_rate": 7.115198495723318e-06, + "loss": 0.8117, + "step": 6761 + }, + { + "epoch": 0.6054731658178969, + "grad_norm": 1.0977739438037732, + "learning_rate": 7.112421631684181e-06, + "loss": 0.7939, + "step": 6762 + }, + { + "epoch": 0.6055627063629749, + "grad_norm": 0.9642488022003376, + "learning_rate": 7.109645010538731e-06, + "loss": 0.8088, + "step": 6763 + }, + { + "epoch": 0.6056522469080531, + "grad_norm": 1.2631811723370763, + "learning_rate": 7.1068686325205215e-06, + "loss": 0.8691, + "step": 6764 + }, + { + "epoch": 0.6057417874531311, + "grad_norm": 1.1660910060559508, + "learning_rate": 7.1040924978630974e-06, + "loss": 0.83, + "step": 6765 + }, + { + "epoch": 0.6058313279982092, + "grad_norm": 0.8817320401313201, + "learning_rate": 7.101316606799975e-06, + "loss": 0.7924, + "step": 6766 + }, + { + "epoch": 0.6059208685432873, + "grad_norm": 0.8621917735252521, + "learning_rate": 7.0985409595646516e-06, + "loss": 0.8496, + "step": 6767 + }, + { + "epoch": 0.6060104090883653, + "grad_norm": 1.007124592022082, + "learning_rate": 7.095765556390606e-06, + "loss": 0.7731, + "step": 6768 + }, + { + "epoch": 0.6060999496334434, + "grad_norm": 0.9238102356886433, + "learning_rate": 7.092990397511302e-06, + "loss": 0.8181, + "step": 6769 + }, + { + "epoch": 0.6061894901785214, + "grad_norm": 0.8927284417962302, + "learning_rate": 7.0902154831601695e-06, + "loss": 0.8173, + "step": 6770 + }, + { + "epoch": 0.6062790307235996, + "grad_norm": 0.8856362681732389, + "learning_rate": 7.0874408135706315e-06, + "loss": 0.8478, + "step": 6771 + }, + { + "epoch": 0.6063685712686776, + "grad_norm": 0.9438029066016451, + "learning_rate": 7.084666388976081e-06, + "loss": 0.8193, + "step": 6772 + }, + { + "epoch": 0.6064581118137556, + "grad_norm": 0.9010187440439678, + "learning_rate": 7.081892209609892e-06, + "loss": 0.8461, + "step": 6773 + }, + { + "epoch": 0.6065476523588338, + "grad_norm": 0.9354921288894348, + "learning_rate": 7.079118275705419e-06, + "loss": 0.8001, + "step": 6774 + }, + { + "epoch": 0.6066371929039118, + "grad_norm": 0.9493644420823326, + "learning_rate": 7.076344587496e-06, + "loss": 0.8738, + "step": 6775 + }, + { + "epoch": 0.6067267334489899, + "grad_norm": 0.9167574995660371, + "learning_rate": 7.07357114521495e-06, + "loss": 0.7922, + "step": 6776 + }, + { + "epoch": 0.6068162739940679, + "grad_norm": 0.8692298853313202, + "learning_rate": 7.070797949095556e-06, + "loss": 0.7489, + "step": 6777 + }, + { + "epoch": 0.606905814539146, + "grad_norm": 0.9053380214298313, + "learning_rate": 7.068024999371095e-06, + "loss": 0.8285, + "step": 6778 + }, + { + "epoch": 0.6069953550842241, + "grad_norm": 0.9330431833163727, + "learning_rate": 7.065252296274814e-06, + "loss": 0.8005, + "step": 6779 + }, + { + "epoch": 0.6070848956293021, + "grad_norm": 0.9705059825484632, + "learning_rate": 7.062479840039946e-06, + "loss": 0.7986, + "step": 6780 + }, + { + "epoch": 0.6071744361743802, + "grad_norm": 0.9705909190178027, + "learning_rate": 7.0597076308997034e-06, + "loss": 0.8111, + "step": 6781 + }, + { + "epoch": 0.6072639767194583, + "grad_norm": 1.0309824194669222, + "learning_rate": 7.056935669087277e-06, + "loss": 0.7869, + "step": 6782 + }, + { + "epoch": 0.6073535172645363, + "grad_norm": 0.894120548259424, + "learning_rate": 7.054163954835825e-06, + "loss": 0.786, + "step": 6783 + }, + { + "epoch": 0.6074430578096144, + "grad_norm": 1.061238307142784, + "learning_rate": 7.051392488378503e-06, + "loss": 0.8015, + "step": 6784 + }, + { + "epoch": 0.6075325983546925, + "grad_norm": 0.9501622634075337, + "learning_rate": 7.048621269948438e-06, + "loss": 0.802, + "step": 6785 + }, + { + "epoch": 0.6076221388997706, + "grad_norm": 0.9168641198693591, + "learning_rate": 7.045850299778733e-06, + "loss": 0.8194, + "step": 6786 + }, + { + "epoch": 0.6077116794448486, + "grad_norm": 1.0918858102785411, + "learning_rate": 7.043079578102476e-06, + "loss": 0.8045, + "step": 6787 + }, + { + "epoch": 0.6078012199899266, + "grad_norm": 1.0672341869298139, + "learning_rate": 7.040309105152728e-06, + "loss": 0.8329, + "step": 6788 + }, + { + "epoch": 0.6078907605350048, + "grad_norm": 0.8444411628893715, + "learning_rate": 7.037538881162531e-06, + "loss": 0.7769, + "step": 6789 + }, + { + "epoch": 0.6079803010800828, + "grad_norm": 0.8758887890100214, + "learning_rate": 7.034768906364912e-06, + "loss": 0.7843, + "step": 6790 + }, + { + "epoch": 0.6080698416251609, + "grad_norm": 1.00796442573516, + "learning_rate": 7.031999180992868e-06, + "loss": 0.84, + "step": 6791 + }, + { + "epoch": 0.608159382170239, + "grad_norm": 0.927288135364999, + "learning_rate": 7.029229705279384e-06, + "loss": 0.8348, + "step": 6792 + }, + { + "epoch": 0.608248922715317, + "grad_norm": 0.9054651493961807, + "learning_rate": 7.0264604794574155e-06, + "loss": 0.8286, + "step": 6793 + }, + { + "epoch": 0.6083384632603951, + "grad_norm": 1.0511370499245034, + "learning_rate": 7.023691503759901e-06, + "loss": 0.8012, + "step": 6794 + }, + { + "epoch": 0.6084280038054731, + "grad_norm": 1.0075045636977054, + "learning_rate": 7.020922778419755e-06, + "loss": 0.8358, + "step": 6795 + }, + { + "epoch": 0.6085175443505513, + "grad_norm": 1.0738314469363892, + "learning_rate": 7.018154303669879e-06, + "loss": 0.8208, + "step": 6796 + }, + { + "epoch": 0.6086070848956293, + "grad_norm": 0.8992154147552629, + "learning_rate": 7.015386079743148e-06, + "loss": 0.7973, + "step": 6797 + }, + { + "epoch": 0.6086966254407074, + "grad_norm": 0.9265629519323908, + "learning_rate": 7.012618106872415e-06, + "loss": 0.84, + "step": 6798 + }, + { + "epoch": 0.6087861659857854, + "grad_norm": 1.0174308741519702, + "learning_rate": 7.009850385290511e-06, + "loss": 0.8086, + "step": 6799 + }, + { + "epoch": 0.6088757065308635, + "grad_norm": 1.0137765206719926, + "learning_rate": 7.007082915230247e-06, + "loss": 0.8352, + "step": 6800 + }, + { + "epoch": 0.6089652470759416, + "grad_norm": 0.9447487626276228, + "learning_rate": 7.004315696924413e-06, + "loss": 0.8178, + "step": 6801 + }, + { + "epoch": 0.6090547876210196, + "grad_norm": 1.106207788450664, + "learning_rate": 7.001548730605783e-06, + "loss": 0.8438, + "step": 6802 + }, + { + "epoch": 0.6091443281660978, + "grad_norm": 0.9621839841777069, + "learning_rate": 6.998782016507104e-06, + "loss": 0.7925, + "step": 6803 + }, + { + "epoch": 0.6092338687111758, + "grad_norm": 1.0749028365733964, + "learning_rate": 6.996015554861101e-06, + "loss": 0.8665, + "step": 6804 + }, + { + "epoch": 0.6093234092562538, + "grad_norm": 0.9405063950600747, + "learning_rate": 6.993249345900479e-06, + "loss": 0.8319, + "step": 6805 + }, + { + "epoch": 0.6094129498013319, + "grad_norm": 0.9909146378814356, + "learning_rate": 6.990483389857925e-06, + "loss": 0.8145, + "step": 6806 + }, + { + "epoch": 0.60950249034641, + "grad_norm": 1.0268234825413491, + "learning_rate": 6.9877176869661e-06, + "loss": 0.8364, + "step": 6807 + }, + { + "epoch": 0.6095920308914881, + "grad_norm": 0.8998589348804009, + "learning_rate": 6.984952237457647e-06, + "loss": 0.8524, + "step": 6808 + }, + { + "epoch": 0.6096815714365661, + "grad_norm": 1.1473573138804667, + "learning_rate": 6.982187041565192e-06, + "loss": 0.81, + "step": 6809 + }, + { + "epoch": 0.6097711119816442, + "grad_norm": 1.1503370653504872, + "learning_rate": 6.979422099521323e-06, + "loss": 0.8473, + "step": 6810 + }, + { + "epoch": 0.6098606525267223, + "grad_norm": 0.9821407158543782, + "learning_rate": 6.976657411558625e-06, + "loss": 0.8077, + "step": 6811 + }, + { + "epoch": 0.6099501930718003, + "grad_norm": 0.9133375862379889, + "learning_rate": 6.973892977909653e-06, + "loss": 0.8041, + "step": 6812 + }, + { + "epoch": 0.6100397336168784, + "grad_norm": 0.8861377590588402, + "learning_rate": 6.971128798806943e-06, + "loss": 0.8148, + "step": 6813 + }, + { + "epoch": 0.6101292741619565, + "grad_norm": 1.0944972378656204, + "learning_rate": 6.9683648744830116e-06, + "loss": 0.7876, + "step": 6814 + }, + { + "epoch": 0.6102188147070345, + "grad_norm": 0.9495173848486047, + "learning_rate": 6.965601205170345e-06, + "loss": 0.804, + "step": 6815 + }, + { + "epoch": 0.6103083552521126, + "grad_norm": 0.8498113193007459, + "learning_rate": 6.962837791101414e-06, + "loss": 0.7816, + "step": 6816 + }, + { + "epoch": 0.6103978957971906, + "grad_norm": 1.1359905441985596, + "learning_rate": 6.960074632508672e-06, + "loss": 0.8681, + "step": 6817 + }, + { + "epoch": 0.6104874363422688, + "grad_norm": 1.006355382225876, + "learning_rate": 6.957311729624547e-06, + "loss": 0.8191, + "step": 6818 + }, + { + "epoch": 0.6105769768873468, + "grad_norm": 0.9260517455408065, + "learning_rate": 6.954549082681444e-06, + "loss": 0.8607, + "step": 6819 + }, + { + "epoch": 0.6106665174324248, + "grad_norm": 0.9079865484712613, + "learning_rate": 6.951786691911751e-06, + "loss": 0.8036, + "step": 6820 + }, + { + "epoch": 0.610756057977503, + "grad_norm": 1.034135095062518, + "learning_rate": 6.949024557547824e-06, + "loss": 0.7989, + "step": 6821 + }, + { + "epoch": 0.610845598522581, + "grad_norm": 1.0030756502315685, + "learning_rate": 6.946262679822009e-06, + "loss": 0.8914, + "step": 6822 + }, + { + "epoch": 0.6109351390676591, + "grad_norm": 0.9761653421831348, + "learning_rate": 6.943501058966626e-06, + "loss": 0.7915, + "step": 6823 + }, + { + "epoch": 0.6110246796127371, + "grad_norm": 0.9606151087322252, + "learning_rate": 6.940739695213976e-06, + "loss": 0.8313, + "step": 6824 + }, + { + "epoch": 0.6111142201578152, + "grad_norm": 1.0641970251505146, + "learning_rate": 6.937978588796335e-06, + "loss": 0.8613, + "step": 6825 + }, + { + "epoch": 0.6112037607028933, + "grad_norm": 0.897624345628596, + "learning_rate": 6.935217739945954e-06, + "loss": 0.8119, + "step": 6826 + }, + { + "epoch": 0.6112933012479713, + "grad_norm": 0.9068447837199171, + "learning_rate": 6.93245714889507e-06, + "loss": 0.7537, + "step": 6827 + }, + { + "epoch": 0.6113828417930495, + "grad_norm": 0.9847564102035016, + "learning_rate": 6.929696815875893e-06, + "loss": 0.8914, + "step": 6828 + }, + { + "epoch": 0.6114723823381275, + "grad_norm": 0.9371524659151274, + "learning_rate": 6.926936741120616e-06, + "loss": 0.8237, + "step": 6829 + }, + { + "epoch": 0.6115619228832055, + "grad_norm": 0.9829707351498234, + "learning_rate": 6.924176924861406e-06, + "loss": 0.8489, + "step": 6830 + }, + { + "epoch": 0.6116514634282836, + "grad_norm": 1.0620218793538247, + "learning_rate": 6.921417367330412e-06, + "loss": 0.8163, + "step": 6831 + }, + { + "epoch": 0.6117410039733617, + "grad_norm": 0.8732960722186752, + "learning_rate": 6.918658068759754e-06, + "loss": 0.8437, + "step": 6832 + }, + { + "epoch": 0.6118305445184398, + "grad_norm": 0.9062623961789811, + "learning_rate": 6.915899029381538e-06, + "loss": 0.8509, + "step": 6833 + }, + { + "epoch": 0.6119200850635178, + "grad_norm": 0.9963413592763147, + "learning_rate": 6.913140249427845e-06, + "loss": 0.837, + "step": 6834 + }, + { + "epoch": 0.6120096256085958, + "grad_norm": 0.9275059773347846, + "learning_rate": 6.910381729130737e-06, + "loss": 0.8363, + "step": 6835 + }, + { + "epoch": 0.612099166153674, + "grad_norm": 0.9880189286796315, + "learning_rate": 6.907623468722253e-06, + "loss": 0.8114, + "step": 6836 + }, + { + "epoch": 0.612188706698752, + "grad_norm": 0.903996391206342, + "learning_rate": 6.904865468434401e-06, + "loss": 0.8347, + "step": 6837 + }, + { + "epoch": 0.6122782472438301, + "grad_norm": 0.9311166715580739, + "learning_rate": 6.902107728499181e-06, + "loss": 0.8201, + "step": 6838 + }, + { + "epoch": 0.6123677877889082, + "grad_norm": 0.9216111817813706, + "learning_rate": 6.8993502491485635e-06, + "loss": 0.804, + "step": 6839 + }, + { + "epoch": 0.6124573283339863, + "grad_norm": 0.9836808978254274, + "learning_rate": 6.8965930306144975e-06, + "loss": 0.7938, + "step": 6840 + }, + { + "epoch": 0.6125468688790643, + "grad_norm": 0.8504655980054405, + "learning_rate": 6.893836073128912e-06, + "loss": 0.8331, + "step": 6841 + }, + { + "epoch": 0.6126364094241423, + "grad_norm": 0.966529725792513, + "learning_rate": 6.891079376923721e-06, + "loss": 0.8053, + "step": 6842 + }, + { + "epoch": 0.6127259499692205, + "grad_norm": 1.0052820061933097, + "learning_rate": 6.888322942230794e-06, + "loss": 0.819, + "step": 6843 + }, + { + "epoch": 0.6128154905142985, + "grad_norm": 1.320637517223321, + "learning_rate": 6.885566769282004e-06, + "loss": 0.8844, + "step": 6844 + }, + { + "epoch": 0.6129050310593765, + "grad_norm": 0.8889108577666743, + "learning_rate": 6.882810858309188e-06, + "loss": 0.8173, + "step": 6845 + }, + { + "epoch": 0.6129945716044547, + "grad_norm": 1.2271222308017888, + "learning_rate": 6.880055209544165e-06, + "loss": 0.7767, + "step": 6846 + }, + { + "epoch": 0.6130841121495327, + "grad_norm": 0.8886368236160457, + "learning_rate": 6.877299823218733e-06, + "loss": 0.8327, + "step": 6847 + }, + { + "epoch": 0.6131736526946108, + "grad_norm": 0.9217922255684089, + "learning_rate": 6.874544699564662e-06, + "loss": 0.8394, + "step": 6848 + }, + { + "epoch": 0.6132631932396888, + "grad_norm": 0.9485812158502913, + "learning_rate": 6.871789838813703e-06, + "loss": 0.8189, + "step": 6849 + }, + { + "epoch": 0.613352733784767, + "grad_norm": 0.9502680072342772, + "learning_rate": 6.869035241197592e-06, + "loss": 0.8269, + "step": 6850 + }, + { + "epoch": 0.613442274329845, + "grad_norm": 0.9642240807913821, + "learning_rate": 6.866280906948033e-06, + "loss": 0.8582, + "step": 6851 + }, + { + "epoch": 0.613531814874923, + "grad_norm": 0.9286782234210027, + "learning_rate": 6.863526836296712e-06, + "loss": 0.8708, + "step": 6852 + }, + { + "epoch": 0.6136213554200011, + "grad_norm": 1.0352072759505886, + "learning_rate": 6.860773029475294e-06, + "loss": 0.8491, + "step": 6853 + }, + { + "epoch": 0.6137108959650792, + "grad_norm": 0.9466367146690194, + "learning_rate": 6.858019486715418e-06, + "loss": 0.846, + "step": 6854 + }, + { + "epoch": 0.6138004365101573, + "grad_norm": 1.2503195140129573, + "learning_rate": 6.855266208248702e-06, + "loss": 0.7971, + "step": 6855 + }, + { + "epoch": 0.6138899770552353, + "grad_norm": 1.0566208566015043, + "learning_rate": 6.852513194306747e-06, + "loss": 0.821, + "step": 6856 + }, + { + "epoch": 0.6139795176003134, + "grad_norm": 1.0060041063347442, + "learning_rate": 6.849760445121125e-06, + "loss": 0.7427, + "step": 6857 + }, + { + "epoch": 0.6140690581453915, + "grad_norm": 0.8554891426553833, + "learning_rate": 6.847007960923391e-06, + "loss": 0.8045, + "step": 6858 + }, + { + "epoch": 0.6141585986904695, + "grad_norm": 0.9598180820536625, + "learning_rate": 6.8442557419450695e-06, + "loss": 0.8775, + "step": 6859 + }, + { + "epoch": 0.6142481392355476, + "grad_norm": 1.1525574158109388, + "learning_rate": 6.841503788417671e-06, + "loss": 0.911, + "step": 6860 + }, + { + "epoch": 0.6143376797806257, + "grad_norm": 1.0095088867488953, + "learning_rate": 6.838752100572681e-06, + "loss": 0.8605, + "step": 6861 + }, + { + "epoch": 0.6144272203257037, + "grad_norm": 0.967964622099855, + "learning_rate": 6.836000678641564e-06, + "loss": 0.8147, + "step": 6862 + }, + { + "epoch": 0.6145167608707818, + "grad_norm": 0.9034640468361166, + "learning_rate": 6.833249522855761e-06, + "loss": 0.8441, + "step": 6863 + }, + { + "epoch": 0.6146063014158599, + "grad_norm": 1.1077748605927817, + "learning_rate": 6.8304986334466884e-06, + "loss": 0.7902, + "step": 6864 + }, + { + "epoch": 0.614695841960938, + "grad_norm": 0.9632528179217105, + "learning_rate": 6.827748010645741e-06, + "loss": 0.7862, + "step": 6865 + }, + { + "epoch": 0.614785382506016, + "grad_norm": 0.9939275199605824, + "learning_rate": 6.824997654684293e-06, + "loss": 0.7966, + "step": 6866 + }, + { + "epoch": 0.614874923051094, + "grad_norm": 0.865792451368466, + "learning_rate": 6.822247565793697e-06, + "loss": 0.8151, + "step": 6867 + }, + { + "epoch": 0.6149644635961722, + "grad_norm": 0.9642295863345405, + "learning_rate": 6.819497744205277e-06, + "loss": 0.7918, + "step": 6868 + }, + { + "epoch": 0.6150540041412502, + "grad_norm": 0.9643131661546134, + "learning_rate": 6.816748190150351e-06, + "loss": 0.7813, + "step": 6869 + }, + { + "epoch": 0.6151435446863283, + "grad_norm": 0.9927479306142228, + "learning_rate": 6.813998903860185e-06, + "loss": 0.8235, + "step": 6870 + }, + { + "epoch": 0.6152330852314063, + "grad_norm": 0.9502333299458386, + "learning_rate": 6.811249885566052e-06, + "loss": 0.8339, + "step": 6871 + }, + { + "epoch": 0.6153226257764844, + "grad_norm": 1.013974031261673, + "learning_rate": 6.808501135499188e-06, + "loss": 0.8522, + "step": 6872 + }, + { + "epoch": 0.6154121663215625, + "grad_norm": 0.9717613484258886, + "learning_rate": 6.805752653890808e-06, + "loss": 0.836, + "step": 6873 + }, + { + "epoch": 0.6155017068666405, + "grad_norm": 0.9318239743237516, + "learning_rate": 6.8030044409721075e-06, + "loss": 0.8409, + "step": 6874 + }, + { + "epoch": 0.6155912474117187, + "grad_norm": 0.933077348792681, + "learning_rate": 6.8002564969742536e-06, + "loss": 0.83, + "step": 6875 + }, + { + "epoch": 0.6156807879567967, + "grad_norm": 1.017866329656441, + "learning_rate": 6.797508822128394e-06, + "loss": 0.8314, + "step": 6876 + }, + { + "epoch": 0.6157703285018747, + "grad_norm": 0.8392712677159732, + "learning_rate": 6.794761416665658e-06, + "loss": 0.8175, + "step": 6877 + }, + { + "epoch": 0.6158598690469528, + "grad_norm": 0.9751822042556472, + "learning_rate": 6.792014280817148e-06, + "loss": 0.7722, + "step": 6878 + }, + { + "epoch": 0.6159494095920309, + "grad_norm": 0.9200636083122777, + "learning_rate": 6.789267414813941e-06, + "loss": 0.7774, + "step": 6879 + }, + { + "epoch": 0.616038950137109, + "grad_norm": 0.926848633195427, + "learning_rate": 6.786520818887099e-06, + "loss": 0.7998, + "step": 6880 + }, + { + "epoch": 0.616128490682187, + "grad_norm": 0.8968750644806187, + "learning_rate": 6.783774493267652e-06, + "loss": 0.8031, + "step": 6881 + }, + { + "epoch": 0.6162180312272652, + "grad_norm": 1.0149494608617347, + "learning_rate": 6.781028438186612e-06, + "loss": 0.8453, + "step": 6882 + }, + { + "epoch": 0.6163075717723432, + "grad_norm": 0.9959631115275402, + "learning_rate": 6.778282653874973e-06, + "loss": 0.8398, + "step": 6883 + }, + { + "epoch": 0.6163971123174212, + "grad_norm": 1.0214234469190036, + "learning_rate": 6.775537140563697e-06, + "loss": 0.8105, + "step": 6884 + }, + { + "epoch": 0.6164866528624993, + "grad_norm": 1.1338735595503195, + "learning_rate": 6.772791898483733e-06, + "loss": 0.7981, + "step": 6885 + }, + { + "epoch": 0.6165761934075774, + "grad_norm": 1.1192560690531386, + "learning_rate": 6.770046927865994e-06, + "loss": 0.8236, + "step": 6886 + }, + { + "epoch": 0.6166657339526554, + "grad_norm": 0.9651837968638589, + "learning_rate": 6.767302228941383e-06, + "loss": 0.8426, + "step": 6887 + }, + { + "epoch": 0.6167552744977335, + "grad_norm": 1.0193860652520395, + "learning_rate": 6.764557801940771e-06, + "loss": 0.8396, + "step": 6888 + }, + { + "epoch": 0.6168448150428115, + "grad_norm": 0.9589074193360166, + "learning_rate": 6.761813647095017e-06, + "loss": 0.7701, + "step": 6889 + }, + { + "epoch": 0.6169343555878897, + "grad_norm": 0.869034794592788, + "learning_rate": 6.759069764634945e-06, + "loss": 0.8201, + "step": 6890 + }, + { + "epoch": 0.6170238961329677, + "grad_norm": 1.0762124881577682, + "learning_rate": 6.756326154791366e-06, + "loss": 0.8426, + "step": 6891 + }, + { + "epoch": 0.6171134366780457, + "grad_norm": 0.9141353749945169, + "learning_rate": 6.753582817795059e-06, + "loss": 0.7611, + "step": 6892 + }, + { + "epoch": 0.6172029772231239, + "grad_norm": 1.0150873853170288, + "learning_rate": 6.750839753876785e-06, + "loss": 0.8231, + "step": 6893 + }, + { + "epoch": 0.6172925177682019, + "grad_norm": 0.9834024375726643, + "learning_rate": 6.748096963267285e-06, + "loss": 0.7864, + "step": 6894 + }, + { + "epoch": 0.61738205831328, + "grad_norm": 1.0855608962192123, + "learning_rate": 6.745354446197267e-06, + "loss": 0.8113, + "step": 6895 + }, + { + "epoch": 0.617471598858358, + "grad_norm": 0.9414822700422412, + "learning_rate": 6.742612202897436e-06, + "loss": 0.8109, + "step": 6896 + }, + { + "epoch": 0.6175611394034362, + "grad_norm": 0.9680316424205204, + "learning_rate": 6.7398702335984436e-06, + "loss": 0.8829, + "step": 6897 + }, + { + "epoch": 0.6176506799485142, + "grad_norm": 1.0812810028008988, + "learning_rate": 6.737128538530946e-06, + "loss": 0.8583, + "step": 6898 + }, + { + "epoch": 0.6177402204935922, + "grad_norm": 1.0590551586059418, + "learning_rate": 6.734387117925562e-06, + "loss": 0.8877, + "step": 6899 + }, + { + "epoch": 0.6178297610386704, + "grad_norm": 0.979256916353065, + "learning_rate": 6.731645972012892e-06, + "loss": 0.8201, + "step": 6900 + }, + { + "epoch": 0.6179193015837484, + "grad_norm": 1.0382208878098076, + "learning_rate": 6.728905101023512e-06, + "loss": 0.7922, + "step": 6901 + }, + { + "epoch": 0.6180088421288265, + "grad_norm": 1.1022771248009708, + "learning_rate": 6.72616450518798e-06, + "loss": 0.8799, + "step": 6902 + }, + { + "epoch": 0.6180983826739045, + "grad_norm": 0.9648599272837541, + "learning_rate": 6.723424184736816e-06, + "loss": 0.8403, + "step": 6903 + }, + { + "epoch": 0.6181879232189826, + "grad_norm": 0.9387292978873782, + "learning_rate": 6.720684139900534e-06, + "loss": 0.777, + "step": 6904 + }, + { + "epoch": 0.6182774637640607, + "grad_norm": 0.9265779630393162, + "learning_rate": 6.717944370909616e-06, + "loss": 0.7941, + "step": 6905 + }, + { + "epoch": 0.6183670043091387, + "grad_norm": 0.9676528923748605, + "learning_rate": 6.715204877994521e-06, + "loss": 0.7885, + "step": 6906 + }, + { + "epoch": 0.6184565448542167, + "grad_norm": 0.976180815737479, + "learning_rate": 6.712465661385692e-06, + "loss": 0.8423, + "step": 6907 + }, + { + "epoch": 0.6185460853992949, + "grad_norm": 0.9178080878821915, + "learning_rate": 6.7097267213135345e-06, + "loss": 0.856, + "step": 6908 + }, + { + "epoch": 0.6186356259443729, + "grad_norm": 0.9602544438249079, + "learning_rate": 6.7069880580084415e-06, + "loss": 0.8349, + "step": 6909 + }, + { + "epoch": 0.618725166489451, + "grad_norm": 1.0568022353132074, + "learning_rate": 6.704249671700785e-06, + "loss": 0.8378, + "step": 6910 + }, + { + "epoch": 0.6188147070345291, + "grad_norm": 0.980577698820659, + "learning_rate": 6.7015115626209035e-06, + "loss": 0.7735, + "step": 6911 + }, + { + "epoch": 0.6189042475796072, + "grad_norm": 0.9636637853010859, + "learning_rate": 6.698773730999124e-06, + "loss": 0.8016, + "step": 6912 + }, + { + "epoch": 0.6189937881246852, + "grad_norm": 1.017534359227623, + "learning_rate": 6.696036177065741e-06, + "loss": 0.8146, + "step": 6913 + }, + { + "epoch": 0.6190833286697632, + "grad_norm": 0.8993718344330415, + "learning_rate": 6.693298901051026e-06, + "loss": 0.7568, + "step": 6914 + }, + { + "epoch": 0.6191728692148414, + "grad_norm": 0.9688416220533915, + "learning_rate": 6.6905619031852295e-06, + "loss": 0.8061, + "step": 6915 + }, + { + "epoch": 0.6192624097599194, + "grad_norm": 0.8858830956937263, + "learning_rate": 6.687825183698584e-06, + "loss": 0.814, + "step": 6916 + }, + { + "epoch": 0.6193519503049975, + "grad_norm": 0.9819610668615756, + "learning_rate": 6.6850887428212905e-06, + "loss": 0.8299, + "step": 6917 + }, + { + "epoch": 0.6194414908500756, + "grad_norm": 0.9661020088389787, + "learning_rate": 6.682352580783531e-06, + "loss": 0.7784, + "step": 6918 + }, + { + "epoch": 0.6195310313951536, + "grad_norm": 0.9307415978375252, + "learning_rate": 6.679616697815461e-06, + "loss": 0.8198, + "step": 6919 + }, + { + "epoch": 0.6196205719402317, + "grad_norm": 0.9326523306181576, + "learning_rate": 6.6768810941472116e-06, + "loss": 0.8397, + "step": 6920 + }, + { + "epoch": 0.6197101124853097, + "grad_norm": 0.9229164439507436, + "learning_rate": 6.674145770008897e-06, + "loss": 0.8311, + "step": 6921 + }, + { + "epoch": 0.6197996530303879, + "grad_norm": 0.9913502736986972, + "learning_rate": 6.671410725630601e-06, + "loss": 0.8489, + "step": 6922 + }, + { + "epoch": 0.6198891935754659, + "grad_norm": 0.9688240168021084, + "learning_rate": 6.668675961242389e-06, + "loss": 0.8363, + "step": 6923 + }, + { + "epoch": 0.6199787341205439, + "grad_norm": 1.1158828057836605, + "learning_rate": 6.665941477074301e-06, + "loss": 0.7921, + "step": 6924 + }, + { + "epoch": 0.620068274665622, + "grad_norm": 0.9509261521658446, + "learning_rate": 6.663207273356351e-06, + "loss": 0.8568, + "step": 6925 + }, + { + "epoch": 0.6201578152107001, + "grad_norm": 0.8768836420587605, + "learning_rate": 6.660473350318529e-06, + "loss": 0.8369, + "step": 6926 + }, + { + "epoch": 0.6202473557557782, + "grad_norm": 1.2551258932128715, + "learning_rate": 6.657739708190807e-06, + "loss": 0.7632, + "step": 6927 + }, + { + "epoch": 0.6203368963008562, + "grad_norm": 0.9901217755491433, + "learning_rate": 6.655006347203128e-06, + "loss": 0.7513, + "step": 6928 + }, + { + "epoch": 0.6204264368459343, + "grad_norm": 1.0833368989169174, + "learning_rate": 6.65227326758542e-06, + "loss": 0.8451, + "step": 6929 + }, + { + "epoch": 0.6205159773910124, + "grad_norm": 0.9589829133918134, + "learning_rate": 6.64954046956757e-06, + "loss": 0.8637, + "step": 6930 + }, + { + "epoch": 0.6206055179360904, + "grad_norm": 0.9133983633630999, + "learning_rate": 6.64680795337946e-06, + "loss": 0.8165, + "step": 6931 + }, + { + "epoch": 0.6206950584811685, + "grad_norm": 0.9470503976085424, + "learning_rate": 6.644075719250938e-06, + "loss": 0.7981, + "step": 6932 + }, + { + "epoch": 0.6207845990262466, + "grad_norm": 0.9474078496994895, + "learning_rate": 6.6413437674118294e-06, + "loss": 0.8313, + "step": 6933 + }, + { + "epoch": 0.6208741395713246, + "grad_norm": 0.9600453895542121, + "learning_rate": 6.638612098091937e-06, + "loss": 0.7844, + "step": 6934 + }, + { + "epoch": 0.6209636801164027, + "grad_norm": 1.0466134362250887, + "learning_rate": 6.635880711521047e-06, + "loss": 0.833, + "step": 6935 + }, + { + "epoch": 0.6210532206614808, + "grad_norm": 0.9306107934701259, + "learning_rate": 6.633149607928901e-06, + "loss": 0.808, + "step": 6936 + }, + { + "epoch": 0.6211427612065589, + "grad_norm": 0.9945883448958968, + "learning_rate": 6.630418787545243e-06, + "loss": 0.8369, + "step": 6937 + }, + { + "epoch": 0.6212323017516369, + "grad_norm": 0.9763299397349428, + "learning_rate": 6.627688250599775e-06, + "loss": 0.7748, + "step": 6938 + }, + { + "epoch": 0.6213218422967149, + "grad_norm": 0.9357816321731504, + "learning_rate": 6.6249579973221835e-06, + "loss": 0.7637, + "step": 6939 + }, + { + "epoch": 0.6214113828417931, + "grad_norm": 0.9993866346409703, + "learning_rate": 6.622228027942128e-06, + "loss": 0.8251, + "step": 6940 + }, + { + "epoch": 0.6215009233868711, + "grad_norm": 0.8438082927325912, + "learning_rate": 6.619498342689241e-06, + "loss": 0.826, + "step": 6941 + }, + { + "epoch": 0.6215904639319492, + "grad_norm": 1.0756882144698472, + "learning_rate": 6.616768941793134e-06, + "loss": 0.8046, + "step": 6942 + }, + { + "epoch": 0.6216800044770272, + "grad_norm": 0.9174458383614348, + "learning_rate": 6.614039825483404e-06, + "loss": 0.7874, + "step": 6943 + }, + { + "epoch": 0.6217695450221054, + "grad_norm": 1.011929825062502, + "learning_rate": 6.611310993989608e-06, + "loss": 0.8627, + "step": 6944 + }, + { + "epoch": 0.6218590855671834, + "grad_norm": 0.9423977343702019, + "learning_rate": 6.608582447541292e-06, + "loss": 0.8992, + "step": 6945 + }, + { + "epoch": 0.6219486261122614, + "grad_norm": 1.011846296837944, + "learning_rate": 6.605854186367965e-06, + "loss": 0.8497, + "step": 6946 + }, + { + "epoch": 0.6220381666573396, + "grad_norm": 1.0506651538098284, + "learning_rate": 6.603126210699124e-06, + "loss": 0.8206, + "step": 6947 + }, + { + "epoch": 0.6221277072024176, + "grad_norm": 0.9285843562525606, + "learning_rate": 6.600398520764237e-06, + "loss": 0.8282, + "step": 6948 + }, + { + "epoch": 0.6222172477474956, + "grad_norm": 0.9607051754572172, + "learning_rate": 6.597671116792745e-06, + "loss": 0.8058, + "step": 6949 + }, + { + "epoch": 0.6223067882925737, + "grad_norm": 0.9890252866269129, + "learning_rate": 6.594943999014076e-06, + "loss": 0.8094, + "step": 6950 + }, + { + "epoch": 0.6223963288376518, + "grad_norm": 0.8990318309790466, + "learning_rate": 6.592217167657622e-06, + "loss": 0.8138, + "step": 6951 + }, + { + "epoch": 0.6224858693827299, + "grad_norm": 0.9081771484960499, + "learning_rate": 6.589490622952752e-06, + "loss": 0.7966, + "step": 6952 + }, + { + "epoch": 0.6225754099278079, + "grad_norm": 1.0070436836417715, + "learning_rate": 6.58676436512882e-06, + "loss": 0.7962, + "step": 6953 + }, + { + "epoch": 0.6226649504728861, + "grad_norm": 0.9720927437013402, + "learning_rate": 6.5840383944151445e-06, + "loss": 0.8819, + "step": 6954 + }, + { + "epoch": 0.6227544910179641, + "grad_norm": 1.0375517597490889, + "learning_rate": 6.581312711041026e-06, + "loss": 0.7754, + "step": 6955 + }, + { + "epoch": 0.6228440315630421, + "grad_norm": 1.0379279831505968, + "learning_rate": 6.578587315235747e-06, + "loss": 0.8557, + "step": 6956 + }, + { + "epoch": 0.6229335721081202, + "grad_norm": 0.9224595131341047, + "learning_rate": 6.57586220722855e-06, + "loss": 0.7874, + "step": 6957 + }, + { + "epoch": 0.6230231126531983, + "grad_norm": 0.9467945030732978, + "learning_rate": 6.573137387248665e-06, + "loss": 0.808, + "step": 6958 + }, + { + "epoch": 0.6231126531982764, + "grad_norm": 0.9282129015331446, + "learning_rate": 6.570412855525298e-06, + "loss": 0.8461, + "step": 6959 + }, + { + "epoch": 0.6232021937433544, + "grad_norm": 1.1037637998533718, + "learning_rate": 6.567688612287625e-06, + "loss": 0.8699, + "step": 6960 + }, + { + "epoch": 0.6232917342884324, + "grad_norm": 1.1526537444983902, + "learning_rate": 6.564964657764799e-06, + "loss": 0.8363, + "step": 6961 + }, + { + "epoch": 0.6233812748335106, + "grad_norm": 0.9879430777158691, + "learning_rate": 6.562240992185958e-06, + "loss": 0.8543, + "step": 6962 + }, + { + "epoch": 0.6234708153785886, + "grad_norm": 1.0523246735197505, + "learning_rate": 6.559517615780196e-06, + "loss": 0.8247, + "step": 6963 + }, + { + "epoch": 0.6235603559236667, + "grad_norm": 1.0222867303386085, + "learning_rate": 6.556794528776602e-06, + "loss": 0.8497, + "step": 6964 + }, + { + "epoch": 0.6236498964687448, + "grad_norm": 0.9675485034821362, + "learning_rate": 6.5540717314042335e-06, + "loss": 0.8109, + "step": 6965 + }, + { + "epoch": 0.6237394370138228, + "grad_norm": 1.0138915662654804, + "learning_rate": 6.55134922389212e-06, + "loss": 0.772, + "step": 6966 + }, + { + "epoch": 0.6238289775589009, + "grad_norm": 0.9169558364325726, + "learning_rate": 6.548627006469276e-06, + "loss": 0.7997, + "step": 6967 + }, + { + "epoch": 0.6239185181039789, + "grad_norm": 0.9635406898239307, + "learning_rate": 6.545905079364678e-06, + "loss": 0.8174, + "step": 6968 + }, + { + "epoch": 0.6240080586490571, + "grad_norm": 0.8759907940326553, + "learning_rate": 6.543183442807286e-06, + "loss": 0.794, + "step": 6969 + }, + { + "epoch": 0.6240975991941351, + "grad_norm": 1.0452357140960589, + "learning_rate": 6.5404620970260415e-06, + "loss": 0.7996, + "step": 6970 + }, + { + "epoch": 0.6241871397392131, + "grad_norm": 1.0831881655381301, + "learning_rate": 6.53774104224985e-06, + "loss": 0.8551, + "step": 6971 + }, + { + "epoch": 0.6242766802842913, + "grad_norm": 0.9401628630064085, + "learning_rate": 6.5350202787076e-06, + "loss": 0.8486, + "step": 6972 + }, + { + "epoch": 0.6243662208293693, + "grad_norm": 0.9214762040281522, + "learning_rate": 6.532299806628156e-06, + "loss": 0.8516, + "step": 6973 + }, + { + "epoch": 0.6244557613744474, + "grad_norm": 0.9372033980921437, + "learning_rate": 6.5295796262403495e-06, + "loss": 0.8612, + "step": 6974 + }, + { + "epoch": 0.6245453019195254, + "grad_norm": 0.9106012685365585, + "learning_rate": 6.526859737772996e-06, + "loss": 0.8402, + "step": 6975 + }, + { + "epoch": 0.6246348424646035, + "grad_norm": 1.1983038972864293, + "learning_rate": 6.524140141454881e-06, + "loss": 0.8196, + "step": 6976 + }, + { + "epoch": 0.6247243830096816, + "grad_norm": 0.9953063885433927, + "learning_rate": 6.5214208375147724e-06, + "loss": 0.8149, + "step": 6977 + }, + { + "epoch": 0.6248139235547596, + "grad_norm": 0.9980508760077046, + "learning_rate": 6.5187018261814095e-06, + "loss": 0.8176, + "step": 6978 + }, + { + "epoch": 0.6249034640998377, + "grad_norm": 1.0294898215156598, + "learning_rate": 6.515983107683504e-06, + "loss": 0.8245, + "step": 6979 + }, + { + "epoch": 0.6249930046449158, + "grad_norm": 0.9257275591198185, + "learning_rate": 6.513264682249742e-06, + "loss": 0.8562, + "step": 6980 + }, + { + "epoch": 0.6250825451899938, + "grad_norm": 0.9088170244784146, + "learning_rate": 6.510546550108796e-06, + "loss": 0.8124, + "step": 6981 + }, + { + "epoch": 0.6251720857350719, + "grad_norm": 0.9861942164958212, + "learning_rate": 6.5078287114893015e-06, + "loss": 0.7892, + "step": 6982 + }, + { + "epoch": 0.62526162628015, + "grad_norm": 1.058059275598195, + "learning_rate": 6.5051111666198755e-06, + "loss": 0.865, + "step": 6983 + }, + { + "epoch": 0.6253511668252281, + "grad_norm": 1.2328752780266363, + "learning_rate": 6.502393915729113e-06, + "loss": 0.8153, + "step": 6984 + }, + { + "epoch": 0.6254407073703061, + "grad_norm": 1.0939841326469963, + "learning_rate": 6.499676959045574e-06, + "loss": 0.8182, + "step": 6985 + }, + { + "epoch": 0.6255302479153841, + "grad_norm": 1.099747295072245, + "learning_rate": 6.496960296797803e-06, + "loss": 0.8017, + "step": 6986 + }, + { + "epoch": 0.6256197884604623, + "grad_norm": 1.0775712758955602, + "learning_rate": 6.494243929214316e-06, + "loss": 0.8652, + "step": 6987 + }, + { + "epoch": 0.6257093290055403, + "grad_norm": 0.9977971528439035, + "learning_rate": 6.491527856523604e-06, + "loss": 0.7569, + "step": 6988 + }, + { + "epoch": 0.6257988695506184, + "grad_norm": 0.8882053653961417, + "learning_rate": 6.488812078954142e-06, + "loss": 0.8828, + "step": 6989 + }, + { + "epoch": 0.6258884100956965, + "grad_norm": 0.9484766998567198, + "learning_rate": 6.486096596734359e-06, + "loss": 0.8026, + "step": 6990 + }, + { + "epoch": 0.6259779506407745, + "grad_norm": 0.8378392888188896, + "learning_rate": 6.483381410092682e-06, + "loss": 0.7673, + "step": 6991 + }, + { + "epoch": 0.6260674911858526, + "grad_norm": 1.096451967419823, + "learning_rate": 6.480666519257501e-06, + "loss": 0.7578, + "step": 6992 + }, + { + "epoch": 0.6261570317309306, + "grad_norm": 0.9486263979420991, + "learning_rate": 6.4779519244571845e-06, + "loss": 0.8699, + "step": 6993 + }, + { + "epoch": 0.6262465722760088, + "grad_norm": 0.8086644362649459, + "learning_rate": 6.4752376259200725e-06, + "loss": 0.7386, + "step": 6994 + }, + { + "epoch": 0.6263361128210868, + "grad_norm": 1.001818834213824, + "learning_rate": 6.472523623874491e-06, + "loss": 0.857, + "step": 6995 + }, + { + "epoch": 0.6264256533661648, + "grad_norm": 0.9435270729308571, + "learning_rate": 6.4698099185487216e-06, + "loss": 0.792, + "step": 6996 + }, + { + "epoch": 0.6265151939112429, + "grad_norm": 0.9544299872650338, + "learning_rate": 6.467096510171039e-06, + "loss": 0.8109, + "step": 6997 + }, + { + "epoch": 0.626604734456321, + "grad_norm": 1.0097359641564345, + "learning_rate": 6.464383398969687e-06, + "loss": 0.7991, + "step": 6998 + }, + { + "epoch": 0.6266942750013991, + "grad_norm": 0.8577228621325402, + "learning_rate": 6.461670585172881e-06, + "loss": 0.8297, + "step": 6999 + }, + { + "epoch": 0.6267838155464771, + "grad_norm": 0.9322767207522131, + "learning_rate": 6.458958069008816e-06, + "loss": 0.7479, + "step": 7000 + }, + { + "epoch": 0.6268733560915553, + "grad_norm": 0.8817747808095097, + "learning_rate": 6.456245850705658e-06, + "loss": 0.8036, + "step": 7001 + }, + { + "epoch": 0.6269628966366333, + "grad_norm": 1.0804966438465284, + "learning_rate": 6.453533930491551e-06, + "loss": 0.8275, + "step": 7002 + }, + { + "epoch": 0.6270524371817113, + "grad_norm": 0.9639257986317283, + "learning_rate": 6.4508223085946105e-06, + "loss": 0.8324, + "step": 7003 + }, + { + "epoch": 0.6271419777267894, + "grad_norm": 1.0462596674159441, + "learning_rate": 6.448110985242935e-06, + "loss": 0.74, + "step": 7004 + }, + { + "epoch": 0.6272315182718675, + "grad_norm": 0.8968321892284347, + "learning_rate": 6.44539996066459e-06, + "loss": 0.7746, + "step": 7005 + }, + { + "epoch": 0.6273210588169456, + "grad_norm": 0.9274040059790555, + "learning_rate": 6.442689235087615e-06, + "loss": 0.7564, + "step": 7006 + }, + { + "epoch": 0.6274105993620236, + "grad_norm": 0.9702677854887344, + "learning_rate": 6.4399788087400285e-06, + "loss": 0.8232, + "step": 7007 + }, + { + "epoch": 0.6275001399071017, + "grad_norm": 0.9872340770929972, + "learning_rate": 6.437268681849824e-06, + "loss": 0.845, + "step": 7008 + }, + { + "epoch": 0.6275896804521798, + "grad_norm": 0.8409612140230771, + "learning_rate": 6.4345588546449675e-06, + "loss": 0.7976, + "step": 7009 + }, + { + "epoch": 0.6276792209972578, + "grad_norm": 0.9822073508036436, + "learning_rate": 6.431849327353401e-06, + "loss": 0.8187, + "step": 7010 + }, + { + "epoch": 0.6277687615423359, + "grad_norm": 1.0096700515470856, + "learning_rate": 6.429140100203046e-06, + "loss": 0.7993, + "step": 7011 + }, + { + "epoch": 0.627858302087414, + "grad_norm": 1.033353444634398, + "learning_rate": 6.4264311734217855e-06, + "loss": 0.8278, + "step": 7012 + }, + { + "epoch": 0.627947842632492, + "grad_norm": 1.0193287839705376, + "learning_rate": 6.423722547237491e-06, + "loss": 0.7762, + "step": 7013 + }, + { + "epoch": 0.6280373831775701, + "grad_norm": 0.8986007300315252, + "learning_rate": 6.421014221878001e-06, + "loss": 0.8822, + "step": 7014 + }, + { + "epoch": 0.6281269237226481, + "grad_norm": 0.9828611344085806, + "learning_rate": 6.418306197571129e-06, + "loss": 0.8941, + "step": 7015 + }, + { + "epoch": 0.6282164642677263, + "grad_norm": 0.9953716396986332, + "learning_rate": 6.4155984745446754e-06, + "loss": 0.8558, + "step": 7016 + }, + { + "epoch": 0.6283060048128043, + "grad_norm": 0.9986898618648041, + "learning_rate": 6.412891053026391e-06, + "loss": 0.8363, + "step": 7017 + }, + { + "epoch": 0.6283955453578823, + "grad_norm": 1.0150457948423264, + "learning_rate": 6.410183933244023e-06, + "loss": 0.8416, + "step": 7018 + }, + { + "epoch": 0.6284850859029605, + "grad_norm": 1.0407326145251505, + "learning_rate": 6.407477115425287e-06, + "loss": 0.8183, + "step": 7019 + }, + { + "epoch": 0.6285746264480385, + "grad_norm": 0.8840504436937133, + "learning_rate": 6.404770599797867e-06, + "loss": 0.8004, + "step": 7020 + }, + { + "epoch": 0.6286641669931166, + "grad_norm": 1.0336948076215837, + "learning_rate": 6.402064386589426e-06, + "loss": 0.7982, + "step": 7021 + }, + { + "epoch": 0.6287537075381946, + "grad_norm": 0.948788830946544, + "learning_rate": 6.3993584760276105e-06, + "loss": 0.824, + "step": 7022 + }, + { + "epoch": 0.6288432480832727, + "grad_norm": 0.9751187453063612, + "learning_rate": 6.396652868340021e-06, + "loss": 0.816, + "step": 7023 + }, + { + "epoch": 0.6289327886283508, + "grad_norm": 0.8392067383607967, + "learning_rate": 6.393947563754253e-06, + "loss": 0.7413, + "step": 7024 + }, + { + "epoch": 0.6290223291734288, + "grad_norm": 0.8762935430495283, + "learning_rate": 6.391242562497864e-06, + "loss": 0.8087, + "step": 7025 + }, + { + "epoch": 0.629111869718507, + "grad_norm": 1.021277806652637, + "learning_rate": 6.3885378647983896e-06, + "loss": 0.8523, + "step": 7026 + }, + { + "epoch": 0.629201410263585, + "grad_norm": 0.9301618998883415, + "learning_rate": 6.385833470883345e-06, + "loss": 0.7941, + "step": 7027 + }, + { + "epoch": 0.629290950808663, + "grad_norm": 0.9445009272389847, + "learning_rate": 6.383129380980209e-06, + "loss": 0.8171, + "step": 7028 + }, + { + "epoch": 0.6293804913537411, + "grad_norm": 0.9296986104138628, + "learning_rate": 6.380425595316442e-06, + "loss": 0.8268, + "step": 7029 + }, + { + "epoch": 0.6294700318988192, + "grad_norm": 1.136819963228013, + "learning_rate": 6.377722114119478e-06, + "loss": 0.7714, + "step": 7030 + }, + { + "epoch": 0.6295595724438973, + "grad_norm": 1.0700816909027835, + "learning_rate": 6.375018937616727e-06, + "loss": 0.8638, + "step": 7031 + }, + { + "epoch": 0.6296491129889753, + "grad_norm": 0.9959267207377598, + "learning_rate": 6.372316066035571e-06, + "loss": 0.7659, + "step": 7032 + }, + { + "epoch": 0.6297386535340533, + "grad_norm": 1.1157612145949023, + "learning_rate": 6.369613499603368e-06, + "loss": 0.7986, + "step": 7033 + }, + { + "epoch": 0.6298281940791315, + "grad_norm": 0.9349567258103602, + "learning_rate": 6.3669112385474445e-06, + "loss": 0.7471, + "step": 7034 + }, + { + "epoch": 0.6299177346242095, + "grad_norm": 1.56993488926938, + "learning_rate": 6.364209283095108e-06, + "loss": 0.8598, + "step": 7035 + }, + { + "epoch": 0.6300072751692876, + "grad_norm": 0.971158141512142, + "learning_rate": 6.361507633473638e-06, + "loss": 0.8137, + "step": 7036 + }, + { + "epoch": 0.6300968157143657, + "grad_norm": 1.3686136629563976, + "learning_rate": 6.358806289910291e-06, + "loss": 0.8253, + "step": 7037 + }, + { + "epoch": 0.6301863562594437, + "grad_norm": 0.953686542401127, + "learning_rate": 6.356105252632294e-06, + "loss": 0.8578, + "step": 7038 + }, + { + "epoch": 0.6302758968045218, + "grad_norm": 0.9369165940752319, + "learning_rate": 6.353404521866848e-06, + "loss": 0.8119, + "step": 7039 + }, + { + "epoch": 0.6303654373495998, + "grad_norm": 0.8767765889042951, + "learning_rate": 6.350704097841129e-06, + "loss": 0.7958, + "step": 7040 + }, + { + "epoch": 0.630454977894678, + "grad_norm": 0.9396009894944904, + "learning_rate": 6.348003980782291e-06, + "loss": 0.7842, + "step": 7041 + }, + { + "epoch": 0.630544518439756, + "grad_norm": 0.9546018855617986, + "learning_rate": 6.345304170917454e-06, + "loss": 0.8027, + "step": 7042 + }, + { + "epoch": 0.630634058984834, + "grad_norm": 0.9206310639484706, + "learning_rate": 6.342604668473724e-06, + "loss": 0.7856, + "step": 7043 + }, + { + "epoch": 0.6307235995299122, + "grad_norm": 0.9995689861637845, + "learning_rate": 6.339905473678172e-06, + "loss": 0.8362, + "step": 7044 + }, + { + "epoch": 0.6308131400749902, + "grad_norm": 0.960493144933787, + "learning_rate": 6.337206586757842e-06, + "loss": 0.8005, + "step": 7045 + }, + { + "epoch": 0.6309026806200683, + "grad_norm": 1.0543854825983656, + "learning_rate": 6.334508007939759e-06, + "loss": 0.7975, + "step": 7046 + }, + { + "epoch": 0.6309922211651463, + "grad_norm": 0.9669013494214188, + "learning_rate": 6.3318097374509165e-06, + "loss": 0.8243, + "step": 7047 + }, + { + "epoch": 0.6310817617102245, + "grad_norm": 1.0782000958648794, + "learning_rate": 6.329111775518284e-06, + "loss": 0.7859, + "step": 7048 + }, + { + "epoch": 0.6311713022553025, + "grad_norm": 1.099900654164012, + "learning_rate": 6.326414122368814e-06, + "loss": 0.7603, + "step": 7049 + }, + { + "epoch": 0.6312608428003805, + "grad_norm": 1.0095604448697453, + "learning_rate": 6.323716778229411e-06, + "loss": 0.8405, + "step": 7050 + }, + { + "epoch": 0.6313503833454586, + "grad_norm": 1.0175641576941423, + "learning_rate": 6.32101974332697e-06, + "loss": 0.8192, + "step": 7051 + }, + { + "epoch": 0.6314399238905367, + "grad_norm": 0.987528811422066, + "learning_rate": 6.318323017888364e-06, + "loss": 0.8226, + "step": 7052 + }, + { + "epoch": 0.6315294644356148, + "grad_norm": 0.9824681983423325, + "learning_rate": 6.315626602140425e-06, + "loss": 0.8892, + "step": 7053 + }, + { + "epoch": 0.6316190049806928, + "grad_norm": 0.9255146575702566, + "learning_rate": 6.31293049630997e-06, + "loss": 0.7946, + "step": 7054 + }, + { + "epoch": 0.6317085455257709, + "grad_norm": 0.9963842637196021, + "learning_rate": 6.310234700623794e-06, + "loss": 0.8486, + "step": 7055 + }, + { + "epoch": 0.631798086070849, + "grad_norm": 0.9984743381961027, + "learning_rate": 6.307539215308644e-06, + "loss": 0.869, + "step": 7056 + }, + { + "epoch": 0.631887626615927, + "grad_norm": 0.9173593219005337, + "learning_rate": 6.304844040591263e-06, + "loss": 0.8366, + "step": 7057 + }, + { + "epoch": 0.631977167161005, + "grad_norm": 0.8843740764529929, + "learning_rate": 6.302149176698361e-06, + "loss": 0.8006, + "step": 7058 + }, + { + "epoch": 0.6320667077060832, + "grad_norm": 0.9183723247563366, + "learning_rate": 6.29945462385662e-06, + "loss": 0.8269, + "step": 7059 + }, + { + "epoch": 0.6321562482511612, + "grad_norm": 0.9629639512738353, + "learning_rate": 6.296760382292699e-06, + "loss": 0.809, + "step": 7060 + }, + { + "epoch": 0.6322457887962393, + "grad_norm": 1.0282789616588772, + "learning_rate": 6.294066452233225e-06, + "loss": 0.7885, + "step": 7061 + }, + { + "epoch": 0.6323353293413174, + "grad_norm": 1.1493429401219268, + "learning_rate": 6.291372833904805e-06, + "loss": 0.8562, + "step": 7062 + }, + { + "epoch": 0.6324248698863955, + "grad_norm": 0.9884442962337517, + "learning_rate": 6.288679527534014e-06, + "loss": 0.8642, + "step": 7063 + }, + { + "epoch": 0.6325144104314735, + "grad_norm": 0.907608382429478, + "learning_rate": 6.28598653334741e-06, + "loss": 0.8487, + "step": 7064 + }, + { + "epoch": 0.6326039509765515, + "grad_norm": 0.91711785399273, + "learning_rate": 6.283293851571515e-06, + "loss": 0.8354, + "step": 7065 + }, + { + "epoch": 0.6326934915216297, + "grad_norm": 0.9097698053028457, + "learning_rate": 6.280601482432831e-06, + "loss": 0.8078, + "step": 7066 + }, + { + "epoch": 0.6327830320667077, + "grad_norm": 0.848249897616302, + "learning_rate": 6.277909426157829e-06, + "loss": 0.7687, + "step": 7067 + }, + { + "epoch": 0.6328725726117858, + "grad_norm": 0.8598755819340291, + "learning_rate": 6.275217682972957e-06, + "loss": 0.8479, + "step": 7068 + }, + { + "epoch": 0.6329621131568638, + "grad_norm": 0.9244989216750829, + "learning_rate": 6.272526253104634e-06, + "loss": 0.8345, + "step": 7069 + }, + { + "epoch": 0.6330516537019419, + "grad_norm": 0.9866361305073986, + "learning_rate": 6.269835136779257e-06, + "loss": 0.8581, + "step": 7070 + }, + { + "epoch": 0.63314119424702, + "grad_norm": 0.9035743965467674, + "learning_rate": 6.267144334223194e-06, + "loss": 0.8186, + "step": 7071 + }, + { + "epoch": 0.633230734792098, + "grad_norm": 0.8869064088197958, + "learning_rate": 6.264453845662785e-06, + "loss": 0.8365, + "step": 7072 + }, + { + "epoch": 0.6333202753371762, + "grad_norm": 1.0018109078297015, + "learning_rate": 6.261763671324345e-06, + "loss": 0.8401, + "step": 7073 + }, + { + "epoch": 0.6334098158822542, + "grad_norm": 1.0271065329642635, + "learning_rate": 6.259073811434162e-06, + "loss": 0.8972, + "step": 7074 + }, + { + "epoch": 0.6334993564273322, + "grad_norm": 1.0018144845395736, + "learning_rate": 6.256384266218498e-06, + "loss": 0.8914, + "step": 7075 + }, + { + "epoch": 0.6335888969724103, + "grad_norm": 0.8854649655012243, + "learning_rate": 6.253695035903598e-06, + "loss": 0.7767, + "step": 7076 + }, + { + "epoch": 0.6336784375174884, + "grad_norm": 0.9337421350337655, + "learning_rate": 6.2510061207156566e-06, + "loss": 0.835, + "step": 7077 + }, + { + "epoch": 0.6337679780625665, + "grad_norm": 0.9895732225870155, + "learning_rate": 6.2483175208808634e-06, + "loss": 0.7911, + "step": 7078 + }, + { + "epoch": 0.6338575186076445, + "grad_norm": 0.9358033205276218, + "learning_rate": 6.245629236625376e-06, + "loss": 0.8796, + "step": 7079 + }, + { + "epoch": 0.6339470591527226, + "grad_norm": 1.0673187047237729, + "learning_rate": 6.2429412681753224e-06, + "loss": 0.8294, + "step": 7080 + }, + { + "epoch": 0.6340365996978007, + "grad_norm": 1.0116146000516488, + "learning_rate": 6.240253615756805e-06, + "loss": 0.7313, + "step": 7081 + }, + { + "epoch": 0.6341261402428787, + "grad_norm": 0.9465729691199621, + "learning_rate": 6.237566279595908e-06, + "loss": 0.7974, + "step": 7082 + }, + { + "epoch": 0.6342156807879568, + "grad_norm": 0.9165613820924751, + "learning_rate": 6.2348792599186695e-06, + "loss": 0.8165, + "step": 7083 + }, + { + "epoch": 0.6343052213330349, + "grad_norm": 0.8921114534459816, + "learning_rate": 6.232192556951118e-06, + "loss": 0.8104, + "step": 7084 + }, + { + "epoch": 0.634394761878113, + "grad_norm": 0.9957749597806583, + "learning_rate": 6.2295061709192505e-06, + "loss": 0.8351, + "step": 7085 + }, + { + "epoch": 0.634484302423191, + "grad_norm": 0.9988394246241886, + "learning_rate": 6.226820102049038e-06, + "loss": 0.792, + "step": 7086 + }, + { + "epoch": 0.634573842968269, + "grad_norm": 1.126694794481609, + "learning_rate": 6.224134350566424e-06, + "loss": 0.8273, + "step": 7087 + }, + { + "epoch": 0.6346633835133472, + "grad_norm": 1.0466130894346675, + "learning_rate": 6.2214489166973235e-06, + "loss": 0.8551, + "step": 7088 + }, + { + "epoch": 0.6347529240584252, + "grad_norm": 0.9081586423033162, + "learning_rate": 6.218763800667625e-06, + "loss": 0.8493, + "step": 7089 + }, + { + "epoch": 0.6348424646035032, + "grad_norm": 0.9909629787937567, + "learning_rate": 6.216079002703193e-06, + "loss": 0.7679, + "step": 7090 + }, + { + "epoch": 0.6349320051485814, + "grad_norm": 1.0170584340470656, + "learning_rate": 6.2133945230298675e-06, + "loss": 0.872, + "step": 7091 + }, + { + "epoch": 0.6350215456936594, + "grad_norm": 0.9251934026850186, + "learning_rate": 6.210710361873453e-06, + "loss": 0.8173, + "step": 7092 + }, + { + "epoch": 0.6351110862387375, + "grad_norm": 0.9398167104802502, + "learning_rate": 6.208026519459738e-06, + "loss": 0.8485, + "step": 7093 + }, + { + "epoch": 0.6352006267838155, + "grad_norm": 0.9658341075945795, + "learning_rate": 6.205342996014474e-06, + "loss": 0.7861, + "step": 7094 + }, + { + "epoch": 0.6352901673288937, + "grad_norm": 0.9222276685307285, + "learning_rate": 6.20265979176339e-06, + "loss": 0.8395, + "step": 7095 + }, + { + "epoch": 0.6353797078739717, + "grad_norm": 0.988598157977415, + "learning_rate": 6.199976906932188e-06, + "loss": 0.8352, + "step": 7096 + }, + { + "epoch": 0.6354692484190497, + "grad_norm": 0.884046723470731, + "learning_rate": 6.197294341746549e-06, + "loss": 0.8349, + "step": 7097 + }, + { + "epoch": 0.6355587889641279, + "grad_norm": 1.056173020712827, + "learning_rate": 6.194612096432119e-06, + "loss": 0.8415, + "step": 7098 + }, + { + "epoch": 0.6356483295092059, + "grad_norm": 0.9460365365340243, + "learning_rate": 6.191930171214517e-06, + "loss": 0.7828, + "step": 7099 + }, + { + "epoch": 0.635737870054284, + "grad_norm": 0.9250268128591796, + "learning_rate": 6.189248566319339e-06, + "loss": 0.8066, + "step": 7100 + }, + { + "epoch": 0.635827410599362, + "grad_norm": 0.8633541502219753, + "learning_rate": 6.1865672819721545e-06, + "loss": 0.8139, + "step": 7101 + }, + { + "epoch": 0.6359169511444401, + "grad_norm": 1.038272444169285, + "learning_rate": 6.1838863183985e-06, + "loss": 0.8798, + "step": 7102 + }, + { + "epoch": 0.6360064916895182, + "grad_norm": 1.0582820831312751, + "learning_rate": 6.181205675823896e-06, + "loss": 0.9162, + "step": 7103 + }, + { + "epoch": 0.6360960322345962, + "grad_norm": 0.9831825362479607, + "learning_rate": 6.17852535447383e-06, + "loss": 0.7819, + "step": 7104 + }, + { + "epoch": 0.6361855727796742, + "grad_norm": 1.009434581984189, + "learning_rate": 6.175845354573753e-06, + "loss": 0.8788, + "step": 7105 + }, + { + "epoch": 0.6362751133247524, + "grad_norm": 0.9803034126725186, + "learning_rate": 6.173165676349103e-06, + "loss": 0.7996, + "step": 7106 + }, + { + "epoch": 0.6363646538698304, + "grad_norm": 0.9697130406576904, + "learning_rate": 6.170486320025287e-06, + "loss": 0.822, + "step": 7107 + }, + { + "epoch": 0.6364541944149085, + "grad_norm": 1.0090211000430436, + "learning_rate": 6.1678072858276805e-06, + "loss": 0.8733, + "step": 7108 + }, + { + "epoch": 0.6365437349599866, + "grad_norm": 0.9968511454912732, + "learning_rate": 6.165128573981642e-06, + "loss": 0.7939, + "step": 7109 + }, + { + "epoch": 0.6366332755050647, + "grad_norm": 0.8891754667407683, + "learning_rate": 6.16245018471249e-06, + "loss": 0.8345, + "step": 7110 + }, + { + "epoch": 0.6367228160501427, + "grad_norm": 1.0813200606014772, + "learning_rate": 6.159772118245518e-06, + "loss": 0.8952, + "step": 7111 + }, + { + "epoch": 0.6368123565952207, + "grad_norm": 0.8896963469459684, + "learning_rate": 6.157094374806005e-06, + "loss": 0.7993, + "step": 7112 + }, + { + "epoch": 0.6369018971402989, + "grad_norm": 0.9093560424284486, + "learning_rate": 6.154416954619189e-06, + "loss": 0.8348, + "step": 7113 + }, + { + "epoch": 0.6369914376853769, + "grad_norm": 0.9125174015568591, + "learning_rate": 6.1517398579102885e-06, + "loss": 0.8531, + "step": 7114 + }, + { + "epoch": 0.637080978230455, + "grad_norm": 1.036580688636479, + "learning_rate": 6.149063084904492e-06, + "loss": 0.8027, + "step": 7115 + }, + { + "epoch": 0.6371705187755331, + "grad_norm": 1.0198915751417055, + "learning_rate": 6.1463866358269575e-06, + "loss": 0.863, + "step": 7116 + }, + { + "epoch": 0.6372600593206111, + "grad_norm": 0.911278093190435, + "learning_rate": 6.143710510902821e-06, + "loss": 0.8349, + "step": 7117 + }, + { + "epoch": 0.6373495998656892, + "grad_norm": 0.9389083708685582, + "learning_rate": 6.14103471035719e-06, + "loss": 0.7833, + "step": 7118 + }, + { + "epoch": 0.6374391404107672, + "grad_norm": 0.9317400669709383, + "learning_rate": 6.138359234415146e-06, + "loss": 0.7714, + "step": 7119 + }, + { + "epoch": 0.6375286809558454, + "grad_norm": 0.9333156352087469, + "learning_rate": 6.135684083301738e-06, + "loss": 0.8253, + "step": 7120 + }, + { + "epoch": 0.6376182215009234, + "grad_norm": 0.9576604584757233, + "learning_rate": 6.133009257241993e-06, + "loss": 0.8249, + "step": 7121 + }, + { + "epoch": 0.6377077620460014, + "grad_norm": 0.9825255573724618, + "learning_rate": 6.130334756460907e-06, + "loss": 0.7953, + "step": 7122 + }, + { + "epoch": 0.6377973025910795, + "grad_norm": 0.939528790669359, + "learning_rate": 6.1276605811834485e-06, + "loss": 0.8208, + "step": 7123 + }, + { + "epoch": 0.6378868431361576, + "grad_norm": 0.9057899481825418, + "learning_rate": 6.124986731634566e-06, + "loss": 0.8007, + "step": 7124 + }, + { + "epoch": 0.6379763836812357, + "grad_norm": 1.0010044825025657, + "learning_rate": 6.122313208039172e-06, + "loss": 0.7948, + "step": 7125 + }, + { + "epoch": 0.6380659242263137, + "grad_norm": 0.9091039513398609, + "learning_rate": 6.119640010622157e-06, + "loss": 0.8229, + "step": 7126 + }, + { + "epoch": 0.6381554647713918, + "grad_norm": 0.9333508445959617, + "learning_rate": 6.116967139608377e-06, + "loss": 0.8466, + "step": 7127 + }, + { + "epoch": 0.6382450053164699, + "grad_norm": 0.9862860070584623, + "learning_rate": 6.114294595222667e-06, + "loss": 0.8567, + "step": 7128 + }, + { + "epoch": 0.6383345458615479, + "grad_norm": 0.9312588972876452, + "learning_rate": 6.111622377689832e-06, + "loss": 0.8367, + "step": 7129 + }, + { + "epoch": 0.638424086406626, + "grad_norm": 1.052348515470203, + "learning_rate": 6.108950487234653e-06, + "loss": 0.7828, + "step": 7130 + }, + { + "epoch": 0.6385136269517041, + "grad_norm": 0.9531537235051175, + "learning_rate": 6.106278924081883e-06, + "loss": 0.8478, + "step": 7131 + }, + { + "epoch": 0.6386031674967821, + "grad_norm": 0.8989914778417699, + "learning_rate": 6.103607688456237e-06, + "loss": 0.826, + "step": 7132 + }, + { + "epoch": 0.6386927080418602, + "grad_norm": 1.0080488468202637, + "learning_rate": 6.100936780582416e-06, + "loss": 0.7689, + "step": 7133 + }, + { + "epoch": 0.6387822485869383, + "grad_norm": 0.9350502948572023, + "learning_rate": 6.098266200685088e-06, + "loss": 0.8203, + "step": 7134 + }, + { + "epoch": 0.6388717891320164, + "grad_norm": 0.9842593086685824, + "learning_rate": 6.095595948988888e-06, + "loss": 0.7946, + "step": 7135 + }, + { + "epoch": 0.6389613296770944, + "grad_norm": 0.9891581732191831, + "learning_rate": 6.092926025718438e-06, + "loss": 0.8316, + "step": 7136 + }, + { + "epoch": 0.6390508702221724, + "grad_norm": 0.9484838801193954, + "learning_rate": 6.090256431098323e-06, + "loss": 0.7725, + "step": 7137 + }, + { + "epoch": 0.6391404107672506, + "grad_norm": 0.9314814210895521, + "learning_rate": 6.087587165353088e-06, + "loss": 0.8316, + "step": 7138 + }, + { + "epoch": 0.6392299513123286, + "grad_norm": 1.0177008987835385, + "learning_rate": 6.084918228707275e-06, + "loss": 0.7743, + "step": 7139 + }, + { + "epoch": 0.6393194918574067, + "grad_norm": 1.035713651930231, + "learning_rate": 6.0822496213853825e-06, + "loss": 0.85, + "step": 7140 + }, + { + "epoch": 0.6394090324024847, + "grad_norm": 0.9038513971622288, + "learning_rate": 6.079581343611885e-06, + "loss": 0.8487, + "step": 7141 + }, + { + "epoch": 0.6394985729475628, + "grad_norm": 1.2458075230027799, + "learning_rate": 6.076913395611231e-06, + "loss": 0.7505, + "step": 7142 + }, + { + "epoch": 0.6395881134926409, + "grad_norm": 1.116459577247019, + "learning_rate": 6.074245777607835e-06, + "loss": 0.8345, + "step": 7143 + }, + { + "epoch": 0.6396776540377189, + "grad_norm": 1.01744219089649, + "learning_rate": 6.071578489826091e-06, + "loss": 0.7972, + "step": 7144 + }, + { + "epoch": 0.6397671945827971, + "grad_norm": 0.95228955360677, + "learning_rate": 6.068911532490364e-06, + "loss": 0.817, + "step": 7145 + }, + { + "epoch": 0.6398567351278751, + "grad_norm": 1.2074015714991864, + "learning_rate": 6.066244905824988e-06, + "loss": 0.8308, + "step": 7146 + }, + { + "epoch": 0.6399462756729531, + "grad_norm": 0.9560156162127247, + "learning_rate": 6.0635786100542745e-06, + "loss": 0.821, + "step": 7147 + }, + { + "epoch": 0.6400358162180312, + "grad_norm": 1.1504852039171807, + "learning_rate": 6.060912645402499e-06, + "loss": 0.8489, + "step": 7148 + }, + { + "epoch": 0.6401253567631093, + "grad_norm": 0.9827147740012714, + "learning_rate": 6.058247012093915e-06, + "loss": 0.7824, + "step": 7149 + }, + { + "epoch": 0.6402148973081874, + "grad_norm": 1.0186738854413284, + "learning_rate": 6.055581710352744e-06, + "loss": 0.8264, + "step": 7150 + }, + { + "epoch": 0.6403044378532654, + "grad_norm": 0.8655650413701632, + "learning_rate": 6.0529167404031905e-06, + "loss": 0.7659, + "step": 7151 + }, + { + "epoch": 0.6403939783983436, + "grad_norm": 0.9091217544442665, + "learning_rate": 6.050252102469417e-06, + "loss": 0.8397, + "step": 7152 + }, + { + "epoch": 0.6404835189434216, + "grad_norm": 1.0390417148127027, + "learning_rate": 6.0475877967755685e-06, + "loss": 0.8498, + "step": 7153 + }, + { + "epoch": 0.6405730594884996, + "grad_norm": 0.9426177171933874, + "learning_rate": 6.044923823545752e-06, + "loss": 0.8181, + "step": 7154 + }, + { + "epoch": 0.6406626000335777, + "grad_norm": 0.9821242494428377, + "learning_rate": 6.042260183004054e-06, + "loss": 0.8743, + "step": 7155 + }, + { + "epoch": 0.6407521405786558, + "grad_norm": 0.9647892315068132, + "learning_rate": 6.039596875374531e-06, + "loss": 0.8243, + "step": 7156 + }, + { + "epoch": 0.6408416811237339, + "grad_norm": 0.9633553608802812, + "learning_rate": 6.036933900881217e-06, + "loss": 0.7716, + "step": 7157 + }, + { + "epoch": 0.6409312216688119, + "grad_norm": 1.0457879016168352, + "learning_rate": 6.0342712597481105e-06, + "loss": 0.8639, + "step": 7158 + }, + { + "epoch": 0.6410207622138899, + "grad_norm": 0.9128032712085212, + "learning_rate": 6.0316089521991775e-06, + "loss": 0.8616, + "step": 7159 + }, + { + "epoch": 0.6411103027589681, + "grad_norm": 1.0471197353760968, + "learning_rate": 6.02894697845837e-06, + "loss": 0.7589, + "step": 7160 + }, + { + "epoch": 0.6411998433040461, + "grad_norm": 0.961378897080113, + "learning_rate": 6.0262853387496e-06, + "loss": 0.781, + "step": 7161 + }, + { + "epoch": 0.6412893838491242, + "grad_norm": 0.893724743883784, + "learning_rate": 6.023624033296758e-06, + "loss": 0.797, + "step": 7162 + }, + { + "epoch": 0.6413789243942023, + "grad_norm": 1.0501690257706617, + "learning_rate": 6.020963062323706e-06, + "loss": 0.8116, + "step": 7163 + }, + { + "epoch": 0.6414684649392803, + "grad_norm": 0.9558225785946043, + "learning_rate": 6.0183024260542785e-06, + "loss": 0.7995, + "step": 7164 + }, + { + "epoch": 0.6415580054843584, + "grad_norm": 1.1114284541026738, + "learning_rate": 6.015642124712271e-06, + "loss": 0.8196, + "step": 7165 + }, + { + "epoch": 0.6416475460294364, + "grad_norm": 0.966595041604333, + "learning_rate": 6.012982158521465e-06, + "loss": 0.8478, + "step": 7166 + }, + { + "epoch": 0.6417370865745146, + "grad_norm": 0.9409852265125261, + "learning_rate": 6.010322527705608e-06, + "loss": 0.8279, + "step": 7167 + }, + { + "epoch": 0.6418266271195926, + "grad_norm": 1.0095614291749664, + "learning_rate": 6.007663232488418e-06, + "loss": 0.8369, + "step": 7168 + }, + { + "epoch": 0.6419161676646706, + "grad_norm": 0.9007443120439561, + "learning_rate": 6.00500427309359e-06, + "loss": 0.8349, + "step": 7169 + }, + { + "epoch": 0.6420057082097488, + "grad_norm": 0.9422820299417833, + "learning_rate": 6.002345649744781e-06, + "loss": 0.8071, + "step": 7170 + }, + { + "epoch": 0.6420952487548268, + "grad_norm": 1.0150018023033678, + "learning_rate": 5.999687362665627e-06, + "loss": 0.8147, + "step": 7171 + }, + { + "epoch": 0.6421847892999049, + "grad_norm": 1.0140194360928527, + "learning_rate": 5.997029412079738e-06, + "loss": 0.8263, + "step": 7172 + }, + { + "epoch": 0.6422743298449829, + "grad_norm": 0.949623263854444, + "learning_rate": 5.994371798210692e-06, + "loss": 0.8555, + "step": 7173 + }, + { + "epoch": 0.642363870390061, + "grad_norm": 0.9855417455915145, + "learning_rate": 5.991714521282035e-06, + "loss": 0.8175, + "step": 7174 + }, + { + "epoch": 0.6424534109351391, + "grad_norm": 1.037590227964297, + "learning_rate": 5.989057581517295e-06, + "loss": 0.8452, + "step": 7175 + }, + { + "epoch": 0.6425429514802171, + "grad_norm": 0.8604341734739114, + "learning_rate": 5.986400979139957e-06, + "loss": 0.784, + "step": 7176 + }, + { + "epoch": 0.6426324920252952, + "grad_norm": 0.9310382953543267, + "learning_rate": 5.9837447143734875e-06, + "loss": 0.8141, + "step": 7177 + }, + { + "epoch": 0.6427220325703733, + "grad_norm": 0.9051739014057687, + "learning_rate": 5.981088787441327e-06, + "loss": 0.8018, + "step": 7178 + }, + { + "epoch": 0.6428115731154513, + "grad_norm": 0.9704794002918998, + "learning_rate": 5.978433198566882e-06, + "loss": 0.8116, + "step": 7179 + }, + { + "epoch": 0.6429011136605294, + "grad_norm": 0.9853586782721148, + "learning_rate": 5.975777947973532e-06, + "loss": 0.8369, + "step": 7180 + }, + { + "epoch": 0.6429906542056075, + "grad_norm": 1.0386183403366624, + "learning_rate": 5.973123035884626e-06, + "loss": 0.8452, + "step": 7181 + }, + { + "epoch": 0.6430801947506856, + "grad_norm": 0.9445704628522498, + "learning_rate": 5.9704684625234875e-06, + "loss": 0.8314, + "step": 7182 + }, + { + "epoch": 0.6431697352957636, + "grad_norm": 1.159075662613163, + "learning_rate": 5.967814228113409e-06, + "loss": 0.8297, + "step": 7183 + }, + { + "epoch": 0.6432592758408416, + "grad_norm": 0.9384246141434094, + "learning_rate": 5.9651603328776606e-06, + "loss": 0.8138, + "step": 7184 + }, + { + "epoch": 0.6433488163859198, + "grad_norm": 0.9605118880508731, + "learning_rate": 5.962506777039476e-06, + "loss": 0.8429, + "step": 7185 + }, + { + "epoch": 0.6434383569309978, + "grad_norm": 0.9702023425419578, + "learning_rate": 5.959853560822066e-06, + "loss": 0.8113, + "step": 7186 + }, + { + "epoch": 0.6435278974760759, + "grad_norm": 1.0023719681192862, + "learning_rate": 5.957200684448607e-06, + "loss": 0.8283, + "step": 7187 + }, + { + "epoch": 0.643617438021154, + "grad_norm": 0.9313455166754111, + "learning_rate": 5.954548148142254e-06, + "loss": 0.817, + "step": 7188 + }, + { + "epoch": 0.643706978566232, + "grad_norm": 0.9833967254459589, + "learning_rate": 5.951895952126125e-06, + "loss": 0.8319, + "step": 7189 + }, + { + "epoch": 0.6437965191113101, + "grad_norm": 1.1617818403893587, + "learning_rate": 5.949244096623317e-06, + "loss": 0.8048, + "step": 7190 + }, + { + "epoch": 0.6438860596563881, + "grad_norm": 0.9104065046674543, + "learning_rate": 5.9465925818569e-06, + "loss": 0.8482, + "step": 7191 + }, + { + "epoch": 0.6439756002014663, + "grad_norm": 0.9767775990518126, + "learning_rate": 5.9439414080499015e-06, + "loss": 0.8607, + "step": 7192 + }, + { + "epoch": 0.6440651407465443, + "grad_norm": 0.904576624021083, + "learning_rate": 5.9412905754253355e-06, + "loss": 0.7803, + "step": 7193 + }, + { + "epoch": 0.6441546812916223, + "grad_norm": 0.9633275396002314, + "learning_rate": 5.93864008420618e-06, + "loss": 0.8629, + "step": 7194 + }, + { + "epoch": 0.6442442218367004, + "grad_norm": 1.2767285607196206, + "learning_rate": 5.935989934615386e-06, + "loss": 0.8908, + "step": 7195 + }, + { + "epoch": 0.6443337623817785, + "grad_norm": 0.9308928192757084, + "learning_rate": 5.933340126875872e-06, + "loss": 0.8048, + "step": 7196 + }, + { + "epoch": 0.6444233029268566, + "grad_norm": 0.9551597668923183, + "learning_rate": 5.930690661210543e-06, + "loss": 0.8162, + "step": 7197 + }, + { + "epoch": 0.6445128434719346, + "grad_norm": 0.9789550251092578, + "learning_rate": 5.928041537842248e-06, + "loss": 0.8172, + "step": 7198 + }, + { + "epoch": 0.6446023840170128, + "grad_norm": 0.9479853693176701, + "learning_rate": 5.925392756993831e-06, + "loss": 0.7687, + "step": 7199 + }, + { + "epoch": 0.6446919245620908, + "grad_norm": 1.0231335816437772, + "learning_rate": 5.922744318888098e-06, + "loss": 0.8441, + "step": 7200 + }, + { + "epoch": 0.6447814651071688, + "grad_norm": 1.188463200990797, + "learning_rate": 5.920096223747827e-06, + "loss": 0.8319, + "step": 7201 + }, + { + "epoch": 0.6448710056522469, + "grad_norm": 0.9779486640050746, + "learning_rate": 5.917448471795766e-06, + "loss": 0.7791, + "step": 7202 + }, + { + "epoch": 0.644960546197325, + "grad_norm": 0.9008776441958956, + "learning_rate": 5.914801063254636e-06, + "loss": 0.793, + "step": 7203 + }, + { + "epoch": 0.645050086742403, + "grad_norm": 0.9745691340883105, + "learning_rate": 5.912153998347124e-06, + "loss": 0.7704, + "step": 7204 + }, + { + "epoch": 0.6451396272874811, + "grad_norm": 1.0076331206242952, + "learning_rate": 5.909507277295901e-06, + "loss": 0.8067, + "step": 7205 + }, + { + "epoch": 0.6452291678325592, + "grad_norm": 1.1650058535900636, + "learning_rate": 5.906860900323595e-06, + "loss": 0.832, + "step": 7206 + }, + { + "epoch": 0.6453187083776373, + "grad_norm": 0.9766281368525203, + "learning_rate": 5.904214867652811e-06, + "loss": 0.8002, + "step": 7207 + }, + { + "epoch": 0.6454082489227153, + "grad_norm": 0.9564607747482262, + "learning_rate": 5.901569179506128e-06, + "loss": 0.7919, + "step": 7208 + }, + { + "epoch": 0.6454977894677933, + "grad_norm": 1.0127029590676444, + "learning_rate": 5.8989238361060875e-06, + "loss": 0.7635, + "step": 7209 + }, + { + "epoch": 0.6455873300128715, + "grad_norm": 0.9958602327563781, + "learning_rate": 5.896278837675209e-06, + "loss": 0.8196, + "step": 7210 + }, + { + "epoch": 0.6456768705579495, + "grad_norm": 0.9124020522899216, + "learning_rate": 5.893634184435983e-06, + "loss": 0.7982, + "step": 7211 + }, + { + "epoch": 0.6457664111030276, + "grad_norm": 1.0866859959192143, + "learning_rate": 5.8909898766108684e-06, + "loss": 0.8619, + "step": 7212 + }, + { + "epoch": 0.6458559516481056, + "grad_norm": 0.9870892615201993, + "learning_rate": 5.888345914422298e-06, + "loss": 0.7717, + "step": 7213 + }, + { + "epoch": 0.6459454921931838, + "grad_norm": 1.0000316986711761, + "learning_rate": 5.885702298092666e-06, + "loss": 0.8308, + "step": 7214 + }, + { + "epoch": 0.6460350327382618, + "grad_norm": 0.9043873536344031, + "learning_rate": 5.883059027844351e-06, + "loss": 0.8369, + "step": 7215 + }, + { + "epoch": 0.6461245732833398, + "grad_norm": 0.8583354639025819, + "learning_rate": 5.880416103899696e-06, + "loss": 0.7811, + "step": 7216 + }, + { + "epoch": 0.646214113828418, + "grad_norm": 1.317675241875174, + "learning_rate": 5.8777735264810094e-06, + "loss": 0.8048, + "step": 7217 + }, + { + "epoch": 0.646303654373496, + "grad_norm": 0.9707293840339516, + "learning_rate": 5.875131295810589e-06, + "loss": 0.8198, + "step": 7218 + }, + { + "epoch": 0.646393194918574, + "grad_norm": 0.9194514313679033, + "learning_rate": 5.872489412110674e-06, + "loss": 0.8597, + "step": 7219 + }, + { + "epoch": 0.6464827354636521, + "grad_norm": 0.9735621729259253, + "learning_rate": 5.869847875603503e-06, + "loss": 0.8087, + "step": 7220 + }, + { + "epoch": 0.6465722760087302, + "grad_norm": 1.0838850774189066, + "learning_rate": 5.8672066865112685e-06, + "loss": 0.8692, + "step": 7221 + }, + { + "epoch": 0.6466618165538083, + "grad_norm": 1.009304888140753, + "learning_rate": 5.8645658450561416e-06, + "loss": 0.8223, + "step": 7222 + }, + { + "epoch": 0.6467513570988863, + "grad_norm": 0.9989737903762165, + "learning_rate": 5.8619253514602556e-06, + "loss": 0.7876, + "step": 7223 + }, + { + "epoch": 0.6468408976439645, + "grad_norm": 0.9976155510178509, + "learning_rate": 5.859285205945733e-06, + "loss": 0.7904, + "step": 7224 + }, + { + "epoch": 0.6469304381890425, + "grad_norm": 0.9929203579267685, + "learning_rate": 5.856645408734638e-06, + "loss": 0.8615, + "step": 7225 + }, + { + "epoch": 0.6470199787341205, + "grad_norm": 1.0254432144742018, + "learning_rate": 5.85400596004903e-06, + "loss": 0.8928, + "step": 7226 + }, + { + "epoch": 0.6471095192791986, + "grad_norm": 1.1345862247066796, + "learning_rate": 5.851366860110932e-06, + "loss": 0.8315, + "step": 7227 + }, + { + "epoch": 0.6471990598242767, + "grad_norm": 0.90370862634329, + "learning_rate": 5.848728109142334e-06, + "loss": 0.8342, + "step": 7228 + }, + { + "epoch": 0.6472886003693548, + "grad_norm": 0.9381508430840132, + "learning_rate": 5.8460897073652015e-06, + "loss": 0.8101, + "step": 7229 + }, + { + "epoch": 0.6473781409144328, + "grad_norm": 0.9350766262316815, + "learning_rate": 5.843451655001464e-06, + "loss": 0.8336, + "step": 7230 + }, + { + "epoch": 0.6474676814595108, + "grad_norm": 0.9321846547337961, + "learning_rate": 5.8408139522730265e-06, + "loss": 0.845, + "step": 7231 + }, + { + "epoch": 0.647557222004589, + "grad_norm": 0.9186505726259667, + "learning_rate": 5.838176599401768e-06, + "loss": 0.7761, + "step": 7232 + }, + { + "epoch": 0.647646762549667, + "grad_norm": 0.9786971563505652, + "learning_rate": 5.835539596609532e-06, + "loss": 0.7763, + "step": 7233 + }, + { + "epoch": 0.6477363030947451, + "grad_norm": 1.0628465920264336, + "learning_rate": 5.832902944118135e-06, + "loss": 0.8505, + "step": 7234 + }, + { + "epoch": 0.6478258436398232, + "grad_norm": 0.9768446858649646, + "learning_rate": 5.830266642149362e-06, + "loss": 0.8335, + "step": 7235 + }, + { + "epoch": 0.6479153841849012, + "grad_norm": 0.9984463672413127, + "learning_rate": 5.827630690924971e-06, + "loss": 0.7947, + "step": 7236 + }, + { + "epoch": 0.6480049247299793, + "grad_norm": 0.9474223630463614, + "learning_rate": 5.824995090666691e-06, + "loss": 0.859, + "step": 7237 + }, + { + "epoch": 0.6480944652750573, + "grad_norm": 0.954657300039822, + "learning_rate": 5.822359841596217e-06, + "loss": 0.7942, + "step": 7238 + }, + { + "epoch": 0.6481840058201355, + "grad_norm": 0.9348212461987404, + "learning_rate": 5.819724943935221e-06, + "loss": 0.7745, + "step": 7239 + }, + { + "epoch": 0.6482735463652135, + "grad_norm": 0.9635219207958502, + "learning_rate": 5.817090397905344e-06, + "loss": 0.818, + "step": 7240 + }, + { + "epoch": 0.6483630869102915, + "grad_norm": 0.9205815714730823, + "learning_rate": 5.814456203728187e-06, + "loss": 0.8774, + "step": 7241 + }, + { + "epoch": 0.6484526274553697, + "grad_norm": 1.122501330240104, + "learning_rate": 5.811822361625332e-06, + "loss": 0.7974, + "step": 7242 + }, + { + "epoch": 0.6485421680004477, + "grad_norm": 0.9573772729650327, + "learning_rate": 5.809188871818336e-06, + "loss": 0.8192, + "step": 7243 + }, + { + "epoch": 0.6486317085455258, + "grad_norm": 0.9481248937414388, + "learning_rate": 5.806555734528714e-06, + "loss": 0.7772, + "step": 7244 + }, + { + "epoch": 0.6487212490906038, + "grad_norm": 0.9320865521008098, + "learning_rate": 5.80392294997796e-06, + "loss": 0.7951, + "step": 7245 + }, + { + "epoch": 0.648810789635682, + "grad_norm": 0.8818783685751009, + "learning_rate": 5.801290518387537e-06, + "loss": 0.8433, + "step": 7246 + }, + { + "epoch": 0.64890033018076, + "grad_norm": 1.023759001844589, + "learning_rate": 5.798658439978869e-06, + "loss": 0.8102, + "step": 7247 + }, + { + "epoch": 0.648989870725838, + "grad_norm": 1.0071736682873758, + "learning_rate": 5.796026714973359e-06, + "loss": 0.8412, + "step": 7248 + }, + { + "epoch": 0.6490794112709161, + "grad_norm": 1.0351473701760932, + "learning_rate": 5.793395343592385e-06, + "loss": 0.7889, + "step": 7249 + }, + { + "epoch": 0.6491689518159942, + "grad_norm": 1.016197515940743, + "learning_rate": 5.7907643260572875e-06, + "loss": 0.8187, + "step": 7250 + }, + { + "epoch": 0.6492584923610722, + "grad_norm": 0.9696778506381909, + "learning_rate": 5.788133662589382e-06, + "loss": 0.84, + "step": 7251 + }, + { + "epoch": 0.6493480329061503, + "grad_norm": 0.94084882398586, + "learning_rate": 5.7855033534099425e-06, + "loss": 0.8667, + "step": 7252 + }, + { + "epoch": 0.6494375734512284, + "grad_norm": 0.9351150703275226, + "learning_rate": 5.7828733987402284e-06, + "loss": 0.8024, + "step": 7253 + }, + { + "epoch": 0.6495271139963065, + "grad_norm": 0.9506930238154522, + "learning_rate": 5.780243798801457e-06, + "loss": 0.8023, + "step": 7254 + }, + { + "epoch": 0.6496166545413845, + "grad_norm": 0.9114792652505668, + "learning_rate": 5.777614553814831e-06, + "loss": 0.7516, + "step": 7255 + }, + { + "epoch": 0.6497061950864625, + "grad_norm": 1.0480896483002362, + "learning_rate": 5.774985664001509e-06, + "loss": 0.8266, + "step": 7256 + }, + { + "epoch": 0.6497957356315407, + "grad_norm": 0.9926862948361596, + "learning_rate": 5.772357129582629e-06, + "loss": 0.8198, + "step": 7257 + }, + { + "epoch": 0.6498852761766187, + "grad_norm": 0.8901943400916471, + "learning_rate": 5.769728950779285e-06, + "loss": 0.8185, + "step": 7258 + }, + { + "epoch": 0.6499748167216968, + "grad_norm": 0.9875713262285745, + "learning_rate": 5.7671011278125585e-06, + "loss": 0.7837, + "step": 7259 + }, + { + "epoch": 0.6500643572667748, + "grad_norm": 0.9220289211211775, + "learning_rate": 5.764473660903487e-06, + "loss": 0.8755, + "step": 7260 + }, + { + "epoch": 0.650153897811853, + "grad_norm": 0.8803950878695499, + "learning_rate": 5.761846550273093e-06, + "loss": 0.7992, + "step": 7261 + }, + { + "epoch": 0.650243438356931, + "grad_norm": 0.927495976983483, + "learning_rate": 5.759219796142359e-06, + "loss": 0.8004, + "step": 7262 + }, + { + "epoch": 0.650332978902009, + "grad_norm": 1.4579481319230319, + "learning_rate": 5.756593398732233e-06, + "loss": 0.8024, + "step": 7263 + }, + { + "epoch": 0.6504225194470872, + "grad_norm": 1.2132165909122088, + "learning_rate": 5.753967358263643e-06, + "loss": 0.7864, + "step": 7264 + }, + { + "epoch": 0.6505120599921652, + "grad_norm": 0.9576310212225297, + "learning_rate": 5.7513416749574815e-06, + "loss": 0.7887, + "step": 7265 + }, + { + "epoch": 0.6506016005372433, + "grad_norm": 0.8860313128664239, + "learning_rate": 5.7487163490346085e-06, + "loss": 0.8131, + "step": 7266 + }, + { + "epoch": 0.6506911410823213, + "grad_norm": 1.1811899705765134, + "learning_rate": 5.746091380715868e-06, + "loss": 0.8778, + "step": 7267 + }, + { + "epoch": 0.6507806816273994, + "grad_norm": 1.0877782977768105, + "learning_rate": 5.743466770222061e-06, + "loss": 0.7988, + "step": 7268 + }, + { + "epoch": 0.6508702221724775, + "grad_norm": 1.1262100601484728, + "learning_rate": 5.740842517773956e-06, + "loss": 0.818, + "step": 7269 + }, + { + "epoch": 0.6509597627175555, + "grad_norm": 1.0768584097694722, + "learning_rate": 5.738218623592298e-06, + "loss": 0.799, + "step": 7270 + }, + { + "epoch": 0.6510493032626337, + "grad_norm": 1.1667712587143617, + "learning_rate": 5.735595087897803e-06, + "loss": 0.8638, + "step": 7271 + }, + { + "epoch": 0.6511388438077117, + "grad_norm": 0.9581948460663813, + "learning_rate": 5.732971910911152e-06, + "loss": 0.8233, + "step": 7272 + }, + { + "epoch": 0.6512283843527897, + "grad_norm": 1.0270593977740592, + "learning_rate": 5.730349092852997e-06, + "loss": 0.8239, + "step": 7273 + }, + { + "epoch": 0.6513179248978678, + "grad_norm": 0.9712164456055157, + "learning_rate": 5.727726633943964e-06, + "loss": 0.8078, + "step": 7274 + }, + { + "epoch": 0.6514074654429459, + "grad_norm": 0.9423601377653869, + "learning_rate": 5.725104534404646e-06, + "loss": 0.8135, + "step": 7275 + }, + { + "epoch": 0.651497005988024, + "grad_norm": 0.9442813646573733, + "learning_rate": 5.722482794455602e-06, + "loss": 0.8191, + "step": 7276 + }, + { + "epoch": 0.651586546533102, + "grad_norm": 0.8872418669916327, + "learning_rate": 5.719861414317367e-06, + "loss": 0.8288, + "step": 7277 + }, + { + "epoch": 0.65167608707818, + "grad_norm": 0.8626985857443107, + "learning_rate": 5.717240394210442e-06, + "loss": 0.7957, + "step": 7278 + }, + { + "epoch": 0.6517656276232582, + "grad_norm": 1.054914101541487, + "learning_rate": 5.714619734355298e-06, + "loss": 0.8814, + "step": 7279 + }, + { + "epoch": 0.6518551681683362, + "grad_norm": 0.9446433944216591, + "learning_rate": 5.711999434972378e-06, + "loss": 0.7696, + "step": 7280 + }, + { + "epoch": 0.6519447087134143, + "grad_norm": 0.8603795016955215, + "learning_rate": 5.7093794962820925e-06, + "loss": 0.749, + "step": 7281 + }, + { + "epoch": 0.6520342492584924, + "grad_norm": 1.0383504863392488, + "learning_rate": 5.7067599185048204e-06, + "loss": 0.8141, + "step": 7282 + }, + { + "epoch": 0.6521237898035704, + "grad_norm": 0.8879828846981133, + "learning_rate": 5.704140701860915e-06, + "loss": 0.7909, + "step": 7283 + }, + { + "epoch": 0.6522133303486485, + "grad_norm": 0.993997998095104, + "learning_rate": 5.701521846570695e-06, + "loss": 0.849, + "step": 7284 + }, + { + "epoch": 0.6523028708937265, + "grad_norm": 1.0302388385306116, + "learning_rate": 5.698903352854449e-06, + "loss": 0.8142, + "step": 7285 + }, + { + "epoch": 0.6523924114388047, + "grad_norm": 0.8626413153787811, + "learning_rate": 5.696285220932439e-06, + "loss": 0.7896, + "step": 7286 + }, + { + "epoch": 0.6524819519838827, + "grad_norm": 1.0077702194034917, + "learning_rate": 5.693667451024889e-06, + "loss": 0.8235, + "step": 7287 + }, + { + "epoch": 0.6525714925289607, + "grad_norm": 0.9593947820404494, + "learning_rate": 5.6910500433519995e-06, + "loss": 0.8141, + "step": 7288 + }, + { + "epoch": 0.6526610330740389, + "grad_norm": 1.0530256479896194, + "learning_rate": 5.688432998133941e-06, + "loss": 0.8382, + "step": 7289 + }, + { + "epoch": 0.6527505736191169, + "grad_norm": 1.0857446826979422, + "learning_rate": 5.685816315590848e-06, + "loss": 0.8245, + "step": 7290 + }, + { + "epoch": 0.652840114164195, + "grad_norm": 0.9081781559056147, + "learning_rate": 5.6831999959428274e-06, + "loss": 0.8588, + "step": 7291 + }, + { + "epoch": 0.652929654709273, + "grad_norm": 1.0702134686456568, + "learning_rate": 5.680584039409955e-06, + "loss": 0.7975, + "step": 7292 + }, + { + "epoch": 0.6530191952543511, + "grad_norm": 0.9725826135016893, + "learning_rate": 5.67796844621228e-06, + "loss": 0.8543, + "step": 7293 + }, + { + "epoch": 0.6531087357994292, + "grad_norm": 0.9043360823316526, + "learning_rate": 5.675353216569813e-06, + "loss": 0.833, + "step": 7294 + }, + { + "epoch": 0.6531982763445072, + "grad_norm": 1.0435938332836103, + "learning_rate": 5.6727383507025455e-06, + "loss": 0.8969, + "step": 7295 + }, + { + "epoch": 0.6532878168895853, + "grad_norm": 0.9219433006794562, + "learning_rate": 5.670123848830419e-06, + "loss": 0.8136, + "step": 7296 + }, + { + "epoch": 0.6533773574346634, + "grad_norm": 0.8801659900234023, + "learning_rate": 5.667509711173368e-06, + "loss": 0.7641, + "step": 7297 + }, + { + "epoch": 0.6534668979797414, + "grad_norm": 0.8752097531235958, + "learning_rate": 5.664895937951282e-06, + "loss": 0.8104, + "step": 7298 + }, + { + "epoch": 0.6535564385248195, + "grad_norm": 1.040426289631077, + "learning_rate": 5.662282529384022e-06, + "loss": 0.8574, + "step": 7299 + }, + { + "epoch": 0.6536459790698976, + "grad_norm": 0.9083628838296266, + "learning_rate": 5.659669485691426e-06, + "loss": 0.7939, + "step": 7300 + }, + { + "epoch": 0.6537355196149757, + "grad_norm": 0.8598224016711261, + "learning_rate": 5.657056807093284e-06, + "loss": 0.7586, + "step": 7301 + }, + { + "epoch": 0.6538250601600537, + "grad_norm": 1.2002828320899779, + "learning_rate": 5.654444493809368e-06, + "loss": 0.8542, + "step": 7302 + }, + { + "epoch": 0.6539146007051317, + "grad_norm": 0.8828257344525524, + "learning_rate": 5.6518325460594235e-06, + "loss": 0.8246, + "step": 7303 + }, + { + "epoch": 0.6540041412502099, + "grad_norm": 0.8802968442790198, + "learning_rate": 5.649220964063156e-06, + "loss": 0.8404, + "step": 7304 + }, + { + "epoch": 0.6540936817952879, + "grad_norm": 1.1403222437605716, + "learning_rate": 5.646609748040241e-06, + "loss": 0.8712, + "step": 7305 + }, + { + "epoch": 0.654183222340366, + "grad_norm": 0.924228868014137, + "learning_rate": 5.643998898210334e-06, + "loss": 0.7553, + "step": 7306 + }, + { + "epoch": 0.6542727628854441, + "grad_norm": 0.861392971177566, + "learning_rate": 5.641388414793041e-06, + "loss": 0.7965, + "step": 7307 + }, + { + "epoch": 0.6543623034305222, + "grad_norm": 0.9086766161455917, + "learning_rate": 5.638778298007947e-06, + "loss": 0.8237, + "step": 7308 + }, + { + "epoch": 0.6544518439756002, + "grad_norm": 0.9135696362139765, + "learning_rate": 5.636168548074613e-06, + "loss": 0.7975, + "step": 7309 + }, + { + "epoch": 0.6545413845206782, + "grad_norm": 0.9470629582502175, + "learning_rate": 5.633559165212561e-06, + "loss": 0.7867, + "step": 7310 + }, + { + "epoch": 0.6546309250657564, + "grad_norm": 1.0727319680281828, + "learning_rate": 5.630950149641288e-06, + "loss": 0.818, + "step": 7311 + }, + { + "epoch": 0.6547204656108344, + "grad_norm": 1.0391089595803378, + "learning_rate": 5.628341501580246e-06, + "loss": 0.8036, + "step": 7312 + }, + { + "epoch": 0.6548100061559124, + "grad_norm": 0.8858640118657765, + "learning_rate": 5.625733221248872e-06, + "loss": 0.7807, + "step": 7313 + }, + { + "epoch": 0.6548995467009905, + "grad_norm": 1.1314388010321084, + "learning_rate": 5.623125308866559e-06, + "loss": 0.84, + "step": 7314 + }, + { + "epoch": 0.6549890872460686, + "grad_norm": 1.0415218186624804, + "learning_rate": 5.620517764652688e-06, + "loss": 0.7979, + "step": 7315 + }, + { + "epoch": 0.6550786277911467, + "grad_norm": 0.9047649313690294, + "learning_rate": 5.617910588826591e-06, + "loss": 0.8513, + "step": 7316 + }, + { + "epoch": 0.6551681683362247, + "grad_norm": 0.9875673380913135, + "learning_rate": 5.61530378160758e-06, + "loss": 0.8096, + "step": 7317 + }, + { + "epoch": 0.6552577088813029, + "grad_norm": 0.9073749978676923, + "learning_rate": 5.612697343214921e-06, + "loss": 0.7871, + "step": 7318 + }, + { + "epoch": 0.6553472494263809, + "grad_norm": 0.9735949957372808, + "learning_rate": 5.610091273867864e-06, + "loss": 0.8511, + "step": 7319 + }, + { + "epoch": 0.6554367899714589, + "grad_norm": 1.05692911885129, + "learning_rate": 5.607485573785621e-06, + "loss": 0.7992, + "step": 7320 + }, + { + "epoch": 0.655526330516537, + "grad_norm": 0.8816779120713112, + "learning_rate": 5.6048802431873805e-06, + "loss": 0.8113, + "step": 7321 + }, + { + "epoch": 0.6556158710616151, + "grad_norm": 0.9116957227301384, + "learning_rate": 5.602275282292298e-06, + "loss": 0.7703, + "step": 7322 + }, + { + "epoch": 0.6557054116066932, + "grad_norm": 1.1308285974169854, + "learning_rate": 5.599670691319481e-06, + "loss": 0.8961, + "step": 7323 + }, + { + "epoch": 0.6557949521517712, + "grad_norm": 1.0660618767927528, + "learning_rate": 5.597066470488027e-06, + "loss": 0.7863, + "step": 7324 + }, + { + "epoch": 0.6558844926968493, + "grad_norm": 0.9815065313578324, + "learning_rate": 5.594462620016994e-06, + "loss": 0.8215, + "step": 7325 + }, + { + "epoch": 0.6559740332419274, + "grad_norm": 0.9316705052277169, + "learning_rate": 5.5918591401254085e-06, + "loss": 0.7851, + "step": 7326 + }, + { + "epoch": 0.6560635737870054, + "grad_norm": 0.997563720851311, + "learning_rate": 5.589256031032264e-06, + "loss": 0.8207, + "step": 7327 + }, + { + "epoch": 0.6561531143320835, + "grad_norm": 1.0479683239328443, + "learning_rate": 5.586653292956536e-06, + "loss": 0.7714, + "step": 7328 + }, + { + "epoch": 0.6562426548771616, + "grad_norm": 0.9523185888104463, + "learning_rate": 5.5840509261171486e-06, + "loss": 0.8355, + "step": 7329 + }, + { + "epoch": 0.6563321954222396, + "grad_norm": 0.9286015896025172, + "learning_rate": 5.581448930733007e-06, + "loss": 0.8496, + "step": 7330 + }, + { + "epoch": 0.6564217359673177, + "grad_norm": 0.9173572916632705, + "learning_rate": 5.578847307022981e-06, + "loss": 0.8393, + "step": 7331 + }, + { + "epoch": 0.6565112765123957, + "grad_norm": 0.857358620175035, + "learning_rate": 5.576246055205914e-06, + "loss": 0.8114, + "step": 7332 + }, + { + "epoch": 0.6566008170574739, + "grad_norm": 0.9077333187836812, + "learning_rate": 5.573645175500611e-06, + "loss": 0.7975, + "step": 7333 + }, + { + "epoch": 0.6566903576025519, + "grad_norm": 0.9581889495963095, + "learning_rate": 5.571044668125853e-06, + "loss": 0.8214, + "step": 7334 + }, + { + "epoch": 0.6567798981476299, + "grad_norm": 0.920453248188504, + "learning_rate": 5.568444533300385e-06, + "loss": 0.8618, + "step": 7335 + }, + { + "epoch": 0.6568694386927081, + "grad_norm": 0.9550485409666128, + "learning_rate": 5.565844771242922e-06, + "loss": 0.822, + "step": 7336 + }, + { + "epoch": 0.6569589792377861, + "grad_norm": 0.9996630610352414, + "learning_rate": 5.563245382172147e-06, + "loss": 0.7952, + "step": 7337 + }, + { + "epoch": 0.6570485197828642, + "grad_norm": 0.9356980566323745, + "learning_rate": 5.560646366306712e-06, + "loss": 0.8154, + "step": 7338 + }, + { + "epoch": 0.6571380603279422, + "grad_norm": 1.0726701922099506, + "learning_rate": 5.558047723865239e-06, + "loss": 0.7855, + "step": 7339 + }, + { + "epoch": 0.6572276008730203, + "grad_norm": 1.0545881007799642, + "learning_rate": 5.555449455066315e-06, + "loss": 0.7662, + "step": 7340 + }, + { + "epoch": 0.6573171414180984, + "grad_norm": 1.073182487184013, + "learning_rate": 5.5528515601285e-06, + "loss": 0.807, + "step": 7341 + }, + { + "epoch": 0.6574066819631764, + "grad_norm": 0.9233745154352145, + "learning_rate": 5.550254039270319e-06, + "loss": 0.8548, + "step": 7342 + }, + { + "epoch": 0.6574962225082546, + "grad_norm": 1.1331102846919707, + "learning_rate": 5.5476568927102695e-06, + "loss": 0.8148, + "step": 7343 + }, + { + "epoch": 0.6575857630533326, + "grad_norm": 0.9484729438441103, + "learning_rate": 5.545060120666812e-06, + "loss": 0.7938, + "step": 7344 + }, + { + "epoch": 0.6576753035984106, + "grad_norm": 1.0418646396880868, + "learning_rate": 5.542463723358381e-06, + "loss": 0.7911, + "step": 7345 + }, + { + "epoch": 0.6577648441434887, + "grad_norm": 0.9366589963970824, + "learning_rate": 5.539867701003375e-06, + "loss": 0.8214, + "step": 7346 + }, + { + "epoch": 0.6578543846885668, + "grad_norm": 1.005938824071756, + "learning_rate": 5.537272053820164e-06, + "loss": 0.7835, + "step": 7347 + }, + { + "epoch": 0.6579439252336449, + "grad_norm": 0.9463366603634388, + "learning_rate": 5.534676782027085e-06, + "loss": 0.8174, + "step": 7348 + }, + { + "epoch": 0.6580334657787229, + "grad_norm": 0.8785162720719428, + "learning_rate": 5.532081885842448e-06, + "loss": 0.7461, + "step": 7349 + }, + { + "epoch": 0.6581230063238009, + "grad_norm": 0.912922919231555, + "learning_rate": 5.529487365484516e-06, + "loss": 0.6957, + "step": 7350 + }, + { + "epoch": 0.6582125468688791, + "grad_norm": 0.9390820851009614, + "learning_rate": 5.5268932211715405e-06, + "loss": 0.761, + "step": 7351 + }, + { + "epoch": 0.6583020874139571, + "grad_norm": 0.9343757444995957, + "learning_rate": 5.524299453121733e-06, + "loss": 0.7784, + "step": 7352 + }, + { + "epoch": 0.6583916279590352, + "grad_norm": 0.8952348721815246, + "learning_rate": 5.521706061553269e-06, + "loss": 0.7844, + "step": 7353 + }, + { + "epoch": 0.6584811685041133, + "grad_norm": 0.9362303813039331, + "learning_rate": 5.519113046684299e-06, + "loss": 0.7859, + "step": 7354 + }, + { + "epoch": 0.6585707090491913, + "grad_norm": 0.97334749441531, + "learning_rate": 5.51652040873294e-06, + "loss": 0.8309, + "step": 7355 + }, + { + "epoch": 0.6586602495942694, + "grad_norm": 0.925735718346601, + "learning_rate": 5.513928147917267e-06, + "loss": 0.7839, + "step": 7356 + }, + { + "epoch": 0.6587497901393474, + "grad_norm": 0.9905775656146384, + "learning_rate": 5.511336264455342e-06, + "loss": 0.8016, + "step": 7357 + }, + { + "epoch": 0.6588393306844256, + "grad_norm": 0.9238283605969263, + "learning_rate": 5.5087447585651855e-06, + "loss": 0.8087, + "step": 7358 + }, + { + "epoch": 0.6589288712295036, + "grad_norm": 0.9086216972085446, + "learning_rate": 5.5061536304647835e-06, + "loss": 0.8004, + "step": 7359 + }, + { + "epoch": 0.6590184117745816, + "grad_norm": 0.9595912388366051, + "learning_rate": 5.5035628803720975e-06, + "loss": 0.826, + "step": 7360 + }, + { + "epoch": 0.6591079523196598, + "grad_norm": 1.0393704241714115, + "learning_rate": 5.500972508505044e-06, + "loss": 0.8234, + "step": 7361 + }, + { + "epoch": 0.6591974928647378, + "grad_norm": 1.02795833513756, + "learning_rate": 5.498382515081522e-06, + "loss": 0.8097, + "step": 7362 + }, + { + "epoch": 0.6592870334098159, + "grad_norm": 0.9272335499815851, + "learning_rate": 5.495792900319394e-06, + "loss": 0.8145, + "step": 7363 + }, + { + "epoch": 0.6593765739548939, + "grad_norm": 0.8750219249462865, + "learning_rate": 5.49320366443649e-06, + "loss": 0.8318, + "step": 7364 + }, + { + "epoch": 0.6594661144999721, + "grad_norm": 0.9796148929627807, + "learning_rate": 5.490614807650608e-06, + "loss": 0.7887, + "step": 7365 + }, + { + "epoch": 0.6595556550450501, + "grad_norm": 0.9348057511564736, + "learning_rate": 5.488026330179518e-06, + "loss": 0.787, + "step": 7366 + }, + { + "epoch": 0.6596451955901281, + "grad_norm": 0.9453429997748579, + "learning_rate": 5.485438232240945e-06, + "loss": 0.7794, + "step": 7367 + }, + { + "epoch": 0.6597347361352062, + "grad_norm": 1.068253877384166, + "learning_rate": 5.4828505140525934e-06, + "loss": 0.79, + "step": 7368 + }, + { + "epoch": 0.6598242766802843, + "grad_norm": 1.0380227832377775, + "learning_rate": 5.480263175832139e-06, + "loss": 0.8142, + "step": 7369 + }, + { + "epoch": 0.6599138172253624, + "grad_norm": 0.9372313527571041, + "learning_rate": 5.477676217797219e-06, + "loss": 0.8475, + "step": 7370 + }, + { + "epoch": 0.6600033577704404, + "grad_norm": 0.9346860805213398, + "learning_rate": 5.475089640165442e-06, + "loss": 0.8564, + "step": 7371 + }, + { + "epoch": 0.6600928983155185, + "grad_norm": 0.8790765893486525, + "learning_rate": 5.4725034431543756e-06, + "loss": 0.7789, + "step": 7372 + }, + { + "epoch": 0.6601824388605966, + "grad_norm": 0.975050367019759, + "learning_rate": 5.469917626981565e-06, + "loss": 0.8363, + "step": 7373 + }, + { + "epoch": 0.6602719794056746, + "grad_norm": 0.9341446083390239, + "learning_rate": 5.467332191864518e-06, + "loss": 0.8228, + "step": 7374 + }, + { + "epoch": 0.6603615199507527, + "grad_norm": 1.0216750756924287, + "learning_rate": 5.464747138020721e-06, + "loss": 0.8228, + "step": 7375 + }, + { + "epoch": 0.6604510604958308, + "grad_norm": 0.9535301817885083, + "learning_rate": 5.462162465667614e-06, + "loss": 0.8317, + "step": 7376 + }, + { + "epoch": 0.6605406010409088, + "grad_norm": 1.0612222195749201, + "learning_rate": 5.459578175022617e-06, + "loss": 0.8887, + "step": 7377 + }, + { + "epoch": 0.6606301415859869, + "grad_norm": 1.0040719151911934, + "learning_rate": 5.456994266303106e-06, + "loss": 0.8495, + "step": 7378 + }, + { + "epoch": 0.660719682131065, + "grad_norm": 0.9258434973711982, + "learning_rate": 5.454410739726432e-06, + "loss": 0.8124, + "step": 7379 + }, + { + "epoch": 0.6608092226761431, + "grad_norm": 0.9208020724616062, + "learning_rate": 5.451827595509913e-06, + "loss": 0.8114, + "step": 7380 + }, + { + "epoch": 0.6608987632212211, + "grad_norm": 1.07516496174586, + "learning_rate": 5.449244833870833e-06, + "loss": 0.8055, + "step": 7381 + }, + { + "epoch": 0.6609883037662991, + "grad_norm": 0.8967501594127987, + "learning_rate": 5.446662455026454e-06, + "loss": 0.7525, + "step": 7382 + }, + { + "epoch": 0.6610778443113773, + "grad_norm": 0.9244881211489062, + "learning_rate": 5.44408045919399e-06, + "loss": 0.7816, + "step": 7383 + }, + { + "epoch": 0.6611673848564553, + "grad_norm": 0.9281095189801799, + "learning_rate": 5.441498846590629e-06, + "loss": 0.8198, + "step": 7384 + }, + { + "epoch": 0.6612569254015334, + "grad_norm": 1.0485567872463224, + "learning_rate": 5.438917617433532e-06, + "loss": 0.8423, + "step": 7385 + }, + { + "epoch": 0.6613464659466114, + "grad_norm": 0.9064092006717579, + "learning_rate": 5.436336771939821e-06, + "loss": 0.8123, + "step": 7386 + }, + { + "epoch": 0.6614360064916895, + "grad_norm": 1.0272951103997416, + "learning_rate": 5.433756310326586e-06, + "loss": 0.8108, + "step": 7387 + }, + { + "epoch": 0.6615255470367676, + "grad_norm": 0.9531636994194864, + "learning_rate": 5.431176232810898e-06, + "loss": 0.8352, + "step": 7388 + }, + { + "epoch": 0.6616150875818456, + "grad_norm": 0.9323118695868394, + "learning_rate": 5.428596539609772e-06, + "loss": 0.7742, + "step": 7389 + }, + { + "epoch": 0.6617046281269238, + "grad_norm": 0.9803015530768365, + "learning_rate": 5.4260172309402085e-06, + "loss": 0.8335, + "step": 7390 + }, + { + "epoch": 0.6617941686720018, + "grad_norm": 0.9418941710611308, + "learning_rate": 5.423438307019169e-06, + "loss": 0.8281, + "step": 7391 + }, + { + "epoch": 0.6618837092170798, + "grad_norm": 0.9845151213632618, + "learning_rate": 5.4208597680635866e-06, + "loss": 0.8257, + "step": 7392 + }, + { + "epoch": 0.6619732497621579, + "grad_norm": 1.0003396445470178, + "learning_rate": 5.418281614290359e-06, + "loss": 0.7762, + "step": 7393 + }, + { + "epoch": 0.662062790307236, + "grad_norm": 1.0231459160384764, + "learning_rate": 5.4157038459163515e-06, + "loss": 0.8461, + "step": 7394 + }, + { + "epoch": 0.6621523308523141, + "grad_norm": 1.148048352112647, + "learning_rate": 5.413126463158396e-06, + "loss": 0.8049, + "step": 7395 + }, + { + "epoch": 0.6622418713973921, + "grad_norm": 0.9039517470063846, + "learning_rate": 5.410549466233297e-06, + "loss": 0.797, + "step": 7396 + }, + { + "epoch": 0.6623314119424702, + "grad_norm": 0.9367403668381581, + "learning_rate": 5.407972855357819e-06, + "loss": 0.8003, + "step": 7397 + }, + { + "epoch": 0.6624209524875483, + "grad_norm": 0.9250594654974407, + "learning_rate": 5.405396630748702e-06, + "loss": 0.8773, + "step": 7398 + }, + { + "epoch": 0.6625104930326263, + "grad_norm": 0.9361369106503858, + "learning_rate": 5.402820792622649e-06, + "loss": 0.8627, + "step": 7399 + }, + { + "epoch": 0.6626000335777044, + "grad_norm": 1.0570686595577783, + "learning_rate": 5.400245341196328e-06, + "loss": 0.8532, + "step": 7400 + }, + { + "epoch": 0.6626895741227825, + "grad_norm": 1.0686440827197978, + "learning_rate": 5.397670276686382e-06, + "loss": 0.8126, + "step": 7401 + }, + { + "epoch": 0.6627791146678605, + "grad_norm": 1.0660252880584309, + "learning_rate": 5.395095599309413e-06, + "loss": 0.8324, + "step": 7402 + }, + { + "epoch": 0.6628686552129386, + "grad_norm": 0.9822559808903727, + "learning_rate": 5.3925213092819965e-06, + "loss": 0.7998, + "step": 7403 + }, + { + "epoch": 0.6629581957580166, + "grad_norm": 0.8760922304305017, + "learning_rate": 5.3899474068206725e-06, + "loss": 0.7846, + "step": 7404 + }, + { + "epoch": 0.6630477363030948, + "grad_norm": 1.196021242665968, + "learning_rate": 5.387373892141951e-06, + "loss": 0.8572, + "step": 7405 + }, + { + "epoch": 0.6631372768481728, + "grad_norm": 0.937323005649023, + "learning_rate": 5.384800765462306e-06, + "loss": 0.8224, + "step": 7406 + }, + { + "epoch": 0.6632268173932508, + "grad_norm": 0.9594156966736437, + "learning_rate": 5.38222802699818e-06, + "loss": 0.8823, + "step": 7407 + }, + { + "epoch": 0.663316357938329, + "grad_norm": 0.9240782072387356, + "learning_rate": 5.379655676965984e-06, + "loss": 0.8021, + "step": 7408 + }, + { + "epoch": 0.663405898483407, + "grad_norm": 1.103379866416763, + "learning_rate": 5.377083715582099e-06, + "loss": 0.841, + "step": 7409 + }, + { + "epoch": 0.6634954390284851, + "grad_norm": 0.9378425975227233, + "learning_rate": 5.374512143062866e-06, + "loss": 0.8633, + "step": 7410 + }, + { + "epoch": 0.6635849795735631, + "grad_norm": 0.9839088072058982, + "learning_rate": 5.371940959624597e-06, + "loss": 0.7524, + "step": 7411 + }, + { + "epoch": 0.6636745201186413, + "grad_norm": 1.0283064649620686, + "learning_rate": 5.3693701654835735e-06, + "loss": 0.8125, + "step": 7412 + }, + { + "epoch": 0.6637640606637193, + "grad_norm": 0.9561122233175984, + "learning_rate": 5.366799760856043e-06, + "loss": 0.8867, + "step": 7413 + }, + { + "epoch": 0.6638536012087973, + "grad_norm": 0.9094966346450513, + "learning_rate": 5.364229745958218e-06, + "loss": 0.7903, + "step": 7414 + }, + { + "epoch": 0.6639431417538755, + "grad_norm": 0.9375052478403006, + "learning_rate": 5.361660121006284e-06, + "loss": 0.8034, + "step": 7415 + }, + { + "epoch": 0.6640326822989535, + "grad_norm": 1.0156641108497368, + "learning_rate": 5.359090886216377e-06, + "loss": 0.7981, + "step": 7416 + }, + { + "epoch": 0.6641222228440316, + "grad_norm": 0.990134380946852, + "learning_rate": 5.356522041804626e-06, + "loss": 0.8524, + "step": 7417 + }, + { + "epoch": 0.6642117633891096, + "grad_norm": 0.9710696815249935, + "learning_rate": 5.353953587987109e-06, + "loss": 0.8195, + "step": 7418 + }, + { + "epoch": 0.6643013039341877, + "grad_norm": 0.9889608822371967, + "learning_rate": 5.351385524979876e-06, + "loss": 0.7835, + "step": 7419 + }, + { + "epoch": 0.6643908444792658, + "grad_norm": 0.9702546289702244, + "learning_rate": 5.348817852998949e-06, + "loss": 0.8224, + "step": 7420 + }, + { + "epoch": 0.6644803850243438, + "grad_norm": 0.9923977026236258, + "learning_rate": 5.346250572260302e-06, + "loss": 0.78, + "step": 7421 + }, + { + "epoch": 0.6645699255694218, + "grad_norm": 1.0137221815382094, + "learning_rate": 5.343683682979888e-06, + "loss": 0.8515, + "step": 7422 + }, + { + "epoch": 0.6646594661145, + "grad_norm": 0.9959043052367144, + "learning_rate": 5.341117185373634e-06, + "loss": 0.7979, + "step": 7423 + }, + { + "epoch": 0.664749006659578, + "grad_norm": 0.9258300976257043, + "learning_rate": 5.338551079657419e-06, + "loss": 0.8231, + "step": 7424 + }, + { + "epoch": 0.6648385472046561, + "grad_norm": 1.0122937954894073, + "learning_rate": 5.335985366047098e-06, + "loss": 0.8322, + "step": 7425 + }, + { + "epoch": 0.6649280877497342, + "grad_norm": 0.8692660357547991, + "learning_rate": 5.3334200447584925e-06, + "loss": 0.8363, + "step": 7426 + }, + { + "epoch": 0.6650176282948123, + "grad_norm": 0.9662689035173921, + "learning_rate": 5.330855116007383e-06, + "loss": 0.8617, + "step": 7427 + }, + { + "epoch": 0.6651071688398903, + "grad_norm": 1.0555477563212419, + "learning_rate": 5.328290580009521e-06, + "loss": 0.8572, + "step": 7428 + }, + { + "epoch": 0.6651967093849683, + "grad_norm": 0.9278839810834268, + "learning_rate": 5.325726436980636e-06, + "loss": 0.778, + "step": 7429 + }, + { + "epoch": 0.6652862499300465, + "grad_norm": 0.9520589004017551, + "learning_rate": 5.32316268713641e-06, + "loss": 0.8313, + "step": 7430 + }, + { + "epoch": 0.6653757904751245, + "grad_norm": 0.964236093657248, + "learning_rate": 5.320599330692504e-06, + "loss": 0.8138, + "step": 7431 + }, + { + "epoch": 0.6654653310202026, + "grad_norm": 0.8835533186185465, + "learning_rate": 5.3180363678645285e-06, + "loss": 0.806, + "step": 7432 + }, + { + "epoch": 0.6655548715652807, + "grad_norm": 0.9188977601670071, + "learning_rate": 5.315473798868076e-06, + "loss": 0.8231, + "step": 7433 + }, + { + "epoch": 0.6656444121103587, + "grad_norm": 0.9848968220683548, + "learning_rate": 5.312911623918704e-06, + "loss": 0.7825, + "step": 7434 + }, + { + "epoch": 0.6657339526554368, + "grad_norm": 0.9161923475666346, + "learning_rate": 5.310349843231926e-06, + "loss": 0.832, + "step": 7435 + }, + { + "epoch": 0.6658234932005148, + "grad_norm": 0.9961997730664517, + "learning_rate": 5.307788457023243e-06, + "loss": 0.8295, + "step": 7436 + }, + { + "epoch": 0.665913033745593, + "grad_norm": 1.0153435195784282, + "learning_rate": 5.305227465508107e-06, + "loss": 0.8045, + "step": 7437 + }, + { + "epoch": 0.666002574290671, + "grad_norm": 1.1160008437698334, + "learning_rate": 5.302666868901936e-06, + "loss": 0.856, + "step": 7438 + }, + { + "epoch": 0.666092114835749, + "grad_norm": 1.1498082171922674, + "learning_rate": 5.300106667420118e-06, + "loss": 0.7827, + "step": 7439 + }, + { + "epoch": 0.6661816553808271, + "grad_norm": 0.9583276176036425, + "learning_rate": 5.297546861278013e-06, + "loss": 0.8602, + "step": 7440 + }, + { + "epoch": 0.6662711959259052, + "grad_norm": 0.9778976042348785, + "learning_rate": 5.2949874506909385e-06, + "loss": 0.8518, + "step": 7441 + }, + { + "epoch": 0.6663607364709833, + "grad_norm": 0.935504297809276, + "learning_rate": 5.292428435874195e-06, + "loss": 0.7922, + "step": 7442 + }, + { + "epoch": 0.6664502770160613, + "grad_norm": 1.0672104663771147, + "learning_rate": 5.289869817043026e-06, + "loss": 0.762, + "step": 7443 + }, + { + "epoch": 0.6665398175611394, + "grad_norm": 0.9363078994811208, + "learning_rate": 5.2873115944126606e-06, + "loss": 0.7891, + "step": 7444 + }, + { + "epoch": 0.6666293581062175, + "grad_norm": 1.1372459074536938, + "learning_rate": 5.284753768198285e-06, + "loss": 0.8297, + "step": 7445 + }, + { + "epoch": 0.6667188986512955, + "grad_norm": 1.1146322193239877, + "learning_rate": 5.282196338615058e-06, + "loss": 0.8785, + "step": 7446 + }, + { + "epoch": 0.6668084391963736, + "grad_norm": 0.910814751170856, + "learning_rate": 5.279639305878097e-06, + "loss": 0.806, + "step": 7447 + }, + { + "epoch": 0.6668979797414517, + "grad_norm": 1.0879951855120666, + "learning_rate": 5.2770826702025026e-06, + "loss": 0.8098, + "step": 7448 + }, + { + "epoch": 0.6669875202865297, + "grad_norm": 0.9997031961300487, + "learning_rate": 5.274526431803319e-06, + "loss": 0.8259, + "step": 7449 + }, + { + "epoch": 0.6670770608316078, + "grad_norm": 0.9030495880992627, + "learning_rate": 5.271970590895575e-06, + "loss": 0.8347, + "step": 7450 + }, + { + "epoch": 0.6671666013766859, + "grad_norm": 0.9516472055111511, + "learning_rate": 5.269415147694257e-06, + "loss": 0.8108, + "step": 7451 + }, + { + "epoch": 0.667256141921764, + "grad_norm": 1.0032231346281724, + "learning_rate": 5.266860102414319e-06, + "loss": 0.7891, + "step": 7452 + }, + { + "epoch": 0.667345682466842, + "grad_norm": 1.0672145005540397, + "learning_rate": 5.2643054552706886e-06, + "loss": 0.7555, + "step": 7453 + }, + { + "epoch": 0.66743522301192, + "grad_norm": 0.9194535133331326, + "learning_rate": 5.26175120647825e-06, + "loss": 0.8336, + "step": 7454 + }, + { + "epoch": 0.6675247635569982, + "grad_norm": 1.0245375535142969, + "learning_rate": 5.259197356251857e-06, + "loss": 0.7985, + "step": 7455 + }, + { + "epoch": 0.6676143041020762, + "grad_norm": 1.0146071621606474, + "learning_rate": 5.256643904806335e-06, + "loss": 0.7828, + "step": 7456 + }, + { + "epoch": 0.6677038446471543, + "grad_norm": 1.007079229211384, + "learning_rate": 5.254090852356473e-06, + "loss": 0.8687, + "step": 7457 + }, + { + "epoch": 0.6677933851922323, + "grad_norm": 0.9560089345908145, + "learning_rate": 5.251538199117019e-06, + "loss": 0.8076, + "step": 7458 + }, + { + "epoch": 0.6678829257373105, + "grad_norm": 0.9064796277733639, + "learning_rate": 5.2489859453027e-06, + "loss": 0.8397, + "step": 7459 + }, + { + "epoch": 0.6679724662823885, + "grad_norm": 0.9507284224000625, + "learning_rate": 5.2464340911282005e-06, + "loss": 0.877, + "step": 7460 + }, + { + "epoch": 0.6680620068274665, + "grad_norm": 0.9925223455270268, + "learning_rate": 5.243882636808175e-06, + "loss": 0.8553, + "step": 7461 + }, + { + "epoch": 0.6681515473725447, + "grad_norm": 0.9320338382056615, + "learning_rate": 5.241331582557244e-06, + "loss": 0.8152, + "step": 7462 + }, + { + "epoch": 0.6682410879176227, + "grad_norm": 1.0672021840139518, + "learning_rate": 5.238780928589992e-06, + "loss": 0.8128, + "step": 7463 + }, + { + "epoch": 0.6683306284627007, + "grad_norm": 1.0342361305984835, + "learning_rate": 5.2362306751209745e-06, + "loss": 0.858, + "step": 7464 + }, + { + "epoch": 0.6684201690077788, + "grad_norm": 1.0742472055273755, + "learning_rate": 5.233680822364708e-06, + "loss": 0.7745, + "step": 7465 + }, + { + "epoch": 0.6685097095528569, + "grad_norm": 0.9156740426985743, + "learning_rate": 5.231131370535678e-06, + "loss": 0.7509, + "step": 7466 + }, + { + "epoch": 0.668599250097935, + "grad_norm": 1.044312950847101, + "learning_rate": 5.228582319848338e-06, + "loss": 0.851, + "step": 7467 + }, + { + "epoch": 0.668688790643013, + "grad_norm": 0.997023360533407, + "learning_rate": 5.226033670517104e-06, + "loss": 0.8289, + "step": 7468 + }, + { + "epoch": 0.6687783311880912, + "grad_norm": 0.9026166514642375, + "learning_rate": 5.2234854227563605e-06, + "loss": 0.8204, + "step": 7469 + }, + { + "epoch": 0.6688678717331692, + "grad_norm": 0.9300533345495118, + "learning_rate": 5.220937576780458e-06, + "loss": 0.8679, + "step": 7470 + }, + { + "epoch": 0.6689574122782472, + "grad_norm": 0.887498342420645, + "learning_rate": 5.218390132803715e-06, + "loss": 0.8381, + "step": 7471 + }, + { + "epoch": 0.6690469528233253, + "grad_norm": 0.9994265287385279, + "learning_rate": 5.215843091040409e-06, + "loss": 0.814, + "step": 7472 + }, + { + "epoch": 0.6691364933684034, + "grad_norm": 1.0229330462446404, + "learning_rate": 5.213296451704794e-06, + "loss": 0.8132, + "step": 7473 + }, + { + "epoch": 0.6692260339134815, + "grad_norm": 0.8760383238576165, + "learning_rate": 5.210750215011082e-06, + "loss": 0.8303, + "step": 7474 + }, + { + "epoch": 0.6693155744585595, + "grad_norm": 0.9215127312523042, + "learning_rate": 5.20820438117346e-06, + "loss": 0.7983, + "step": 7475 + }, + { + "epoch": 0.6694051150036375, + "grad_norm": 1.0585305059620385, + "learning_rate": 5.205658950406062e-06, + "loss": 0.8278, + "step": 7476 + }, + { + "epoch": 0.6694946555487157, + "grad_norm": 0.9146819254230831, + "learning_rate": 5.203113922923013e-06, + "loss": 0.7584, + "step": 7477 + }, + { + "epoch": 0.6695841960937937, + "grad_norm": 0.8999781515085166, + "learning_rate": 5.2005692989383906e-06, + "loss": 0.8531, + "step": 7478 + }, + { + "epoch": 0.6696737366388718, + "grad_norm": 1.058164729069856, + "learning_rate": 5.198025078666238e-06, + "loss": 0.8349, + "step": 7479 + }, + { + "epoch": 0.6697632771839499, + "grad_norm": 0.9490043094538922, + "learning_rate": 5.195481262320572e-06, + "loss": 0.8558, + "step": 7480 + }, + { + "epoch": 0.6698528177290279, + "grad_norm": 0.955446385343134, + "learning_rate": 5.1929378501153605e-06, + "loss": 0.8335, + "step": 7481 + }, + { + "epoch": 0.669942358274106, + "grad_norm": 1.038726251441477, + "learning_rate": 5.1903948422645504e-06, + "loss": 0.8178, + "step": 7482 + }, + { + "epoch": 0.670031898819184, + "grad_norm": 0.9287181574941412, + "learning_rate": 5.1878522389820564e-06, + "loss": 0.7642, + "step": 7483 + }, + { + "epoch": 0.6701214393642622, + "grad_norm": 0.9212863177157766, + "learning_rate": 5.18531004048175e-06, + "loss": 0.8077, + "step": 7484 + }, + { + "epoch": 0.6702109799093402, + "grad_norm": 1.1388234273804994, + "learning_rate": 5.1827682469774734e-06, + "loss": 0.8636, + "step": 7485 + }, + { + "epoch": 0.6703005204544182, + "grad_norm": 1.0371924260488867, + "learning_rate": 5.180226858683037e-06, + "loss": 0.8238, + "step": 7486 + }, + { + "epoch": 0.6703900609994964, + "grad_norm": 0.8976472394533889, + "learning_rate": 5.177685875812208e-06, + "loss": 0.8342, + "step": 7487 + }, + { + "epoch": 0.6704796015445744, + "grad_norm": 1.0051818038805378, + "learning_rate": 5.17514529857873e-06, + "loss": 0.8455, + "step": 7488 + }, + { + "epoch": 0.6705691420896525, + "grad_norm": 0.9237004532306378, + "learning_rate": 5.1726051271963015e-06, + "loss": 0.8098, + "step": 7489 + }, + { + "epoch": 0.6706586826347305, + "grad_norm": 0.9706467095901712, + "learning_rate": 5.170065361878603e-06, + "loss": 0.7624, + "step": 7490 + }, + { + "epoch": 0.6707482231798086, + "grad_norm": 0.9171849596374392, + "learning_rate": 5.167526002839269e-06, + "loss": 0.8188, + "step": 7491 + }, + { + "epoch": 0.6708377637248867, + "grad_norm": 0.8471845347852861, + "learning_rate": 5.1649870502918985e-06, + "loss": 0.7975, + "step": 7492 + }, + { + "epoch": 0.6709273042699647, + "grad_norm": 1.016625239331802, + "learning_rate": 5.1624485044500605e-06, + "loss": 0.756, + "step": 7493 + }, + { + "epoch": 0.6710168448150428, + "grad_norm": 0.9335033752202787, + "learning_rate": 5.15991036552729e-06, + "loss": 0.7968, + "step": 7494 + }, + { + "epoch": 0.6711063853601209, + "grad_norm": 0.9242766071517782, + "learning_rate": 5.157372633737083e-06, + "loss": 0.8168, + "step": 7495 + }, + { + "epoch": 0.6711959259051989, + "grad_norm": 1.0171395304765374, + "learning_rate": 5.1548353092929136e-06, + "loss": 0.804, + "step": 7496 + }, + { + "epoch": 0.671285466450277, + "grad_norm": 0.9029617088719335, + "learning_rate": 5.152298392408214e-06, + "loss": 0.8441, + "step": 7497 + }, + { + "epoch": 0.6713750069953551, + "grad_norm": 0.9249425769070901, + "learning_rate": 5.149761883296371e-06, + "loss": 0.7588, + "step": 7498 + }, + { + "epoch": 0.6714645475404332, + "grad_norm": 1.0316346555021108, + "learning_rate": 5.1472257821707535e-06, + "loss": 0.777, + "step": 7499 + }, + { + "epoch": 0.6715540880855112, + "grad_norm": 0.9954084167613391, + "learning_rate": 5.144690089244689e-06, + "loss": 0.8317, + "step": 7500 + }, + { + "epoch": 0.6716436286305892, + "grad_norm": 0.9314948110388149, + "learning_rate": 5.142154804731469e-06, + "loss": 0.7828, + "step": 7501 + }, + { + "epoch": 0.6717331691756674, + "grad_norm": 1.0439696949968391, + "learning_rate": 5.139619928844364e-06, + "loss": 0.7926, + "step": 7502 + }, + { + "epoch": 0.6718227097207454, + "grad_norm": 1.0055186706159907, + "learning_rate": 5.137085461796588e-06, + "loss": 0.8162, + "step": 7503 + }, + { + "epoch": 0.6719122502658235, + "grad_norm": 0.9531468359933698, + "learning_rate": 5.134551403801336e-06, + "loss": 0.814, + "step": 7504 + }, + { + "epoch": 0.6720017908109016, + "grad_norm": 0.9346789551081877, + "learning_rate": 5.132017755071765e-06, + "loss": 0.8596, + "step": 7505 + }, + { + "epoch": 0.6720913313559796, + "grad_norm": 0.9810943822605321, + "learning_rate": 5.129484515820998e-06, + "loss": 0.8174, + "step": 7506 + }, + { + "epoch": 0.6721808719010577, + "grad_norm": 0.9382684512531585, + "learning_rate": 5.126951686262117e-06, + "loss": 0.7857, + "step": 7507 + }, + { + "epoch": 0.6722704124461357, + "grad_norm": 1.017698161369508, + "learning_rate": 5.124419266608189e-06, + "loss": 0.8067, + "step": 7508 + }, + { + "epoch": 0.6723599529912139, + "grad_norm": 0.9317609377325201, + "learning_rate": 5.12188725707222e-06, + "loss": 0.8028, + "step": 7509 + }, + { + "epoch": 0.6724494935362919, + "grad_norm": 2.204019561288505, + "learning_rate": 5.1193556578671975e-06, + "loss": 0.8299, + "step": 7510 + }, + { + "epoch": 0.67253903408137, + "grad_norm": 0.9608891975316171, + "learning_rate": 5.116824469206074e-06, + "loss": 0.8108, + "step": 7511 + }, + { + "epoch": 0.672628574626448, + "grad_norm": 0.9592661850599546, + "learning_rate": 5.114293691301763e-06, + "loss": 0.7898, + "step": 7512 + }, + { + "epoch": 0.6727181151715261, + "grad_norm": 0.8534904469281832, + "learning_rate": 5.111763324367145e-06, + "loss": 0.7313, + "step": 7513 + }, + { + "epoch": 0.6728076557166042, + "grad_norm": 0.9547537367829539, + "learning_rate": 5.109233368615067e-06, + "loss": 0.8272, + "step": 7514 + }, + { + "epoch": 0.6728971962616822, + "grad_norm": 0.9204370604994293, + "learning_rate": 5.106703824258341e-06, + "loss": 0.8234, + "step": 7515 + }, + { + "epoch": 0.6729867368067604, + "grad_norm": 1.0066684713887253, + "learning_rate": 5.104174691509743e-06, + "loss": 0.8718, + "step": 7516 + }, + { + "epoch": 0.6730762773518384, + "grad_norm": 0.9002281534564198, + "learning_rate": 5.101645970582017e-06, + "loss": 0.8566, + "step": 7517 + }, + { + "epoch": 0.6731658178969164, + "grad_norm": 0.9639191628074935, + "learning_rate": 5.099117661687868e-06, + "loss": 0.8473, + "step": 7518 + }, + { + "epoch": 0.6732553584419945, + "grad_norm": 1.0826106820159531, + "learning_rate": 5.096589765039972e-06, + "loss": 0.8362, + "step": 7519 + }, + { + "epoch": 0.6733448989870726, + "grad_norm": 1.2107454223334093, + "learning_rate": 5.0940622808509645e-06, + "loss": 0.8497, + "step": 7520 + }, + { + "epoch": 0.6734344395321507, + "grad_norm": 0.9917261812284213, + "learning_rate": 5.091535209333453e-06, + "loss": 0.8256, + "step": 7521 + }, + { + "epoch": 0.6735239800772287, + "grad_norm": 0.890952544661504, + "learning_rate": 5.089008550700003e-06, + "loss": 0.8132, + "step": 7522 + }, + { + "epoch": 0.6736135206223068, + "grad_norm": 1.1269947104198972, + "learning_rate": 5.086482305163152e-06, + "loss": 0.7769, + "step": 7523 + }, + { + "epoch": 0.6737030611673849, + "grad_norm": 1.027993473330337, + "learning_rate": 5.083956472935397e-06, + "loss": 0.7511, + "step": 7524 + }, + { + "epoch": 0.6737926017124629, + "grad_norm": 0.9969078447399685, + "learning_rate": 5.081431054229202e-06, + "loss": 0.7811, + "step": 7525 + }, + { + "epoch": 0.673882142257541, + "grad_norm": 0.8810772464371397, + "learning_rate": 5.078906049257e-06, + "loss": 0.7871, + "step": 7526 + }, + { + "epoch": 0.6739716828026191, + "grad_norm": 0.9474611161696102, + "learning_rate": 5.076381458231185e-06, + "loss": 0.8011, + "step": 7527 + }, + { + "epoch": 0.6740612233476971, + "grad_norm": 0.9252084659679431, + "learning_rate": 5.073857281364116e-06, + "loss": 0.8167, + "step": 7528 + }, + { + "epoch": 0.6741507638927752, + "grad_norm": 0.9965973227698414, + "learning_rate": 5.07133351886812e-06, + "loss": 0.7971, + "step": 7529 + }, + { + "epoch": 0.6742403044378532, + "grad_norm": 1.1247928276409016, + "learning_rate": 5.068810170955487e-06, + "loss": 0.8136, + "step": 7530 + }, + { + "epoch": 0.6743298449829314, + "grad_norm": 0.9034461762130201, + "learning_rate": 5.066287237838474e-06, + "loss": 0.8632, + "step": 7531 + }, + { + "epoch": 0.6744193855280094, + "grad_norm": 0.9173709650549339, + "learning_rate": 5.063764719729301e-06, + "loss": 0.769, + "step": 7532 + }, + { + "epoch": 0.6745089260730874, + "grad_norm": 0.916455163389593, + "learning_rate": 5.061242616840154e-06, + "loss": 0.8209, + "step": 7533 + }, + { + "epoch": 0.6745984666181656, + "grad_norm": 1.0292300635573934, + "learning_rate": 5.058720929383184e-06, + "loss": 0.7841, + "step": 7534 + }, + { + "epoch": 0.6746880071632436, + "grad_norm": 0.8243488510378381, + "learning_rate": 5.0561996575705105e-06, + "loss": 0.7918, + "step": 7535 + }, + { + "epoch": 0.6747775477083217, + "grad_norm": 1.0169033932694205, + "learning_rate": 5.053678801614205e-06, + "loss": 0.8172, + "step": 7536 + }, + { + "epoch": 0.6748670882533997, + "grad_norm": 0.9965161218062968, + "learning_rate": 5.051158361726322e-06, + "loss": 0.8438, + "step": 7537 + }, + { + "epoch": 0.6749566287984778, + "grad_norm": 0.8794659720767055, + "learning_rate": 5.048638338118873e-06, + "loss": 0.7932, + "step": 7538 + }, + { + "epoch": 0.6750461693435559, + "grad_norm": 0.8973243245104964, + "learning_rate": 5.04611873100383e-06, + "loss": 0.8217, + "step": 7539 + }, + { + "epoch": 0.6751357098886339, + "grad_norm": 0.9468084820196486, + "learning_rate": 5.043599540593138e-06, + "loss": 0.7828, + "step": 7540 + }, + { + "epoch": 0.6752252504337121, + "grad_norm": 1.056046061891345, + "learning_rate": 5.041080767098705e-06, + "loss": 0.7768, + "step": 7541 + }, + { + "epoch": 0.6753147909787901, + "grad_norm": 0.9138748765882617, + "learning_rate": 5.038562410732393e-06, + "loss": 0.7956, + "step": 7542 + }, + { + "epoch": 0.6754043315238681, + "grad_norm": 0.9397286561832034, + "learning_rate": 5.03604447170604e-06, + "loss": 0.7927, + "step": 7543 + }, + { + "epoch": 0.6754938720689462, + "grad_norm": 0.9026669017995445, + "learning_rate": 5.033526950231453e-06, + "loss": 0.8251, + "step": 7544 + }, + { + "epoch": 0.6755834126140243, + "grad_norm": 0.8667935152454881, + "learning_rate": 5.031009846520396e-06, + "loss": 0.7354, + "step": 7545 + }, + { + "epoch": 0.6756729531591024, + "grad_norm": 1.002266487198374, + "learning_rate": 5.028493160784602e-06, + "loss": 0.7544, + "step": 7546 + }, + { + "epoch": 0.6757624937041804, + "grad_norm": 0.968580537296959, + "learning_rate": 5.025976893235758e-06, + "loss": 0.8059, + "step": 7547 + }, + { + "epoch": 0.6758520342492584, + "grad_norm": 0.9158189331992367, + "learning_rate": 5.023461044085529e-06, + "loss": 0.8023, + "step": 7548 + }, + { + "epoch": 0.6759415747943366, + "grad_norm": 0.9462203703567819, + "learning_rate": 5.020945613545536e-06, + "loss": 0.8449, + "step": 7549 + }, + { + "epoch": 0.6760311153394146, + "grad_norm": 0.9572721266398347, + "learning_rate": 5.018430601827376e-06, + "loss": 0.7574, + "step": 7550 + }, + { + "epoch": 0.6761206558844927, + "grad_norm": 1.018689468576089, + "learning_rate": 5.015916009142605e-06, + "loss": 0.84, + "step": 7551 + }, + { + "epoch": 0.6762101964295708, + "grad_norm": 0.9829722911945921, + "learning_rate": 5.013401835702733e-06, + "loss": 0.7998, + "step": 7552 + }, + { + "epoch": 0.6762997369746488, + "grad_norm": 0.9625691457898718, + "learning_rate": 5.0108880817192504e-06, + "loss": 0.8175, + "step": 7553 + }, + { + "epoch": 0.6763892775197269, + "grad_norm": 0.8573185535742263, + "learning_rate": 5.008374747403604e-06, + "loss": 0.8173, + "step": 7554 + }, + { + "epoch": 0.6764788180648049, + "grad_norm": 0.9488532289103421, + "learning_rate": 5.005861832967203e-06, + "loss": 0.8708, + "step": 7555 + }, + { + "epoch": 0.6765683586098831, + "grad_norm": 0.9615133905289535, + "learning_rate": 5.003349338621435e-06, + "loss": 0.8109, + "step": 7556 + }, + { + "epoch": 0.6766578991549611, + "grad_norm": 1.3226853279419994, + "learning_rate": 5.00083726457764e-06, + "loss": 0.7571, + "step": 7557 + }, + { + "epoch": 0.6767474397000391, + "grad_norm": 0.9291071429946327, + "learning_rate": 4.998325611047121e-06, + "loss": 0.8047, + "step": 7558 + }, + { + "epoch": 0.6768369802451173, + "grad_norm": 1.036769219474491, + "learning_rate": 4.995814378241153e-06, + "loss": 0.8127, + "step": 7559 + }, + { + "epoch": 0.6769265207901953, + "grad_norm": 1.0757566848200948, + "learning_rate": 4.993303566370971e-06, + "loss": 0.8041, + "step": 7560 + }, + { + "epoch": 0.6770160613352734, + "grad_norm": 0.9068336875308911, + "learning_rate": 4.9907931756477744e-06, + "loss": 0.7835, + "step": 7561 + }, + { + "epoch": 0.6771056018803514, + "grad_norm": 1.1994711857198965, + "learning_rate": 4.98828320628274e-06, + "loss": 0.8362, + "step": 7562 + }, + { + "epoch": 0.6771951424254296, + "grad_norm": 0.9641376951626224, + "learning_rate": 4.985773658486988e-06, + "loss": 0.832, + "step": 7563 + }, + { + "epoch": 0.6772846829705076, + "grad_norm": 0.9431638330572186, + "learning_rate": 4.983264532471614e-06, + "loss": 0.8303, + "step": 7564 + }, + { + "epoch": 0.6773742235155856, + "grad_norm": 0.9746218243758481, + "learning_rate": 4.980755828447681e-06, + "loss": 0.8495, + "step": 7565 + }, + { + "epoch": 0.6774637640606637, + "grad_norm": 0.9471577352587641, + "learning_rate": 4.97824754662621e-06, + "loss": 0.7492, + "step": 7566 + }, + { + "epoch": 0.6775533046057418, + "grad_norm": 1.1106370398062748, + "learning_rate": 4.975739687218188e-06, + "loss": 0.8122, + "step": 7567 + }, + { + "epoch": 0.6776428451508199, + "grad_norm": 1.2833976317718927, + "learning_rate": 4.973232250434579e-06, + "loss": 0.8209, + "step": 7568 + }, + { + "epoch": 0.6777323856958979, + "grad_norm": 1.2006940702092859, + "learning_rate": 4.970725236486288e-06, + "loss": 0.7849, + "step": 7569 + }, + { + "epoch": 0.677821926240976, + "grad_norm": 1.0565416637083969, + "learning_rate": 4.968218645584202e-06, + "loss": 0.806, + "step": 7570 + }, + { + "epoch": 0.6779114667860541, + "grad_norm": 0.8591469239214488, + "learning_rate": 4.9657124779391656e-06, + "loss": 0.8174, + "step": 7571 + }, + { + "epoch": 0.6780010073311321, + "grad_norm": 1.0623254200749057, + "learning_rate": 4.963206733761991e-06, + "loss": 0.8163, + "step": 7572 + }, + { + "epoch": 0.6780905478762101, + "grad_norm": 0.8791705025294435, + "learning_rate": 4.9607014132634515e-06, + "loss": 0.6918, + "step": 7573 + }, + { + "epoch": 0.6781800884212883, + "grad_norm": 0.926894440955406, + "learning_rate": 4.958196516654288e-06, + "loss": 0.8165, + "step": 7574 + }, + { + "epoch": 0.6782696289663663, + "grad_norm": 1.0592807743841275, + "learning_rate": 4.955692044145203e-06, + "loss": 0.7589, + "step": 7575 + }, + { + "epoch": 0.6783591695114444, + "grad_norm": 0.9047740776223159, + "learning_rate": 4.953187995946867e-06, + "loss": 0.7469, + "step": 7576 + }, + { + "epoch": 0.6784487100565225, + "grad_norm": 0.9388423372826439, + "learning_rate": 4.950684372269909e-06, + "loss": 0.7952, + "step": 7577 + }, + { + "epoch": 0.6785382506016006, + "grad_norm": 0.9816996176824034, + "learning_rate": 4.948181173324928e-06, + "loss": 0.8015, + "step": 7578 + }, + { + "epoch": 0.6786277911466786, + "grad_norm": 0.9624851839084834, + "learning_rate": 4.945678399322484e-06, + "loss": 0.8457, + "step": 7579 + }, + { + "epoch": 0.6787173316917566, + "grad_norm": 1.0522278971321075, + "learning_rate": 4.943176050473104e-06, + "loss": 0.8185, + "step": 7580 + }, + { + "epoch": 0.6788068722368348, + "grad_norm": 1.0076229725927537, + "learning_rate": 4.940674126987275e-06, + "loss": 0.7723, + "step": 7581 + }, + { + "epoch": 0.6788964127819128, + "grad_norm": 0.9804275497429261, + "learning_rate": 4.938172629075451e-06, + "loss": 0.7914, + "step": 7582 + }, + { + "epoch": 0.6789859533269909, + "grad_norm": 0.9147226724079263, + "learning_rate": 4.9356715569480515e-06, + "loss": 0.792, + "step": 7583 + }, + { + "epoch": 0.6790754938720689, + "grad_norm": 0.9089921563894359, + "learning_rate": 4.933170910815457e-06, + "loss": 0.7909, + "step": 7584 + }, + { + "epoch": 0.679165034417147, + "grad_norm": 1.0983847021340474, + "learning_rate": 4.930670690888014e-06, + "loss": 0.8087, + "step": 7585 + }, + { + "epoch": 0.6792545749622251, + "grad_norm": 0.9549856195768626, + "learning_rate": 4.928170897376034e-06, + "loss": 0.8119, + "step": 7586 + }, + { + "epoch": 0.6793441155073031, + "grad_norm": 1.1262802207785858, + "learning_rate": 4.925671530489789e-06, + "loss": 0.8091, + "step": 7587 + }, + { + "epoch": 0.6794336560523813, + "grad_norm": 1.11050910004489, + "learning_rate": 4.92317259043952e-06, + "loss": 0.8128, + "step": 7588 + }, + { + "epoch": 0.6795231965974593, + "grad_norm": 0.9483210252979469, + "learning_rate": 4.920674077435429e-06, + "loss": 0.8119, + "step": 7589 + }, + { + "epoch": 0.6796127371425373, + "grad_norm": 0.9822993840827573, + "learning_rate": 4.918175991687681e-06, + "loss": 0.8002, + "step": 7590 + }, + { + "epoch": 0.6797022776876154, + "grad_norm": 1.0490399036840128, + "learning_rate": 4.915678333406411e-06, + "loss": 0.791, + "step": 7591 + }, + { + "epoch": 0.6797918182326935, + "grad_norm": 1.130388825297679, + "learning_rate": 4.913181102801709e-06, + "loss": 0.7744, + "step": 7592 + }, + { + "epoch": 0.6798813587777716, + "grad_norm": 1.0292039283944732, + "learning_rate": 4.910684300083638e-06, + "loss": 0.8222, + "step": 7593 + }, + { + "epoch": 0.6799708993228496, + "grad_norm": 1.2080676388083944, + "learning_rate": 4.908187925462217e-06, + "loss": 0.7731, + "step": 7594 + }, + { + "epoch": 0.6800604398679277, + "grad_norm": 1.0555071494191735, + "learning_rate": 4.9056919791474415e-06, + "loss": 0.853, + "step": 7595 + }, + { + "epoch": 0.6801499804130058, + "grad_norm": 0.9471430476366979, + "learning_rate": 4.90319646134925e-06, + "loss": 0.8401, + "step": 7596 + }, + { + "epoch": 0.6802395209580838, + "grad_norm": 1.0824350837631747, + "learning_rate": 4.900701372277561e-06, + "loss": 0.8634, + "step": 7597 + }, + { + "epoch": 0.6803290615031619, + "grad_norm": 0.8713173419290678, + "learning_rate": 4.898206712142258e-06, + "loss": 0.8134, + "step": 7598 + }, + { + "epoch": 0.68041860204824, + "grad_norm": 0.935352956437394, + "learning_rate": 4.895712481153181e-06, + "loss": 0.8112, + "step": 7599 + }, + { + "epoch": 0.680508142593318, + "grad_norm": 0.9719918837772018, + "learning_rate": 4.893218679520137e-06, + "loss": 0.7741, + "step": 7600 + }, + { + "epoch": 0.6805976831383961, + "grad_norm": 0.9990795148284224, + "learning_rate": 4.8907253074529e-06, + "loss": 0.8095, + "step": 7601 + }, + { + "epoch": 0.6806872236834741, + "grad_norm": 1.0801695996720977, + "learning_rate": 4.888232365161198e-06, + "loss": 0.8335, + "step": 7602 + }, + { + "epoch": 0.6807767642285523, + "grad_norm": 0.9341204358069326, + "learning_rate": 4.885739852854726e-06, + "loss": 0.8284, + "step": 7603 + }, + { + "epoch": 0.6808663047736303, + "grad_norm": 1.2744498853275787, + "learning_rate": 4.883247770743157e-06, + "loss": 0.8952, + "step": 7604 + }, + { + "epoch": 0.6809558453187083, + "grad_norm": 0.915741769965082, + "learning_rate": 4.88075611903611e-06, + "loss": 0.8081, + "step": 7605 + }, + { + "epoch": 0.6810453858637865, + "grad_norm": 0.9328446516789622, + "learning_rate": 4.878264897943181e-06, + "loss": 0.8362, + "step": 7606 + }, + { + "epoch": 0.6811349264088645, + "grad_norm": 0.9173323000262648, + "learning_rate": 4.875774107673915e-06, + "loss": 0.7871, + "step": 7607 + }, + { + "epoch": 0.6812244669539426, + "grad_norm": 0.8990433187101706, + "learning_rate": 4.8732837484378325e-06, + "loss": 0.7947, + "step": 7608 + }, + { + "epoch": 0.6813140074990206, + "grad_norm": 0.9484370283842838, + "learning_rate": 4.87079382044441e-06, + "loss": 0.8109, + "step": 7609 + }, + { + "epoch": 0.6814035480440988, + "grad_norm": 0.95573197457004, + "learning_rate": 4.868304323903102e-06, + "loss": 0.8214, + "step": 7610 + }, + { + "epoch": 0.6814930885891768, + "grad_norm": 0.9646586834778087, + "learning_rate": 4.865815259023311e-06, + "loss": 0.8678, + "step": 7611 + }, + { + "epoch": 0.6815826291342548, + "grad_norm": 0.9859063125363904, + "learning_rate": 4.863326626014413e-06, + "loss": 0.8347, + "step": 7612 + }, + { + "epoch": 0.681672169679333, + "grad_norm": 0.9365612863709317, + "learning_rate": 4.860838425085737e-06, + "loss": 0.8505, + "step": 7613 + }, + { + "epoch": 0.681761710224411, + "grad_norm": 1.0297270398875087, + "learning_rate": 4.858350656446585e-06, + "loss": 0.8118, + "step": 7614 + }, + { + "epoch": 0.681851250769489, + "grad_norm": 1.1197022641287375, + "learning_rate": 4.855863320306218e-06, + "loss": 0.8261, + "step": 7615 + }, + { + "epoch": 0.6819407913145671, + "grad_norm": 1.0158166462829825, + "learning_rate": 4.853376416873867e-06, + "loss": 0.8152, + "step": 7616 + }, + { + "epoch": 0.6820303318596452, + "grad_norm": 0.9716624722409757, + "learning_rate": 4.850889946358727e-06, + "loss": 0.8037, + "step": 7617 + }, + { + "epoch": 0.6821198724047233, + "grad_norm": 0.9569106891818252, + "learning_rate": 4.848403908969939e-06, + "loss": 0.788, + "step": 7618 + }, + { + "epoch": 0.6822094129498013, + "grad_norm": 1.0607843232233458, + "learning_rate": 4.845918304916628e-06, + "loss": 0.828, + "step": 7619 + }, + { + "epoch": 0.6822989534948793, + "grad_norm": 0.9026834339520259, + "learning_rate": 4.843433134407874e-06, + "loss": 0.7685, + "step": 7620 + }, + { + "epoch": 0.6823884940399575, + "grad_norm": 0.9285624327160942, + "learning_rate": 4.840948397652716e-06, + "loss": 0.7488, + "step": 7621 + }, + { + "epoch": 0.6824780345850355, + "grad_norm": 0.8952129327182544, + "learning_rate": 4.838464094860175e-06, + "loss": 0.8249, + "step": 7622 + }, + { + "epoch": 0.6825675751301136, + "grad_norm": 0.9354090487094243, + "learning_rate": 4.835980226239211e-06, + "loss": 0.8642, + "step": 7623 + }, + { + "epoch": 0.6826571156751917, + "grad_norm": 0.9063402268475304, + "learning_rate": 4.833496791998762e-06, + "loss": 0.7941, + "step": 7624 + }, + { + "epoch": 0.6827466562202698, + "grad_norm": 1.054187429198294, + "learning_rate": 4.831013792347727e-06, + "loss": 0.8467, + "step": 7625 + }, + { + "epoch": 0.6828361967653478, + "grad_norm": 1.0246144621520605, + "learning_rate": 4.828531227494968e-06, + "loss": 0.8106, + "step": 7626 + }, + { + "epoch": 0.6829257373104258, + "grad_norm": 1.0523314318923513, + "learning_rate": 4.826049097649309e-06, + "loss": 0.7716, + "step": 7627 + }, + { + "epoch": 0.683015277855504, + "grad_norm": 0.9751922511718797, + "learning_rate": 4.82356740301954e-06, + "loss": 0.8885, + "step": 7628 + }, + { + "epoch": 0.683104818400582, + "grad_norm": 0.9465294192145584, + "learning_rate": 4.8210861438144126e-06, + "loss": 0.8249, + "step": 7629 + }, + { + "epoch": 0.68319435894566, + "grad_norm": 0.9712886638650309, + "learning_rate": 4.818605320242642e-06, + "loss": 0.8189, + "step": 7630 + }, + { + "epoch": 0.6832838994907382, + "grad_norm": 1.0970167104956374, + "learning_rate": 4.816124932512908e-06, + "loss": 0.8201, + "step": 7631 + }, + { + "epoch": 0.6833734400358162, + "grad_norm": 1.0249335430441642, + "learning_rate": 4.813644980833851e-06, + "loss": 0.7223, + "step": 7632 + }, + { + "epoch": 0.6834629805808943, + "grad_norm": 0.9901811056507533, + "learning_rate": 4.811165465414077e-06, + "loss": 0.8557, + "step": 7633 + }, + { + "epoch": 0.6835525211259723, + "grad_norm": 0.961801284809666, + "learning_rate": 4.808686386462156e-06, + "loss": 0.8099, + "step": 7634 + }, + { + "epoch": 0.6836420616710505, + "grad_norm": 1.2401348633004983, + "learning_rate": 4.806207744186619e-06, + "loss": 0.7904, + "step": 7635 + }, + { + "epoch": 0.6837316022161285, + "grad_norm": 0.845660549421603, + "learning_rate": 4.803729538795962e-06, + "loss": 0.7643, + "step": 7636 + }, + { + "epoch": 0.6838211427612065, + "grad_norm": 0.9830017878832183, + "learning_rate": 4.801251770498643e-06, + "loss": 0.7951, + "step": 7637 + }, + { + "epoch": 0.6839106833062846, + "grad_norm": 0.8870034294269233, + "learning_rate": 4.798774439503083e-06, + "loss": 0.7595, + "step": 7638 + }, + { + "epoch": 0.6840002238513627, + "grad_norm": 0.9963640308409181, + "learning_rate": 4.796297546017669e-06, + "loss": 0.7931, + "step": 7639 + }, + { + "epoch": 0.6840897643964408, + "grad_norm": 1.0535424027199087, + "learning_rate": 4.793821090250748e-06, + "loss": 0.8176, + "step": 7640 + }, + { + "epoch": 0.6841793049415188, + "grad_norm": 1.039270292588724, + "learning_rate": 4.79134507241063e-06, + "loss": 0.7515, + "step": 7641 + }, + { + "epoch": 0.6842688454865969, + "grad_norm": 1.006781845763195, + "learning_rate": 4.788869492705593e-06, + "loss": 0.8068, + "step": 7642 + }, + { + "epoch": 0.684358386031675, + "grad_norm": 1.0622641299399038, + "learning_rate": 4.786394351343872e-06, + "loss": 0.7972, + "step": 7643 + }, + { + "epoch": 0.684447926576753, + "grad_norm": 0.9646098817166341, + "learning_rate": 4.783919648533668e-06, + "loss": 0.8354, + "step": 7644 + }, + { + "epoch": 0.6845374671218311, + "grad_norm": 0.9250212951935629, + "learning_rate": 4.781445384483145e-06, + "loss": 0.8548, + "step": 7645 + }, + { + "epoch": 0.6846270076669092, + "grad_norm": 1.155151162348634, + "learning_rate": 4.7789715594004325e-06, + "loss": 0.7811, + "step": 7646 + }, + { + "epoch": 0.6847165482119872, + "grad_norm": 1.592338376503375, + "learning_rate": 4.776498173493618e-06, + "loss": 0.846, + "step": 7647 + }, + { + "epoch": 0.6848060887570653, + "grad_norm": 0.9848437779403034, + "learning_rate": 4.774025226970754e-06, + "loss": 0.7672, + "step": 7648 + }, + { + "epoch": 0.6848956293021434, + "grad_norm": 0.9969095880015193, + "learning_rate": 4.7715527200398595e-06, + "loss": 0.8169, + "step": 7649 + }, + { + "epoch": 0.6849851698472215, + "grad_norm": 0.916716849341787, + "learning_rate": 4.769080652908915e-06, + "loss": 0.852, + "step": 7650 + }, + { + "epoch": 0.6850747103922995, + "grad_norm": 0.9379705083690661, + "learning_rate": 4.766609025785853e-06, + "loss": 0.8082, + "step": 7651 + }, + { + "epoch": 0.6851642509373775, + "grad_norm": 0.9536911403075226, + "learning_rate": 4.76413783887859e-06, + "loss": 0.768, + "step": 7652 + }, + { + "epoch": 0.6852537914824557, + "grad_norm": 0.9892955448658866, + "learning_rate": 4.761667092394989e-06, + "loss": 0.7919, + "step": 7653 + }, + { + "epoch": 0.6853433320275337, + "grad_norm": 1.0063083527315473, + "learning_rate": 4.759196786542882e-06, + "loss": 0.7875, + "step": 7654 + }, + { + "epoch": 0.6854328725726118, + "grad_norm": 0.9789605535837096, + "learning_rate": 4.756726921530067e-06, + "loss": 0.8304, + "step": 7655 + }, + { + "epoch": 0.6855224131176898, + "grad_norm": 1.2433125894198715, + "learning_rate": 4.754257497564293e-06, + "loss": 0.8564, + "step": 7656 + }, + { + "epoch": 0.685611953662768, + "grad_norm": 0.9290662614153107, + "learning_rate": 4.75178851485328e-06, + "loss": 0.8424, + "step": 7657 + }, + { + "epoch": 0.685701494207846, + "grad_norm": 0.9566815537682959, + "learning_rate": 4.7493199736047205e-06, + "loss": 0.8465, + "step": 7658 + }, + { + "epoch": 0.685791034752924, + "grad_norm": 0.9071667309646064, + "learning_rate": 4.746851874026253e-06, + "loss": 0.7891, + "step": 7659 + }, + { + "epoch": 0.6858805752980022, + "grad_norm": 0.9806487861828885, + "learning_rate": 4.744384216325487e-06, + "loss": 0.7876, + "step": 7660 + }, + { + "epoch": 0.6859701158430802, + "grad_norm": 1.0407761021696793, + "learning_rate": 4.7419170007099975e-06, + "loss": 0.7453, + "step": 7661 + }, + { + "epoch": 0.6860596563881582, + "grad_norm": 0.9562445846799578, + "learning_rate": 4.7394502273873135e-06, + "loss": 0.8163, + "step": 7662 + }, + { + "epoch": 0.6861491969332363, + "grad_norm": 1.0444108755044383, + "learning_rate": 4.736983896564928e-06, + "loss": 0.7591, + "step": 7663 + }, + { + "epoch": 0.6862387374783144, + "grad_norm": 0.9683041362144316, + "learning_rate": 4.734518008450312e-06, + "loss": 0.8287, + "step": 7664 + }, + { + "epoch": 0.6863282780233925, + "grad_norm": 1.098163438299449, + "learning_rate": 4.732052563250882e-06, + "loss": 0.7516, + "step": 7665 + }, + { + "epoch": 0.6864178185684705, + "grad_norm": 0.8173488978592476, + "learning_rate": 4.729587561174027e-06, + "loss": 0.7569, + "step": 7666 + }, + { + "epoch": 0.6865073591135487, + "grad_norm": 0.9584898496040919, + "learning_rate": 4.727123002427089e-06, + "loss": 0.7873, + "step": 7667 + }, + { + "epoch": 0.6865968996586267, + "grad_norm": 0.926146504490765, + "learning_rate": 4.72465888721738e-06, + "loss": 0.7789, + "step": 7668 + }, + { + "epoch": 0.6866864402037047, + "grad_norm": 1.2639116589026649, + "learning_rate": 4.722195215752171e-06, + "loss": 0.8264, + "step": 7669 + }, + { + "epoch": 0.6867759807487828, + "grad_norm": 0.9533545296032012, + "learning_rate": 4.719731988238706e-06, + "loss": 0.801, + "step": 7670 + }, + { + "epoch": 0.6868655212938609, + "grad_norm": 1.040869138732014, + "learning_rate": 4.717269204884178e-06, + "loss": 0.7383, + "step": 7671 + }, + { + "epoch": 0.686955061838939, + "grad_norm": 1.0037610729874973, + "learning_rate": 4.714806865895756e-06, + "loss": 0.8485, + "step": 7672 + }, + { + "epoch": 0.687044602384017, + "grad_norm": 0.9178281339532298, + "learning_rate": 4.712344971480551e-06, + "loss": 0.8039, + "step": 7673 + }, + { + "epoch": 0.687134142929095, + "grad_norm": 0.9039723582972342, + "learning_rate": 4.7098835218456585e-06, + "loss": 0.8248, + "step": 7674 + }, + { + "epoch": 0.6872236834741732, + "grad_norm": 1.0837590541970161, + "learning_rate": 4.707422517198119e-06, + "loss": 0.8412, + "step": 7675 + }, + { + "epoch": 0.6873132240192512, + "grad_norm": 1.0356362102668961, + "learning_rate": 4.704961957744956e-06, + "loss": 0.7524, + "step": 7676 + }, + { + "epoch": 0.6874027645643292, + "grad_norm": 0.9750985610759151, + "learning_rate": 4.702501843693141e-06, + "loss": 0.7638, + "step": 7677 + }, + { + "epoch": 0.6874923051094074, + "grad_norm": 0.9644398739455586, + "learning_rate": 4.7000421752496055e-06, + "loss": 0.8151, + "step": 7678 + }, + { + "epoch": 0.6875818456544854, + "grad_norm": 1.1516897239170134, + "learning_rate": 4.69758295262125e-06, + "loss": 0.7597, + "step": 7679 + }, + { + "epoch": 0.6876713861995635, + "grad_norm": 0.8791866827091167, + "learning_rate": 4.695124176014938e-06, + "loss": 0.8384, + "step": 7680 + }, + { + "epoch": 0.6877609267446415, + "grad_norm": 0.9294702399020952, + "learning_rate": 4.692665845637493e-06, + "loss": 0.7844, + "step": 7681 + }, + { + "epoch": 0.6878504672897197, + "grad_norm": 0.965780943257856, + "learning_rate": 4.690207961695702e-06, + "loss": 0.8198, + "step": 7682 + }, + { + "epoch": 0.6879400078347977, + "grad_norm": 0.972430293034956, + "learning_rate": 4.687750524396314e-06, + "loss": 0.864, + "step": 7683 + }, + { + "epoch": 0.6880295483798757, + "grad_norm": 0.8944555470932781, + "learning_rate": 4.685293533946042e-06, + "loss": 0.7956, + "step": 7684 + }, + { + "epoch": 0.6881190889249539, + "grad_norm": 0.8972459279295408, + "learning_rate": 4.6828369905515565e-06, + "loss": 0.778, + "step": 7685 + }, + { + "epoch": 0.6882086294700319, + "grad_norm": 0.9209436696056206, + "learning_rate": 4.680380894419499e-06, + "loss": 0.8245, + "step": 7686 + }, + { + "epoch": 0.68829817001511, + "grad_norm": 0.9071930465407908, + "learning_rate": 4.677925245756464e-06, + "loss": 0.8328, + "step": 7687 + }, + { + "epoch": 0.688387710560188, + "grad_norm": 0.9713506291746641, + "learning_rate": 4.675470044769015e-06, + "loss": 0.8059, + "step": 7688 + }, + { + "epoch": 0.6884772511052661, + "grad_norm": 1.0322890781315812, + "learning_rate": 4.673015291663674e-06, + "loss": 0.8349, + "step": 7689 + }, + { + "epoch": 0.6885667916503442, + "grad_norm": 0.885311818496522, + "learning_rate": 4.6705609866469286e-06, + "loss": 0.8, + "step": 7690 + }, + { + "epoch": 0.6886563321954222, + "grad_norm": 0.8888731075690266, + "learning_rate": 4.668107129925225e-06, + "loss": 0.7692, + "step": 7691 + }, + { + "epoch": 0.6887458727405003, + "grad_norm": 0.8856236156532676, + "learning_rate": 4.665653721704975e-06, + "loss": 0.823, + "step": 7692 + }, + { + "epoch": 0.6888354132855784, + "grad_norm": 0.8516781050595209, + "learning_rate": 4.6632007621925514e-06, + "loss": 0.8173, + "step": 7693 + }, + { + "epoch": 0.6889249538306564, + "grad_norm": 0.8760734530128444, + "learning_rate": 4.660748251594288e-06, + "loss": 0.7824, + "step": 7694 + }, + { + "epoch": 0.6890144943757345, + "grad_norm": 0.9777360637584239, + "learning_rate": 4.658296190116482e-06, + "loss": 0.7815, + "step": 7695 + }, + { + "epoch": 0.6891040349208126, + "grad_norm": 0.9474816684833404, + "learning_rate": 4.6558445779653946e-06, + "loss": 0.7974, + "step": 7696 + }, + { + "epoch": 0.6891935754658907, + "grad_norm": 1.0740336970510092, + "learning_rate": 4.653393415347246e-06, + "loss": 0.8154, + "step": 7697 + }, + { + "epoch": 0.6892831160109687, + "grad_norm": 0.8660586746066604, + "learning_rate": 4.650942702468219e-06, + "loss": 0.7534, + "step": 7698 + }, + { + "epoch": 0.6893726565560467, + "grad_norm": 0.8909767852453753, + "learning_rate": 4.648492439534463e-06, + "loss": 0.7966, + "step": 7699 + }, + { + "epoch": 0.6894621971011249, + "grad_norm": 0.9220333075557067, + "learning_rate": 4.646042626752083e-06, + "loss": 0.7921, + "step": 7700 + }, + { + "epoch": 0.6895517376462029, + "grad_norm": 0.9098350959629002, + "learning_rate": 4.6435932643271496e-06, + "loss": 0.8346, + "step": 7701 + }, + { + "epoch": 0.689641278191281, + "grad_norm": 0.8965014505742412, + "learning_rate": 4.641144352465697e-06, + "loss": 0.8193, + "step": 7702 + }, + { + "epoch": 0.6897308187363591, + "grad_norm": 0.9234633268070609, + "learning_rate": 4.638695891373718e-06, + "loss": 0.856, + "step": 7703 + }, + { + "epoch": 0.6898203592814371, + "grad_norm": 0.9374769186639121, + "learning_rate": 4.6362478812571746e-06, + "loss": 0.7961, + "step": 7704 + }, + { + "epoch": 0.6899098998265152, + "grad_norm": 1.0058684765401815, + "learning_rate": 4.633800322321972e-06, + "loss": 0.7304, + "step": 7705 + }, + { + "epoch": 0.6899994403715932, + "grad_norm": 0.9423020288073447, + "learning_rate": 4.631353214774003e-06, + "loss": 0.8515, + "step": 7706 + }, + { + "epoch": 0.6900889809166714, + "grad_norm": 0.9047967924996625, + "learning_rate": 4.628906558819106e-06, + "loss": 0.7752, + "step": 7707 + }, + { + "epoch": 0.6901785214617494, + "grad_norm": 0.9308127260698004, + "learning_rate": 4.626460354663088e-06, + "loss": 0.8291, + "step": 7708 + }, + { + "epoch": 0.6902680620068274, + "grad_norm": 0.9687661406505695, + "learning_rate": 4.624014602511714e-06, + "loss": 0.8376, + "step": 7709 + }, + { + "epoch": 0.6903576025519055, + "grad_norm": 0.9622354488294877, + "learning_rate": 4.621569302570715e-06, + "loss": 0.8254, + "step": 7710 + }, + { + "epoch": 0.6904471430969836, + "grad_norm": 1.040135557361331, + "learning_rate": 4.6191244550457735e-06, + "loss": 0.7294, + "step": 7711 + }, + { + "epoch": 0.6905366836420617, + "grad_norm": 1.0002495013137138, + "learning_rate": 4.616680060142552e-06, + "loss": 0.803, + "step": 7712 + }, + { + "epoch": 0.6906262241871397, + "grad_norm": 0.9219391263097959, + "learning_rate": 4.614236118066662e-06, + "loss": 0.8666, + "step": 7713 + }, + { + "epoch": 0.6907157647322179, + "grad_norm": 1.0065588862821842, + "learning_rate": 4.611792629023677e-06, + "loss": 0.8229, + "step": 7714 + }, + { + "epoch": 0.6908053052772959, + "grad_norm": 1.002724892031868, + "learning_rate": 4.6093495932191425e-06, + "loss": 0.8133, + "step": 7715 + }, + { + "epoch": 0.6908948458223739, + "grad_norm": 0.9097203547323798, + "learning_rate": 4.60690701085855e-06, + "loss": 0.8113, + "step": 7716 + }, + { + "epoch": 0.690984386367452, + "grad_norm": 0.9833261082368646, + "learning_rate": 4.604464882147362e-06, + "loss": 0.7726, + "step": 7717 + }, + { + "epoch": 0.6910739269125301, + "grad_norm": 0.9135802813590834, + "learning_rate": 4.602023207291008e-06, + "loss": 0.827, + "step": 7718 + }, + { + "epoch": 0.6911634674576081, + "grad_norm": 0.9523278917149808, + "learning_rate": 4.599581986494872e-06, + "loss": 0.8425, + "step": 7719 + }, + { + "epoch": 0.6912530080026862, + "grad_norm": 1.0003514879124802, + "learning_rate": 4.5971412199643005e-06, + "loss": 0.7713, + "step": 7720 + }, + { + "epoch": 0.6913425485477643, + "grad_norm": 1.0838163936618297, + "learning_rate": 4.594700907904608e-06, + "loss": 0.8341, + "step": 7721 + }, + { + "epoch": 0.6914320890928424, + "grad_norm": 1.015604191759641, + "learning_rate": 4.5922610505210566e-06, + "loss": 0.8376, + "step": 7722 + }, + { + "epoch": 0.6915216296379204, + "grad_norm": 0.8546784471872672, + "learning_rate": 4.58982164801888e-06, + "loss": 0.805, + "step": 7723 + }, + { + "epoch": 0.6916111701829984, + "grad_norm": 1.0385395725943547, + "learning_rate": 4.587382700603279e-06, + "loss": 0.838, + "step": 7724 + }, + { + "epoch": 0.6917007107280766, + "grad_norm": 0.9078574954047972, + "learning_rate": 4.584944208479407e-06, + "loss": 0.8336, + "step": 7725 + }, + { + "epoch": 0.6917902512731546, + "grad_norm": 1.2275033869971155, + "learning_rate": 4.582506171852386e-06, + "loss": 0.7917, + "step": 7726 + }, + { + "epoch": 0.6918797918182327, + "grad_norm": 0.9339527676210228, + "learning_rate": 4.58006859092729e-06, + "loss": 0.8336, + "step": 7727 + }, + { + "epoch": 0.6919693323633107, + "grad_norm": 0.938958883099842, + "learning_rate": 4.57763146590916e-06, + "loss": 0.8114, + "step": 7728 + }, + { + "epoch": 0.6920588729083889, + "grad_norm": 0.921114466993026, + "learning_rate": 4.575194797002999e-06, + "loss": 0.823, + "step": 7729 + }, + { + "epoch": 0.6921484134534669, + "grad_norm": 0.8848028670625154, + "learning_rate": 4.572758584413777e-06, + "loss": 0.8281, + "step": 7730 + }, + { + "epoch": 0.6922379539985449, + "grad_norm": 0.9286944268121133, + "learning_rate": 4.5703228283464165e-06, + "loss": 0.7904, + "step": 7731 + }, + { + "epoch": 0.6923274945436231, + "grad_norm": 0.952864911808103, + "learning_rate": 4.56788752900581e-06, + "loss": 0.8471, + "step": 7732 + }, + { + "epoch": 0.6924170350887011, + "grad_norm": 0.9699577288490665, + "learning_rate": 4.565452686596799e-06, + "loss": 0.7812, + "step": 7733 + }, + { + "epoch": 0.6925065756337792, + "grad_norm": 0.911285786162714, + "learning_rate": 4.563018301324199e-06, + "loss": 0.8117, + "step": 7734 + }, + { + "epoch": 0.6925961161788572, + "grad_norm": 1.0333532386576183, + "learning_rate": 4.560584373392783e-06, + "loss": 0.8293, + "step": 7735 + }, + { + "epoch": 0.6926856567239353, + "grad_norm": 0.9697470828221156, + "learning_rate": 4.558150903007278e-06, + "loss": 0.8098, + "step": 7736 + }, + { + "epoch": 0.6927751972690134, + "grad_norm": 0.9779244131744482, + "learning_rate": 4.555717890372394e-06, + "loss": 0.8948, + "step": 7737 + }, + { + "epoch": 0.6928647378140914, + "grad_norm": 0.9590323306175039, + "learning_rate": 4.553285335692776e-06, + "loss": 0.832, + "step": 7738 + }, + { + "epoch": 0.6929542783591696, + "grad_norm": 0.9484394434483989, + "learning_rate": 4.550853239173047e-06, + "loss": 0.7909, + "step": 7739 + }, + { + "epoch": 0.6930438189042476, + "grad_norm": 0.9456791005515883, + "learning_rate": 4.548421601017786e-06, + "loss": 0.802, + "step": 7740 + }, + { + "epoch": 0.6931333594493256, + "grad_norm": 1.0010515938153786, + "learning_rate": 4.545990421431535e-06, + "loss": 0.7364, + "step": 7741 + }, + { + "epoch": 0.6932228999944037, + "grad_norm": 1.0210524712540772, + "learning_rate": 4.543559700618792e-06, + "loss": 0.7757, + "step": 7742 + }, + { + "epoch": 0.6933124405394818, + "grad_norm": 1.0273529023242547, + "learning_rate": 4.541129438784036e-06, + "loss": 0.8012, + "step": 7743 + }, + { + "epoch": 0.6934019810845599, + "grad_norm": 0.9829214825923223, + "learning_rate": 4.538699636131676e-06, + "loss": 0.8531, + "step": 7744 + }, + { + "epoch": 0.6934915216296379, + "grad_norm": 1.0278999485409048, + "learning_rate": 4.536270292866108e-06, + "loss": 0.7943, + "step": 7745 + }, + { + "epoch": 0.6935810621747159, + "grad_norm": 0.9454099504143345, + "learning_rate": 4.533841409191677e-06, + "loss": 0.8208, + "step": 7746 + }, + { + "epoch": 0.6936706027197941, + "grad_norm": 0.9145060065432331, + "learning_rate": 4.531412985312694e-06, + "loss": 0.7971, + "step": 7747 + }, + { + "epoch": 0.6937601432648721, + "grad_norm": 0.9528201805784614, + "learning_rate": 4.528985021433431e-06, + "loss": 0.8258, + "step": 7748 + }, + { + "epoch": 0.6938496838099502, + "grad_norm": 1.0701720010775788, + "learning_rate": 4.526557517758119e-06, + "loss": 0.7632, + "step": 7749 + }, + { + "epoch": 0.6939392243550283, + "grad_norm": 0.9576936634197529, + "learning_rate": 4.524130474490953e-06, + "loss": 0.8053, + "step": 7750 + }, + { + "epoch": 0.6940287649001063, + "grad_norm": 1.082811699820177, + "learning_rate": 4.521703891836087e-06, + "loss": 0.8491, + "step": 7751 + }, + { + "epoch": 0.6941183054451844, + "grad_norm": 0.9750481696007716, + "learning_rate": 4.519277769997637e-06, + "loss": 0.7557, + "step": 7752 + }, + { + "epoch": 0.6942078459902624, + "grad_norm": 0.9152437304075808, + "learning_rate": 4.516852109179682e-06, + "loss": 0.8848, + "step": 7753 + }, + { + "epoch": 0.6942973865353406, + "grad_norm": 0.9789031284351487, + "learning_rate": 4.514426909586258e-06, + "loss": 0.7547, + "step": 7754 + }, + { + "epoch": 0.6943869270804186, + "grad_norm": 1.197333642551522, + "learning_rate": 4.512002171421368e-06, + "loss": 0.8332, + "step": 7755 + }, + { + "epoch": 0.6944764676254966, + "grad_norm": 0.884446932583186, + "learning_rate": 4.50957789488897e-06, + "loss": 0.7517, + "step": 7756 + }, + { + "epoch": 0.6945660081705748, + "grad_norm": 0.8833605930695296, + "learning_rate": 4.507154080192989e-06, + "loss": 0.8384, + "step": 7757 + }, + { + "epoch": 0.6946555487156528, + "grad_norm": 1.0608193854329326, + "learning_rate": 4.504730727537307e-06, + "loss": 0.8073, + "step": 7758 + }, + { + "epoch": 0.6947450892607309, + "grad_norm": 0.9729726466497831, + "learning_rate": 4.502307837125769e-06, + "loss": 0.7803, + "step": 7759 + }, + { + "epoch": 0.6948346298058089, + "grad_norm": 1.023350043853379, + "learning_rate": 4.49988540916218e-06, + "loss": 0.821, + "step": 7760 + }, + { + "epoch": 0.694924170350887, + "grad_norm": 0.86515487605003, + "learning_rate": 4.497463443850307e-06, + "loss": 0.8651, + "step": 7761 + }, + { + "epoch": 0.6950137108959651, + "grad_norm": 0.9164565222107208, + "learning_rate": 4.4950419413938785e-06, + "loss": 0.8167, + "step": 7762 + }, + { + "epoch": 0.6951032514410431, + "grad_norm": 0.9190754724173374, + "learning_rate": 4.492620901996583e-06, + "loss": 0.818, + "step": 7763 + }, + { + "epoch": 0.6951927919861212, + "grad_norm": 0.9907111111052157, + "learning_rate": 4.490200325862073e-06, + "loss": 0.8471, + "step": 7764 + }, + { + "epoch": 0.6952823325311993, + "grad_norm": 0.9532964344673837, + "learning_rate": 4.48778021319395e-06, + "loss": 0.7751, + "step": 7765 + }, + { + "epoch": 0.6953718730762773, + "grad_norm": 0.9225948104435617, + "learning_rate": 4.485360564195797e-06, + "loss": 0.8216, + "step": 7766 + }, + { + "epoch": 0.6954614136213554, + "grad_norm": 1.0067853398920983, + "learning_rate": 4.482941379071142e-06, + "loss": 0.819, + "step": 7767 + }, + { + "epoch": 0.6955509541664335, + "grad_norm": 0.9196174655914519, + "learning_rate": 4.480522658023479e-06, + "loss": 0.7719, + "step": 7768 + }, + { + "epoch": 0.6956404947115116, + "grad_norm": 0.9107983728077748, + "learning_rate": 4.478104401256266e-06, + "loss": 0.8021, + "step": 7769 + }, + { + "epoch": 0.6957300352565896, + "grad_norm": 0.9294936855310101, + "learning_rate": 4.475686608972918e-06, + "loss": 0.7564, + "step": 7770 + }, + { + "epoch": 0.6958195758016676, + "grad_norm": 0.8450624277835593, + "learning_rate": 4.473269281376804e-06, + "loss": 0.7805, + "step": 7771 + }, + { + "epoch": 0.6959091163467458, + "grad_norm": 0.9795022319205948, + "learning_rate": 4.470852418671271e-06, + "loss": 0.8042, + "step": 7772 + }, + { + "epoch": 0.6959986568918238, + "grad_norm": 0.9866579823969005, + "learning_rate": 4.4684360210596154e-06, + "loss": 0.815, + "step": 7773 + }, + { + "epoch": 0.6960881974369019, + "grad_norm": 1.227092642163139, + "learning_rate": 4.466020088745097e-06, + "loss": 0.8008, + "step": 7774 + }, + { + "epoch": 0.69617773798198, + "grad_norm": 0.9510083267097689, + "learning_rate": 4.463604621930937e-06, + "loss": 0.8126, + "step": 7775 + }, + { + "epoch": 0.696267278527058, + "grad_norm": 0.9862930043956016, + "learning_rate": 4.461189620820312e-06, + "loss": 0.8338, + "step": 7776 + }, + { + "epoch": 0.6963568190721361, + "grad_norm": 0.9418095761541713, + "learning_rate": 4.458775085616363e-06, + "loss": 0.805, + "step": 7777 + }, + { + "epoch": 0.6964463596172141, + "grad_norm": 0.9525776491121389, + "learning_rate": 4.4563610165221995e-06, + "loss": 0.8112, + "step": 7778 + }, + { + "epoch": 0.6965359001622923, + "grad_norm": 0.8948369026606042, + "learning_rate": 4.4539474137408825e-06, + "loss": 0.7846, + "step": 7779 + }, + { + "epoch": 0.6966254407073703, + "grad_norm": 0.921271952153349, + "learning_rate": 4.451534277475436e-06, + "loss": 0.7583, + "step": 7780 + }, + { + "epoch": 0.6967149812524484, + "grad_norm": 0.9456674920470037, + "learning_rate": 4.44912160792885e-06, + "loss": 0.7987, + "step": 7781 + }, + { + "epoch": 0.6968045217975264, + "grad_norm": 1.0370215105300973, + "learning_rate": 4.446709405304061e-06, + "loss": 0.8429, + "step": 7782 + }, + { + "epoch": 0.6968940623426045, + "grad_norm": 0.9629235140407333, + "learning_rate": 4.444297669803981e-06, + "loss": 0.8453, + "step": 7783 + }, + { + "epoch": 0.6969836028876826, + "grad_norm": 0.9475338653041179, + "learning_rate": 4.441886401631472e-06, + "loss": 0.8113, + "step": 7784 + }, + { + "epoch": 0.6970731434327606, + "grad_norm": 0.9810510231460815, + "learning_rate": 4.439475600989372e-06, + "loss": 0.8382, + "step": 7785 + }, + { + "epoch": 0.6971626839778388, + "grad_norm": 0.9593807466063948, + "learning_rate": 4.437065268080466e-06, + "loss": 0.783, + "step": 7786 + }, + { + "epoch": 0.6972522245229168, + "grad_norm": 0.9210281043068721, + "learning_rate": 4.434655403107499e-06, + "loss": 0.7818, + "step": 7787 + }, + { + "epoch": 0.6973417650679948, + "grad_norm": 0.9531472552897879, + "learning_rate": 4.432246006273183e-06, + "loss": 0.8135, + "step": 7788 + }, + { + "epoch": 0.6974313056130729, + "grad_norm": 0.9709806118305161, + "learning_rate": 4.42983707778019e-06, + "loss": 0.8077, + "step": 7789 + }, + { + "epoch": 0.697520846158151, + "grad_norm": 0.9314103307693076, + "learning_rate": 4.427428617831146e-06, + "loss": 0.7729, + "step": 7790 + }, + { + "epoch": 0.6976103867032291, + "grad_norm": 1.0016380002825547, + "learning_rate": 4.4250206266286535e-06, + "loss": 0.7844, + "step": 7791 + }, + { + "epoch": 0.6976999272483071, + "grad_norm": 0.9146578802186879, + "learning_rate": 4.422613104375259e-06, + "loss": 0.7897, + "step": 7792 + }, + { + "epoch": 0.6977894677933852, + "grad_norm": 1.0265693910687193, + "learning_rate": 4.4202060512734736e-06, + "loss": 0.8051, + "step": 7793 + }, + { + "epoch": 0.6978790083384633, + "grad_norm": 1.0721668945427831, + "learning_rate": 4.417799467525772e-06, + "loss": 0.8924, + "step": 7794 + }, + { + "epoch": 0.6979685488835413, + "grad_norm": 0.9693514671026972, + "learning_rate": 4.415393353334588e-06, + "loss": 0.8024, + "step": 7795 + }, + { + "epoch": 0.6980580894286194, + "grad_norm": 1.0051226006411156, + "learning_rate": 4.4129877089023135e-06, + "loss": 0.813, + "step": 7796 + }, + { + "epoch": 0.6981476299736975, + "grad_norm": 0.9714005803199256, + "learning_rate": 4.410582534431313e-06, + "loss": 0.8357, + "step": 7797 + }, + { + "epoch": 0.6982371705187755, + "grad_norm": 1.0392086715695477, + "learning_rate": 4.408177830123892e-06, + "loss": 0.8025, + "step": 7798 + }, + { + "epoch": 0.6983267110638536, + "grad_norm": 0.9476414130880175, + "learning_rate": 4.40577359618233e-06, + "loss": 0.7997, + "step": 7799 + }, + { + "epoch": 0.6984162516089316, + "grad_norm": 0.9522635099772635, + "learning_rate": 4.403369832808862e-06, + "loss": 0.7633, + "step": 7800 + }, + { + "epoch": 0.6985057921540098, + "grad_norm": 0.9691524164500117, + "learning_rate": 4.400966540205688e-06, + "loss": 0.8148, + "step": 7801 + }, + { + "epoch": 0.6985953326990878, + "grad_norm": 1.0282249072193876, + "learning_rate": 4.398563718574959e-06, + "loss": 0.7545, + "step": 7802 + }, + { + "epoch": 0.6986848732441658, + "grad_norm": 0.9949166864329059, + "learning_rate": 4.396161368118803e-06, + "loss": 0.8307, + "step": 7803 + }, + { + "epoch": 0.698774413789244, + "grad_norm": 0.927874432714334, + "learning_rate": 4.393759489039288e-06, + "loss": 0.8376, + "step": 7804 + }, + { + "epoch": 0.698863954334322, + "grad_norm": 0.9156546636999212, + "learning_rate": 4.391358081538456e-06, + "loss": 0.8065, + "step": 7805 + }, + { + "epoch": 0.6989534948794001, + "grad_norm": 0.9450259623191144, + "learning_rate": 4.388957145818305e-06, + "loss": 0.7827, + "step": 7806 + }, + { + "epoch": 0.6990430354244781, + "grad_norm": 0.9623017302044576, + "learning_rate": 4.386556682080794e-06, + "loss": 0.8143, + "step": 7807 + }, + { + "epoch": 0.6991325759695562, + "grad_norm": 0.9092367335316479, + "learning_rate": 4.384156690527842e-06, + "loss": 0.8282, + "step": 7808 + }, + { + "epoch": 0.6992221165146343, + "grad_norm": 1.0272497689897835, + "learning_rate": 4.38175717136133e-06, + "loss": 0.7684, + "step": 7809 + }, + { + "epoch": 0.6993116570597123, + "grad_norm": 1.1460948266469708, + "learning_rate": 4.379358124783096e-06, + "loss": 0.807, + "step": 7810 + }, + { + "epoch": 0.6994011976047905, + "grad_norm": 1.0209818011587013, + "learning_rate": 4.37695955099494e-06, + "loss": 0.8201, + "step": 7811 + }, + { + "epoch": 0.6994907381498685, + "grad_norm": 0.981735900252388, + "learning_rate": 4.3745614501986234e-06, + "loss": 0.8194, + "step": 7812 + }, + { + "epoch": 0.6995802786949465, + "grad_norm": 0.9906248491297962, + "learning_rate": 4.372163822595866e-06, + "loss": 0.7833, + "step": 7813 + }, + { + "epoch": 0.6996698192400246, + "grad_norm": 0.9287905432843976, + "learning_rate": 4.3697666683883475e-06, + "loss": 0.7676, + "step": 7814 + }, + { + "epoch": 0.6997593597851027, + "grad_norm": 0.9438507823490722, + "learning_rate": 4.367369987777711e-06, + "loss": 0.7796, + "step": 7815 + }, + { + "epoch": 0.6998489003301808, + "grad_norm": 0.8883555693470103, + "learning_rate": 4.364973780965556e-06, + "loss": 0.7951, + "step": 7816 + }, + { + "epoch": 0.6999384408752588, + "grad_norm": 1.0572897438650468, + "learning_rate": 4.362578048153442e-06, + "loss": 0.8651, + "step": 7817 + }, + { + "epoch": 0.7000279814203368, + "grad_norm": 0.8475297817693815, + "learning_rate": 4.3601827895428926e-06, + "loss": 0.8149, + "step": 7818 + }, + { + "epoch": 0.700117521965415, + "grad_norm": 0.9092678173475608, + "learning_rate": 4.357788005335389e-06, + "loss": 0.8225, + "step": 7819 + }, + { + "epoch": 0.700207062510493, + "grad_norm": 0.8893830545386018, + "learning_rate": 4.355393695732371e-06, + "loss": 0.814, + "step": 7820 + }, + { + "epoch": 0.7002966030555711, + "grad_norm": 0.9032946005309451, + "learning_rate": 4.352999860935243e-06, + "loss": 0.8169, + "step": 7821 + }, + { + "epoch": 0.7003861436006492, + "grad_norm": 0.9481847724172328, + "learning_rate": 4.3506065011453645e-06, + "loss": 0.8141, + "step": 7822 + }, + { + "epoch": 0.7004756841457273, + "grad_norm": 0.9442256078249543, + "learning_rate": 4.348213616564057e-06, + "loss": 0.7861, + "step": 7823 + }, + { + "epoch": 0.7005652246908053, + "grad_norm": 0.9324253264008724, + "learning_rate": 4.345821207392605e-06, + "loss": 0.7409, + "step": 7824 + }, + { + "epoch": 0.7006547652358833, + "grad_norm": 1.197510646973898, + "learning_rate": 4.343429273832242e-06, + "loss": 0.8429, + "step": 7825 + }, + { + "epoch": 0.7007443057809615, + "grad_norm": 0.9549727419731101, + "learning_rate": 4.3410378160841785e-06, + "loss": 0.7685, + "step": 7826 + }, + { + "epoch": 0.7008338463260395, + "grad_norm": 0.8876965354083094, + "learning_rate": 4.338646834349573e-06, + "loss": 0.7565, + "step": 7827 + }, + { + "epoch": 0.7009233868711175, + "grad_norm": 0.9820012132776125, + "learning_rate": 4.336256328829547e-06, + "loss": 0.8042, + "step": 7828 + }, + { + "epoch": 0.7010129274161957, + "grad_norm": 1.026695065438196, + "learning_rate": 4.333866299725182e-06, + "loss": 0.8188, + "step": 7829 + }, + { + "epoch": 0.7011024679612737, + "grad_norm": 0.9066142969266826, + "learning_rate": 4.331476747237524e-06, + "loss": 0.8242, + "step": 7830 + }, + { + "epoch": 0.7011920085063518, + "grad_norm": 1.0006242470898197, + "learning_rate": 4.3290876715675625e-06, + "loss": 0.8117, + "step": 7831 + }, + { + "epoch": 0.7012815490514298, + "grad_norm": 1.0263349500593006, + "learning_rate": 4.326699072916269e-06, + "loss": 0.8366, + "step": 7832 + }, + { + "epoch": 0.701371089596508, + "grad_norm": 0.8933530940189127, + "learning_rate": 4.324310951484563e-06, + "loss": 0.8038, + "step": 7833 + }, + { + "epoch": 0.701460630141586, + "grad_norm": 0.9064932606278285, + "learning_rate": 4.321923307473324e-06, + "loss": 0.7977, + "step": 7834 + }, + { + "epoch": 0.701550170686664, + "grad_norm": 0.8927858256687038, + "learning_rate": 4.319536141083397e-06, + "loss": 0.7973, + "step": 7835 + }, + { + "epoch": 0.7016397112317421, + "grad_norm": 0.9699247794056655, + "learning_rate": 4.3171494525155745e-06, + "loss": 0.8298, + "step": 7836 + }, + { + "epoch": 0.7017292517768202, + "grad_norm": 1.0082420296479497, + "learning_rate": 4.314763241970622e-06, + "loss": 0.8104, + "step": 7837 + }, + { + "epoch": 0.7018187923218983, + "grad_norm": 0.9386219749028808, + "learning_rate": 4.312377509649255e-06, + "loss": 0.8301, + "step": 7838 + }, + { + "epoch": 0.7019083328669763, + "grad_norm": 0.9924220137191154, + "learning_rate": 4.309992255752161e-06, + "loss": 0.8214, + "step": 7839 + }, + { + "epoch": 0.7019978734120544, + "grad_norm": 0.893715958904001, + "learning_rate": 4.307607480479977e-06, + "loss": 0.7787, + "step": 7840 + }, + { + "epoch": 0.7020874139571325, + "grad_norm": 1.1659680417144989, + "learning_rate": 4.3052231840333055e-06, + "loss": 0.7749, + "step": 7841 + }, + { + "epoch": 0.7021769545022105, + "grad_norm": 1.1360113900712276, + "learning_rate": 4.302839366612699e-06, + "loss": 0.8193, + "step": 7842 + }, + { + "epoch": 0.7022664950472886, + "grad_norm": 1.0902357207734859, + "learning_rate": 4.300456028418679e-06, + "loss": 0.7777, + "step": 7843 + }, + { + "epoch": 0.7023560355923667, + "grad_norm": 0.9819442830933688, + "learning_rate": 4.298073169651721e-06, + "loss": 0.7683, + "step": 7844 + }, + { + "epoch": 0.7024455761374447, + "grad_norm": 0.9699269300147558, + "learning_rate": 4.295690790512271e-06, + "loss": 0.7655, + "step": 7845 + }, + { + "epoch": 0.7025351166825228, + "grad_norm": 1.318565760918533, + "learning_rate": 4.293308891200727e-06, + "loss": 0.7904, + "step": 7846 + }, + { + "epoch": 0.7026246572276009, + "grad_norm": 0.8932380165667645, + "learning_rate": 4.290927471917438e-06, + "loss": 0.8129, + "step": 7847 + }, + { + "epoch": 0.702714197772679, + "grad_norm": 0.8901047211548933, + "learning_rate": 4.288546532862727e-06, + "loss": 0.762, + "step": 7848 + }, + { + "epoch": 0.702803738317757, + "grad_norm": 0.9531585357043469, + "learning_rate": 4.2861660742368695e-06, + "loss": 0.8109, + "step": 7849 + }, + { + "epoch": 0.702893278862835, + "grad_norm": 1.0439964747070103, + "learning_rate": 4.283786096240098e-06, + "loss": 0.7944, + "step": 7850 + }, + { + "epoch": 0.7029828194079132, + "grad_norm": 0.9514954874560548, + "learning_rate": 4.281406599072616e-06, + "loss": 0.8591, + "step": 7851 + }, + { + "epoch": 0.7030723599529912, + "grad_norm": 0.9358611423209198, + "learning_rate": 4.279027582934581e-06, + "loss": 0.871, + "step": 7852 + }, + { + "epoch": 0.7031619004980693, + "grad_norm": 1.1246277609593942, + "learning_rate": 4.276649048026097e-06, + "loss": 0.801, + "step": 7853 + }, + { + "epoch": 0.7032514410431473, + "grad_norm": 0.9258365067213435, + "learning_rate": 4.274270994547246e-06, + "loss": 0.8183, + "step": 7854 + }, + { + "epoch": 0.7033409815882254, + "grad_norm": 1.0393722817239102, + "learning_rate": 4.27189342269806e-06, + "loss": 0.7878, + "step": 7855 + }, + { + "epoch": 0.7034305221333035, + "grad_norm": 1.0160081285434908, + "learning_rate": 4.269516332678529e-06, + "loss": 0.8369, + "step": 7856 + }, + { + "epoch": 0.7035200626783815, + "grad_norm": 0.9505343277588941, + "learning_rate": 4.267139724688618e-06, + "loss": 0.8408, + "step": 7857 + }, + { + "epoch": 0.7036096032234597, + "grad_norm": 1.084436095234868, + "learning_rate": 4.2647635989282275e-06, + "loss": 0.8662, + "step": 7858 + }, + { + "epoch": 0.7036991437685377, + "grad_norm": 1.0138485545406704, + "learning_rate": 4.262387955597233e-06, + "loss": 0.9004, + "step": 7859 + }, + { + "epoch": 0.7037886843136157, + "grad_norm": 1.0634460732207964, + "learning_rate": 4.260012794895468e-06, + "loss": 0.7773, + "step": 7860 + }, + { + "epoch": 0.7038782248586938, + "grad_norm": 0.8835714399883221, + "learning_rate": 4.257638117022721e-06, + "loss": 0.8256, + "step": 7861 + }, + { + "epoch": 0.7039677654037719, + "grad_norm": 0.9317028246628536, + "learning_rate": 4.255263922178739e-06, + "loss": 0.7913, + "step": 7862 + }, + { + "epoch": 0.70405730594885, + "grad_norm": 0.9356333730773462, + "learning_rate": 4.252890210563244e-06, + "loss": 0.8488, + "step": 7863 + }, + { + "epoch": 0.704146846493928, + "grad_norm": 0.9926217639873891, + "learning_rate": 4.250516982375892e-06, + "loss": 0.7833, + "step": 7864 + }, + { + "epoch": 0.7042363870390062, + "grad_norm": 1.0265120533352918, + "learning_rate": 4.248144237816315e-06, + "loss": 0.8155, + "step": 7865 + }, + { + "epoch": 0.7043259275840842, + "grad_norm": 1.0513806022086791, + "learning_rate": 4.245771977084102e-06, + "loss": 0.8546, + "step": 7866 + }, + { + "epoch": 0.7044154681291622, + "grad_norm": 0.8821769700797972, + "learning_rate": 4.243400200378798e-06, + "loss": 0.7909, + "step": 7867 + }, + { + "epoch": 0.7045050086742403, + "grad_norm": 1.0525150184734302, + "learning_rate": 4.241028907899911e-06, + "loss": 0.8223, + "step": 7868 + }, + { + "epoch": 0.7045945492193184, + "grad_norm": 0.9560231789424795, + "learning_rate": 4.238658099846905e-06, + "loss": 0.8177, + "step": 7869 + }, + { + "epoch": 0.7046840897643964, + "grad_norm": 0.9082779880232594, + "learning_rate": 4.236287776419206e-06, + "loss": 0.7921, + "step": 7870 + }, + { + "epoch": 0.7047736303094745, + "grad_norm": 0.9209774468871164, + "learning_rate": 4.233917937816195e-06, + "loss": 0.782, + "step": 7871 + }, + { + "epoch": 0.7048631708545525, + "grad_norm": 0.9904592439812467, + "learning_rate": 4.231548584237219e-06, + "loss": 0.7909, + "step": 7872 + }, + { + "epoch": 0.7049527113996307, + "grad_norm": 0.8814979759439844, + "learning_rate": 4.229179715881577e-06, + "loss": 0.7606, + "step": 7873 + }, + { + "epoch": 0.7050422519447087, + "grad_norm": 0.9607445067312818, + "learning_rate": 4.226811332948534e-06, + "loss": 0.787, + "step": 7874 + }, + { + "epoch": 0.7051317924897867, + "grad_norm": 0.9329985025763997, + "learning_rate": 4.224443435637307e-06, + "loss": 0.8061, + "step": 7875 + }, + { + "epoch": 0.7052213330348649, + "grad_norm": 0.958620912046123, + "learning_rate": 4.222076024147077e-06, + "loss": 0.755, + "step": 7876 + }, + { + "epoch": 0.7053108735799429, + "grad_norm": 1.0273678410741975, + "learning_rate": 4.219709098676984e-06, + "loss": 0.7651, + "step": 7877 + }, + { + "epoch": 0.705400414125021, + "grad_norm": 0.9759808936753737, + "learning_rate": 4.2173426594261254e-06, + "loss": 0.823, + "step": 7878 + }, + { + "epoch": 0.705489954670099, + "grad_norm": 0.9248341649307702, + "learning_rate": 4.214976706593559e-06, + "loss": 0.7811, + "step": 7879 + }, + { + "epoch": 0.7055794952151772, + "grad_norm": 1.008164766325714, + "learning_rate": 4.2126112403782996e-06, + "loss": 0.7852, + "step": 7880 + }, + { + "epoch": 0.7056690357602552, + "grad_norm": 1.1703414622579127, + "learning_rate": 4.210246260979323e-06, + "loss": 0.8333, + "step": 7881 + }, + { + "epoch": 0.7057585763053332, + "grad_norm": 0.9028509865637157, + "learning_rate": 4.207881768595564e-06, + "loss": 0.7843, + "step": 7882 + }, + { + "epoch": 0.7058481168504114, + "grad_norm": 0.9838227996832009, + "learning_rate": 4.205517763425916e-06, + "loss": 0.7918, + "step": 7883 + }, + { + "epoch": 0.7059376573954894, + "grad_norm": 1.0246423285432387, + "learning_rate": 4.203154245669231e-06, + "loss": 0.8413, + "step": 7884 + }, + { + "epoch": 0.7060271979405675, + "grad_norm": 0.9534446735398414, + "learning_rate": 4.2007912155243215e-06, + "loss": 0.8007, + "step": 7885 + }, + { + "epoch": 0.7061167384856455, + "grad_norm": 1.0098657084374096, + "learning_rate": 4.198428673189956e-06, + "loss": 0.7606, + "step": 7886 + }, + { + "epoch": 0.7062062790307236, + "grad_norm": 0.9629509916070518, + "learning_rate": 4.196066618864865e-06, + "loss": 0.8154, + "step": 7887 + }, + { + "epoch": 0.7062958195758017, + "grad_norm": 0.9379535700610556, + "learning_rate": 4.193705052747737e-06, + "loss": 0.8208, + "step": 7888 + }, + { + "epoch": 0.7063853601208797, + "grad_norm": 0.9332714417153479, + "learning_rate": 4.191343975037219e-06, + "loss": 0.7736, + "step": 7889 + }, + { + "epoch": 0.7064749006659578, + "grad_norm": 0.9653329514944474, + "learning_rate": 4.18898338593192e-06, + "loss": 0.7614, + "step": 7890 + }, + { + "epoch": 0.7065644412110359, + "grad_norm": 0.957423444698433, + "learning_rate": 4.1866232856304e-06, + "loss": 0.7956, + "step": 7891 + }, + { + "epoch": 0.7066539817561139, + "grad_norm": 0.9612204566749764, + "learning_rate": 4.184263674331181e-06, + "loss": 0.8145, + "step": 7892 + }, + { + "epoch": 0.706743522301192, + "grad_norm": 1.1200635799006722, + "learning_rate": 4.181904552232753e-06, + "loss": 0.7996, + "step": 7893 + }, + { + "epoch": 0.7068330628462701, + "grad_norm": 0.9031182189730383, + "learning_rate": 4.179545919533555e-06, + "loss": 0.8206, + "step": 7894 + }, + { + "epoch": 0.7069226033913482, + "grad_norm": 1.0239648291935521, + "learning_rate": 4.177187776431991e-06, + "loss": 0.7711, + "step": 7895 + }, + { + "epoch": 0.7070121439364262, + "grad_norm": 0.9937433912198858, + "learning_rate": 4.174830123126412e-06, + "loss": 0.8238, + "step": 7896 + }, + { + "epoch": 0.7071016844815042, + "grad_norm": 0.9943993546463767, + "learning_rate": 4.1724729598151414e-06, + "loss": 0.859, + "step": 7897 + }, + { + "epoch": 0.7071912250265824, + "grad_norm": 0.9703798066369955, + "learning_rate": 4.170116286696452e-06, + "loss": 0.7966, + "step": 7898 + }, + { + "epoch": 0.7072807655716604, + "grad_norm": 1.0137997829982364, + "learning_rate": 4.167760103968585e-06, + "loss": 0.8332, + "step": 7899 + }, + { + "epoch": 0.7073703061167385, + "grad_norm": 0.9205957086889073, + "learning_rate": 4.165404411829733e-06, + "loss": 0.8347, + "step": 7900 + }, + { + "epoch": 0.7074598466618166, + "grad_norm": 0.9366670914366876, + "learning_rate": 4.163049210478053e-06, + "loss": 0.7775, + "step": 7901 + }, + { + "epoch": 0.7075493872068946, + "grad_norm": 0.9648487891203498, + "learning_rate": 4.160694500111648e-06, + "loss": 0.7761, + "step": 7902 + }, + { + "epoch": 0.7076389277519727, + "grad_norm": 0.9579742233533441, + "learning_rate": 4.158340280928593e-06, + "loss": 0.7935, + "step": 7903 + }, + { + "epoch": 0.7077284682970507, + "grad_norm": 1.0387420342653628, + "learning_rate": 4.155986553126914e-06, + "loss": 0.7674, + "step": 7904 + }, + { + "epoch": 0.7078180088421289, + "grad_norm": 0.9691208797090396, + "learning_rate": 4.153633316904606e-06, + "loss": 0.7907, + "step": 7905 + }, + { + "epoch": 0.7079075493872069, + "grad_norm": 0.9089252736690521, + "learning_rate": 4.151280572459615e-06, + "loss": 0.8024, + "step": 7906 + }, + { + "epoch": 0.7079970899322849, + "grad_norm": 1.0324167530110693, + "learning_rate": 4.14892831998984e-06, + "loss": 0.8468, + "step": 7907 + }, + { + "epoch": 0.708086630477363, + "grad_norm": 0.9349287080606827, + "learning_rate": 4.146576559693149e-06, + "loss": 0.8407, + "step": 7908 + }, + { + "epoch": 0.7081761710224411, + "grad_norm": 0.9035333457679109, + "learning_rate": 4.144225291767361e-06, + "loss": 0.8207, + "step": 7909 + }, + { + "epoch": 0.7082657115675192, + "grad_norm": 1.0195723202710272, + "learning_rate": 4.141874516410256e-06, + "loss": 0.7465, + "step": 7910 + }, + { + "epoch": 0.7083552521125972, + "grad_norm": 0.9400807474145519, + "learning_rate": 4.139524233819581e-06, + "loss": 0.8371, + "step": 7911 + }, + { + "epoch": 0.7084447926576753, + "grad_norm": 0.9352587151199779, + "learning_rate": 4.137174444193033e-06, + "loss": 0.7829, + "step": 7912 + }, + { + "epoch": 0.7085343332027534, + "grad_norm": 0.9689332243534247, + "learning_rate": 4.134825147728262e-06, + "loss": 0.8017, + "step": 7913 + }, + { + "epoch": 0.7086238737478314, + "grad_norm": 1.0010788167056794, + "learning_rate": 4.132476344622888e-06, + "loss": 0.8122, + "step": 7914 + }, + { + "epoch": 0.7087134142929095, + "grad_norm": 0.9236896594888196, + "learning_rate": 4.130128035074482e-06, + "loss": 0.8279, + "step": 7915 + }, + { + "epoch": 0.7088029548379876, + "grad_norm": 0.985686777914297, + "learning_rate": 4.127780219280574e-06, + "loss": 0.7951, + "step": 7916 + }, + { + "epoch": 0.7088924953830656, + "grad_norm": 0.863027795616886, + "learning_rate": 4.125432897438666e-06, + "loss": 0.7746, + "step": 7917 + }, + { + "epoch": 0.7089820359281437, + "grad_norm": 1.011365398333579, + "learning_rate": 4.123086069746195e-06, + "loss": 0.7568, + "step": 7918 + }, + { + "epoch": 0.7090715764732218, + "grad_norm": 0.9332451547221217, + "learning_rate": 4.1207397364005715e-06, + "loss": 0.7637, + "step": 7919 + }, + { + "epoch": 0.7091611170182999, + "grad_norm": 1.0286177760694848, + "learning_rate": 4.1183938975991644e-06, + "loss": 0.7759, + "step": 7920 + }, + { + "epoch": 0.7092506575633779, + "grad_norm": 1.007619922556112, + "learning_rate": 4.116048553539296e-06, + "loss": 0.8194, + "step": 7921 + }, + { + "epoch": 0.7093401981084559, + "grad_norm": 1.0065814748096025, + "learning_rate": 4.11370370441825e-06, + "loss": 0.7677, + "step": 7922 + }, + { + "epoch": 0.7094297386535341, + "grad_norm": 0.9501200430969721, + "learning_rate": 4.111359350433265e-06, + "loss": 0.7903, + "step": 7923 + }, + { + "epoch": 0.7095192791986121, + "grad_norm": 0.958283816949814, + "learning_rate": 4.109015491781542e-06, + "loss": 0.7639, + "step": 7924 + }, + { + "epoch": 0.7096088197436902, + "grad_norm": 0.960043186707044, + "learning_rate": 4.106672128660241e-06, + "loss": 0.8056, + "step": 7925 + }, + { + "epoch": 0.7096983602887682, + "grad_norm": 1.220801612777027, + "learning_rate": 4.104329261266474e-06, + "loss": 0.7711, + "step": 7926 + }, + { + "epoch": 0.7097879008338464, + "grad_norm": 1.0184681053866198, + "learning_rate": 4.101986889797318e-06, + "loss": 0.7886, + "step": 7927 + }, + { + "epoch": 0.7098774413789244, + "grad_norm": 0.8984661512895591, + "learning_rate": 4.099645014449805e-06, + "loss": 0.7794, + "step": 7928 + }, + { + "epoch": 0.7099669819240024, + "grad_norm": 0.9717266925490577, + "learning_rate": 4.097303635420925e-06, + "loss": 0.8038, + "step": 7929 + }, + { + "epoch": 0.7100565224690806, + "grad_norm": 0.9656954729521396, + "learning_rate": 4.094962752907628e-06, + "loss": 0.7813, + "step": 7930 + }, + { + "epoch": 0.7101460630141586, + "grad_norm": 0.9534951119145328, + "learning_rate": 4.0926223671068235e-06, + "loss": 0.7729, + "step": 7931 + }, + { + "epoch": 0.7102356035592367, + "grad_norm": 0.9891020367400325, + "learning_rate": 4.090282478215374e-06, + "loss": 0.7888, + "step": 7932 + }, + { + "epoch": 0.7103251441043147, + "grad_norm": 0.8510690078994433, + "learning_rate": 4.087943086430104e-06, + "loss": 0.7444, + "step": 7933 + }, + { + "epoch": 0.7104146846493928, + "grad_norm": 0.9998491382768321, + "learning_rate": 4.085604191947796e-06, + "loss": 0.8064, + "step": 7934 + }, + { + "epoch": 0.7105042251944709, + "grad_norm": 0.9318757738463096, + "learning_rate": 4.0832657949651895e-06, + "loss": 0.7532, + "step": 7935 + }, + { + "epoch": 0.7105937657395489, + "grad_norm": 1.0046147108323689, + "learning_rate": 4.080927895678984e-06, + "loss": 0.8176, + "step": 7936 + }, + { + "epoch": 0.7106833062846271, + "grad_norm": 0.8537130152515398, + "learning_rate": 4.078590494285835e-06, + "loss": 0.789, + "step": 7937 + }, + { + "epoch": 0.7107728468297051, + "grad_norm": 0.9281267347927185, + "learning_rate": 4.07625359098236e-06, + "loss": 0.8354, + "step": 7938 + }, + { + "epoch": 0.7108623873747831, + "grad_norm": 1.0736654965205041, + "learning_rate": 4.073917185965126e-06, + "loss": 0.8491, + "step": 7939 + }, + { + "epoch": 0.7109519279198612, + "grad_norm": 0.9727907542381893, + "learning_rate": 4.0715812794306685e-06, + "loss": 0.7846, + "step": 7940 + }, + { + "epoch": 0.7110414684649393, + "grad_norm": 0.9444498914137567, + "learning_rate": 4.069245871575474e-06, + "loss": 0.8057, + "step": 7941 + }, + { + "epoch": 0.7111310090100174, + "grad_norm": 0.8752647310048607, + "learning_rate": 4.066910962595992e-06, + "loss": 0.7933, + "step": 7942 + }, + { + "epoch": 0.7112205495550954, + "grad_norm": 1.3559600165104373, + "learning_rate": 4.064576552688624e-06, + "loss": 0.7946, + "step": 7943 + }, + { + "epoch": 0.7113100901001734, + "grad_norm": 1.0482616943537175, + "learning_rate": 4.062242642049735e-06, + "loss": 0.791, + "step": 7944 + }, + { + "epoch": 0.7113996306452516, + "grad_norm": 0.9705393193805912, + "learning_rate": 4.05990923087565e-06, + "loss": 0.7481, + "step": 7945 + }, + { + "epoch": 0.7114891711903296, + "grad_norm": 0.9004170629753756, + "learning_rate": 4.057576319362635e-06, + "loss": 0.7807, + "step": 7946 + }, + { + "epoch": 0.7115787117354077, + "grad_norm": 0.9892818435110183, + "learning_rate": 4.0552439077069395e-06, + "loss": 0.7834, + "step": 7947 + }, + { + "epoch": 0.7116682522804858, + "grad_norm": 1.210605684692914, + "learning_rate": 4.052911996104754e-06, + "loss": 0.778, + "step": 7948 + }, + { + "epoch": 0.7117577928255638, + "grad_norm": 0.9730425979151602, + "learning_rate": 4.050580584752232e-06, + "loss": 0.7394, + "step": 7949 + }, + { + "epoch": 0.7118473333706419, + "grad_norm": 0.9459761549118909, + "learning_rate": 4.048249673845487e-06, + "loss": 0.8388, + "step": 7950 + }, + { + "epoch": 0.7119368739157199, + "grad_norm": 1.0157323617866478, + "learning_rate": 4.045919263580581e-06, + "loss": 0.7967, + "step": 7951 + }, + { + "epoch": 0.7120264144607981, + "grad_norm": 0.9730101016927492, + "learning_rate": 4.043589354153541e-06, + "loss": 0.8552, + "step": 7952 + }, + { + "epoch": 0.7121159550058761, + "grad_norm": 1.066143243095896, + "learning_rate": 4.041259945760357e-06, + "loss": 0.8064, + "step": 7953 + }, + { + "epoch": 0.7122054955509541, + "grad_norm": 1.0165902162100957, + "learning_rate": 4.038931038596969e-06, + "loss": 0.8303, + "step": 7954 + }, + { + "epoch": 0.7122950360960323, + "grad_norm": 0.8840146987770654, + "learning_rate": 4.03660263285928e-06, + "loss": 0.8135, + "step": 7955 + }, + { + "epoch": 0.7123845766411103, + "grad_norm": 0.899977793439772, + "learning_rate": 4.034274728743141e-06, + "loss": 0.8084, + "step": 7956 + }, + { + "epoch": 0.7124741171861884, + "grad_norm": 0.9712973427485663, + "learning_rate": 4.031947326444372e-06, + "loss": 0.7998, + "step": 7957 + }, + { + "epoch": 0.7125636577312664, + "grad_norm": 0.8740344209898921, + "learning_rate": 4.029620426158742e-06, + "loss": 0.8192, + "step": 7958 + }, + { + "epoch": 0.7126531982763445, + "grad_norm": 0.9557553227333138, + "learning_rate": 4.02729402808199e-06, + "loss": 0.817, + "step": 7959 + }, + { + "epoch": 0.7127427388214226, + "grad_norm": 0.9432002157250226, + "learning_rate": 4.0249681324098e-06, + "loss": 0.7738, + "step": 7960 + }, + { + "epoch": 0.7128322793665006, + "grad_norm": 1.0066602902148762, + "learning_rate": 4.022642739337824e-06, + "loss": 0.8013, + "step": 7961 + }, + { + "epoch": 0.7129218199115787, + "grad_norm": 0.957436151866808, + "learning_rate": 4.020317849061658e-06, + "loss": 0.829, + "step": 7962 + }, + { + "epoch": 0.7130113604566568, + "grad_norm": 1.0110497044311084, + "learning_rate": 4.017993461776869e-06, + "loss": 0.7691, + "step": 7963 + }, + { + "epoch": 0.7131009010017348, + "grad_norm": 0.9986891888961377, + "learning_rate": 4.0156695776789736e-06, + "loss": 0.8277, + "step": 7964 + }, + { + "epoch": 0.7131904415468129, + "grad_norm": 1.183629025985562, + "learning_rate": 4.013346196963455e-06, + "loss": 0.7621, + "step": 7965 + }, + { + "epoch": 0.713279982091891, + "grad_norm": 1.0496257323601976, + "learning_rate": 4.01102331982575e-06, + "loss": 0.7961, + "step": 7966 + }, + { + "epoch": 0.7133695226369691, + "grad_norm": 1.0149202691127053, + "learning_rate": 4.0087009464612426e-06, + "loss": 0.7539, + "step": 7967 + }, + { + "epoch": 0.7134590631820471, + "grad_norm": 0.9588487319642659, + "learning_rate": 4.006379077065288e-06, + "loss": 0.8085, + "step": 7968 + }, + { + "epoch": 0.7135486037271251, + "grad_norm": 0.9272255713327721, + "learning_rate": 4.004057711833193e-06, + "loss": 0.7819, + "step": 7969 + }, + { + "epoch": 0.7136381442722033, + "grad_norm": 0.9325813789105739, + "learning_rate": 4.001736850960222e-06, + "loss": 0.8246, + "step": 7970 + }, + { + "epoch": 0.7137276848172813, + "grad_norm": 1.010335752112128, + "learning_rate": 3.999416494641604e-06, + "loss": 0.8179, + "step": 7971 + }, + { + "epoch": 0.7138172253623594, + "grad_norm": 0.8859424094485543, + "learning_rate": 3.997096643072519e-06, + "loss": 0.8206, + "step": 7972 + }, + { + "epoch": 0.7139067659074375, + "grad_norm": 0.9282613048012488, + "learning_rate": 3.9947772964481e-06, + "loss": 0.7969, + "step": 7973 + }, + { + "epoch": 0.7139963064525156, + "grad_norm": 0.9419502149154005, + "learning_rate": 3.992458454963445e-06, + "loss": 0.8046, + "step": 7974 + }, + { + "epoch": 0.7140858469975936, + "grad_norm": 1.017906708025248, + "learning_rate": 3.990140118813608e-06, + "loss": 0.8518, + "step": 7975 + }, + { + "epoch": 0.7141753875426716, + "grad_norm": 0.8846642506074188, + "learning_rate": 3.9878222881936e-06, + "loss": 0.8395, + "step": 7976 + }, + { + "epoch": 0.7142649280877498, + "grad_norm": 0.9024168813494983, + "learning_rate": 3.98550496329839e-06, + "loss": 0.7929, + "step": 7977 + }, + { + "epoch": 0.7143544686328278, + "grad_norm": 0.9371200847778404, + "learning_rate": 3.983188144322903e-06, + "loss": 0.7665, + "step": 7978 + }, + { + "epoch": 0.7144440091779058, + "grad_norm": 0.9591274244960174, + "learning_rate": 3.980871831462021e-06, + "loss": 0.7747, + "step": 7979 + }, + { + "epoch": 0.7145335497229839, + "grad_norm": 1.0776678325139482, + "learning_rate": 3.978556024910587e-06, + "loss": 0.8369, + "step": 7980 + }, + { + "epoch": 0.714623090268062, + "grad_norm": 0.9513783281966097, + "learning_rate": 3.976240724863397e-06, + "loss": 0.8396, + "step": 7981 + }, + { + "epoch": 0.7147126308131401, + "grad_norm": 0.9722841782002879, + "learning_rate": 3.973925931515209e-06, + "loss": 0.8576, + "step": 7982 + }, + { + "epoch": 0.7148021713582181, + "grad_norm": 1.0040634137016153, + "learning_rate": 3.971611645060733e-06, + "loss": 0.8162, + "step": 7983 + }, + { + "epoch": 0.7148917119032963, + "grad_norm": 0.9237933316661637, + "learning_rate": 3.969297865694641e-06, + "loss": 0.763, + "step": 7984 + }, + { + "epoch": 0.7149812524483743, + "grad_norm": 0.9499048967072253, + "learning_rate": 3.966984593611562e-06, + "loss": 0.7532, + "step": 7985 + }, + { + "epoch": 0.7150707929934523, + "grad_norm": 1.1389897159918918, + "learning_rate": 3.964671829006077e-06, + "loss": 0.8011, + "step": 7986 + }, + { + "epoch": 0.7151603335385304, + "grad_norm": 1.0261115567855932, + "learning_rate": 3.962359572072731e-06, + "loss": 0.8149, + "step": 7987 + }, + { + "epoch": 0.7152498740836085, + "grad_norm": 1.1441028080738103, + "learning_rate": 3.960047823006024e-06, + "loss": 0.8059, + "step": 7988 + }, + { + "epoch": 0.7153394146286866, + "grad_norm": 1.160074525132683, + "learning_rate": 3.957736582000411e-06, + "loss": 0.7693, + "step": 7989 + }, + { + "epoch": 0.7154289551737646, + "grad_norm": 0.9672790373711078, + "learning_rate": 3.955425849250306e-06, + "loss": 0.7985, + "step": 7990 + }, + { + "epoch": 0.7155184957188427, + "grad_norm": 0.9215136614405941, + "learning_rate": 3.953115624950082e-06, + "loss": 0.8289, + "step": 7991 + }, + { + "epoch": 0.7156080362639208, + "grad_norm": 0.9938147266252024, + "learning_rate": 3.950805909294067e-06, + "loss": 0.8112, + "step": 7992 + }, + { + "epoch": 0.7156975768089988, + "grad_norm": 1.0276848101316947, + "learning_rate": 3.9484967024765455e-06, + "loss": 0.8623, + "step": 7993 + }, + { + "epoch": 0.7157871173540769, + "grad_norm": 0.9755649065242386, + "learning_rate": 3.946188004691761e-06, + "loss": 0.8213, + "step": 7994 + }, + { + "epoch": 0.715876657899155, + "grad_norm": 1.0073359299386058, + "learning_rate": 3.943879816133915e-06, + "loss": 0.757, + "step": 7995 + }, + { + "epoch": 0.715966198444233, + "grad_norm": 0.9160595124822789, + "learning_rate": 3.941572136997164e-06, + "loss": 0.7846, + "step": 7996 + }, + { + "epoch": 0.7160557389893111, + "grad_norm": 0.9371290887147591, + "learning_rate": 3.939264967475621e-06, + "loss": 0.7846, + "step": 7997 + }, + { + "epoch": 0.7161452795343891, + "grad_norm": 0.8692792357205559, + "learning_rate": 3.936958307763359e-06, + "loss": 0.805, + "step": 7998 + }, + { + "epoch": 0.7162348200794673, + "grad_norm": 0.905193356552538, + "learning_rate": 3.934652158054411e-06, + "loss": 0.8427, + "step": 7999 + }, + { + "epoch": 0.7163243606245453, + "grad_norm": 1.032344251142508, + "learning_rate": 3.93234651854275e-06, + "loss": 0.7878, + "step": 8000 + }, + { + "epoch": 0.7164139011696233, + "grad_norm": 1.0087972887651344, + "learning_rate": 3.930041389422331e-06, + "loss": 0.7603, + "step": 8001 + }, + { + "epoch": 0.7165034417147015, + "grad_norm": 0.9059150175063786, + "learning_rate": 3.927736770887051e-06, + "loss": 0.7677, + "step": 8002 + }, + { + "epoch": 0.7165929822597795, + "grad_norm": 0.92748998457732, + "learning_rate": 3.925432663130765e-06, + "loss": 0.8345, + "step": 8003 + }, + { + "epoch": 0.7166825228048576, + "grad_norm": 1.1181317201951209, + "learning_rate": 3.9231290663472885e-06, + "loss": 0.8411, + "step": 8004 + }, + { + "epoch": 0.7167720633499356, + "grad_norm": 0.9313268099527412, + "learning_rate": 3.920825980730396e-06, + "loss": 0.8042, + "step": 8005 + }, + { + "epoch": 0.7168616038950137, + "grad_norm": 0.9946674575222921, + "learning_rate": 3.918523406473805e-06, + "loss": 0.7948, + "step": 8006 + }, + { + "epoch": 0.7169511444400918, + "grad_norm": 0.9288893990107036, + "learning_rate": 3.916221343771211e-06, + "loss": 0.8106, + "step": 8007 + }, + { + "epoch": 0.7170406849851698, + "grad_norm": 0.9053957623973863, + "learning_rate": 3.913919792816252e-06, + "loss": 0.765, + "step": 8008 + }, + { + "epoch": 0.717130225530248, + "grad_norm": 1.0021944640227343, + "learning_rate": 3.911618753802526e-06, + "loss": 0.7994, + "step": 8009 + }, + { + "epoch": 0.717219766075326, + "grad_norm": 1.0033825936963994, + "learning_rate": 3.909318226923595e-06, + "loss": 0.7544, + "step": 8010 + }, + { + "epoch": 0.717309306620404, + "grad_norm": 1.2158394849756007, + "learning_rate": 3.9070182123729635e-06, + "loss": 0.849, + "step": 8011 + }, + { + "epoch": 0.7173988471654821, + "grad_norm": 0.9184268916762881, + "learning_rate": 3.904718710344101e-06, + "loss": 0.7671, + "step": 8012 + }, + { + "epoch": 0.7174883877105602, + "grad_norm": 0.9125189166497218, + "learning_rate": 3.9024197210304415e-06, + "loss": 0.7582, + "step": 8013 + }, + { + "epoch": 0.7175779282556383, + "grad_norm": 1.0523067583606374, + "learning_rate": 3.900121244625366e-06, + "loss": 0.8017, + "step": 8014 + }, + { + "epoch": 0.7176674688007163, + "grad_norm": 1.0256777600298561, + "learning_rate": 3.897823281322212e-06, + "loss": 0.8007, + "step": 8015 + }, + { + "epoch": 0.7177570093457943, + "grad_norm": 1.0869108154789842, + "learning_rate": 3.895525831314282e-06, + "loss": 0.8211, + "step": 8016 + }, + { + "epoch": 0.7178465498908725, + "grad_norm": 1.2495996134599217, + "learning_rate": 3.893228894794824e-06, + "loss": 0.795, + "step": 8017 + }, + { + "epoch": 0.7179360904359505, + "grad_norm": 0.9950749795943328, + "learning_rate": 3.8909324719570465e-06, + "loss": 0.8463, + "step": 8018 + }, + { + "epoch": 0.7180256309810286, + "grad_norm": 0.95745753774366, + "learning_rate": 3.888636562994126e-06, + "loss": 0.7838, + "step": 8019 + }, + { + "epoch": 0.7181151715261067, + "grad_norm": 1.0524359568894825, + "learning_rate": 3.886341168099182e-06, + "loss": 0.7946, + "step": 8020 + }, + { + "epoch": 0.7182047120711847, + "grad_norm": 0.9278183375525393, + "learning_rate": 3.884046287465301e-06, + "loss": 0.8409, + "step": 8021 + }, + { + "epoch": 0.7182942526162628, + "grad_norm": 0.9364164843220585, + "learning_rate": 3.881751921285511e-06, + "loss": 0.8118, + "step": 8022 + }, + { + "epoch": 0.7183837931613408, + "grad_norm": 1.0136311894022136, + "learning_rate": 3.879458069752814e-06, + "loss": 0.8571, + "step": 8023 + }, + { + "epoch": 0.718473333706419, + "grad_norm": 1.0017969451364805, + "learning_rate": 3.877164733060154e-06, + "loss": 0.7609, + "step": 8024 + }, + { + "epoch": 0.718562874251497, + "grad_norm": 0.8972703093890377, + "learning_rate": 3.874871911400449e-06, + "loss": 0.7891, + "step": 8025 + }, + { + "epoch": 0.718652414796575, + "grad_norm": 1.0252206317435733, + "learning_rate": 3.872579604966561e-06, + "loss": 0.8407, + "step": 8026 + }, + { + "epoch": 0.7187419553416532, + "grad_norm": 0.9459550098041324, + "learning_rate": 3.870287813951307e-06, + "loss": 0.8029, + "step": 8027 + }, + { + "epoch": 0.7188314958867312, + "grad_norm": 1.15623606566502, + "learning_rate": 3.867996538547466e-06, + "loss": 0.8109, + "step": 8028 + }, + { + "epoch": 0.7189210364318093, + "grad_norm": 1.0318236631971909, + "learning_rate": 3.865705778947774e-06, + "loss": 0.8068, + "step": 8029 + }, + { + "epoch": 0.7190105769768873, + "grad_norm": 0.9899560999344845, + "learning_rate": 3.863415535344922e-06, + "loss": 0.7837, + "step": 8030 + }, + { + "epoch": 0.7191001175219655, + "grad_norm": 0.9112563641482628, + "learning_rate": 3.861125807931555e-06, + "loss": 0.8358, + "step": 8031 + }, + { + "epoch": 0.7191896580670435, + "grad_norm": 0.9849194139074654, + "learning_rate": 3.858836596900286e-06, + "loss": 0.8483, + "step": 8032 + }, + { + "epoch": 0.7192791986121215, + "grad_norm": 0.8952514405515637, + "learning_rate": 3.856547902443668e-06, + "loss": 0.7663, + "step": 8033 + }, + { + "epoch": 0.7193687391571996, + "grad_norm": 0.9354199453808414, + "learning_rate": 3.85425972475422e-06, + "loss": 0.7526, + "step": 8034 + }, + { + "epoch": 0.7194582797022777, + "grad_norm": 1.0062265731282394, + "learning_rate": 3.8519720640244174e-06, + "loss": 0.7762, + "step": 8035 + }, + { + "epoch": 0.7195478202473558, + "grad_norm": 0.9562340083177004, + "learning_rate": 3.8496849204466906e-06, + "loss": 0.7831, + "step": 8036 + }, + { + "epoch": 0.7196373607924338, + "grad_norm": 0.997124203732317, + "learning_rate": 3.847398294213425e-06, + "loss": 0.8162, + "step": 8037 + }, + { + "epoch": 0.7197269013375119, + "grad_norm": 0.865633526356508, + "learning_rate": 3.845112185516966e-06, + "loss": 0.8034, + "step": 8038 + }, + { + "epoch": 0.71981644188259, + "grad_norm": 0.9179973980461723, + "learning_rate": 3.842826594549612e-06, + "loss": 0.8267, + "step": 8039 + }, + { + "epoch": 0.719905982427668, + "grad_norm": 0.9644592330231287, + "learning_rate": 3.840541521503622e-06, + "loss": 0.794, + "step": 8040 + }, + { + "epoch": 0.719995522972746, + "grad_norm": 0.9008078217844488, + "learning_rate": 3.838256966571207e-06, + "loss": 0.811, + "step": 8041 + }, + { + "epoch": 0.7200850635178242, + "grad_norm": 0.9649580178942744, + "learning_rate": 3.835972929944537e-06, + "loss": 0.7526, + "step": 8042 + }, + { + "epoch": 0.7201746040629022, + "grad_norm": 1.2026079919165602, + "learning_rate": 3.833689411815736e-06, + "loss": 0.8408, + "step": 8043 + }, + { + "epoch": 0.7202641446079803, + "grad_norm": 0.8753704204773811, + "learning_rate": 3.831406412376889e-06, + "loss": 0.8079, + "step": 8044 + }, + { + "epoch": 0.7203536851530584, + "grad_norm": 0.8803886757760556, + "learning_rate": 3.829123931820031e-06, + "loss": 0.7928, + "step": 8045 + }, + { + "epoch": 0.7204432256981365, + "grad_norm": 0.9163872344600541, + "learning_rate": 3.8268419703371605e-06, + "loss": 0.7831, + "step": 8046 + }, + { + "epoch": 0.7205327662432145, + "grad_norm": 0.8961934150094862, + "learning_rate": 3.824560528120227e-06, + "loss": 0.8116, + "step": 8047 + }, + { + "epoch": 0.7206223067882925, + "grad_norm": 0.8796961345182243, + "learning_rate": 3.822279605361138e-06, + "loss": 0.8211, + "step": 8048 + }, + { + "epoch": 0.7207118473333707, + "grad_norm": 0.9527637654143722, + "learning_rate": 3.819999202251756e-06, + "loss": 0.7861, + "step": 8049 + }, + { + "epoch": 0.7208013878784487, + "grad_norm": 1.0914293678368323, + "learning_rate": 3.817719318983903e-06, + "loss": 0.8075, + "step": 8050 + }, + { + "epoch": 0.7208909284235268, + "grad_norm": 0.9175555823292989, + "learning_rate": 3.815439955749355e-06, + "loss": 0.7916, + "step": 8051 + }, + { + "epoch": 0.7209804689686048, + "grad_norm": 0.9683923944958911, + "learning_rate": 3.8131611127398436e-06, + "loss": 0.7975, + "step": 8052 + }, + { + "epoch": 0.7210700095136829, + "grad_norm": 1.1111248589629346, + "learning_rate": 3.810882790147059e-06, + "loss": 0.8446, + "step": 8053 + }, + { + "epoch": 0.721159550058761, + "grad_norm": 0.866830034766766, + "learning_rate": 3.8086049881626453e-06, + "loss": 0.757, + "step": 8054 + }, + { + "epoch": 0.721249090603839, + "grad_norm": 0.9333112125504118, + "learning_rate": 3.8063277069782047e-06, + "loss": 0.7649, + "step": 8055 + }, + { + "epoch": 0.7213386311489172, + "grad_norm": 0.9682247942287495, + "learning_rate": 3.8040509467852926e-06, + "loss": 0.7856, + "step": 8056 + }, + { + "epoch": 0.7214281716939952, + "grad_norm": 1.0255023826794731, + "learning_rate": 3.8017747077754252e-06, + "loss": 0.7964, + "step": 8057 + }, + { + "epoch": 0.7215177122390732, + "grad_norm": 1.0998535628079154, + "learning_rate": 3.79949899014007e-06, + "loss": 0.7649, + "step": 8058 + }, + { + "epoch": 0.7216072527841513, + "grad_norm": 1.0307667273747294, + "learning_rate": 3.797223794070659e-06, + "loss": 0.8281, + "step": 8059 + }, + { + "epoch": 0.7216967933292294, + "grad_norm": 0.9274621816833512, + "learning_rate": 3.794949119758562e-06, + "loss": 0.7855, + "step": 8060 + }, + { + "epoch": 0.7217863338743075, + "grad_norm": 0.9866631774880115, + "learning_rate": 3.792674967395128e-06, + "loss": 0.8064, + "step": 8061 + }, + { + "epoch": 0.7218758744193855, + "grad_norm": 0.8910589452060911, + "learning_rate": 3.7904013371716485e-06, + "loss": 0.8252, + "step": 8062 + }, + { + "epoch": 0.7219654149644636, + "grad_norm": 1.0353101918553995, + "learning_rate": 3.788128229279373e-06, + "loss": 0.8544, + "step": 8063 + }, + { + "epoch": 0.7220549555095417, + "grad_norm": 1.1380655138446412, + "learning_rate": 3.7858556439095073e-06, + "loss": 0.7387, + "step": 8064 + }, + { + "epoch": 0.7221444960546197, + "grad_norm": 1.0295647522710205, + "learning_rate": 3.7835835812532194e-06, + "loss": 0.834, + "step": 8065 + }, + { + "epoch": 0.7222340365996978, + "grad_norm": 0.9888002351891818, + "learning_rate": 3.781312041501616e-06, + "loss": 0.8066, + "step": 8066 + }, + { + "epoch": 0.7223235771447759, + "grad_norm": 1.062838979211488, + "learning_rate": 3.779041024845782e-06, + "loss": 0.8262, + "step": 8067 + }, + { + "epoch": 0.722413117689854, + "grad_norm": 0.9898503839660485, + "learning_rate": 3.7767705314767444e-06, + "loss": 0.8307, + "step": 8068 + }, + { + "epoch": 0.722502658234932, + "grad_norm": 1.28546456795325, + "learning_rate": 3.77450056158549e-06, + "loss": 0.7595, + "step": 8069 + }, + { + "epoch": 0.72259219878001, + "grad_norm": 0.9323703622844991, + "learning_rate": 3.7722311153629654e-06, + "loss": 0.8278, + "step": 8070 + }, + { + "epoch": 0.7226817393250882, + "grad_norm": 1.0569201472244942, + "learning_rate": 3.7699621930000617e-06, + "loss": 0.8052, + "step": 8071 + }, + { + "epoch": 0.7227712798701662, + "grad_norm": 0.8216402297424501, + "learning_rate": 3.7676937946876324e-06, + "loss": 0.8542, + "step": 8072 + }, + { + "epoch": 0.7228608204152442, + "grad_norm": 1.0250025859374998, + "learning_rate": 3.7654259206164956e-06, + "loss": 0.8111, + "step": 8073 + }, + { + "epoch": 0.7229503609603224, + "grad_norm": 0.9852012841158032, + "learning_rate": 3.763158570977413e-06, + "loss": 0.8629, + "step": 8074 + }, + { + "epoch": 0.7230399015054004, + "grad_norm": 0.9445473731434566, + "learning_rate": 3.7608917459611083e-06, + "loss": 0.7752, + "step": 8075 + }, + { + "epoch": 0.7231294420504785, + "grad_norm": 0.8854110373307847, + "learning_rate": 3.7586254457582615e-06, + "loss": 0.7903, + "step": 8076 + }, + { + "epoch": 0.7232189825955565, + "grad_norm": 1.0782779709867207, + "learning_rate": 3.7563596705595006e-06, + "loss": 0.818, + "step": 8077 + }, + { + "epoch": 0.7233085231406347, + "grad_norm": 1.2375401834473274, + "learning_rate": 3.754094420555414e-06, + "loss": 0.8289, + "step": 8078 + }, + { + "epoch": 0.7233980636857127, + "grad_norm": 0.8681756008706156, + "learning_rate": 3.7518296959365542e-06, + "loss": 0.7578, + "step": 8079 + }, + { + "epoch": 0.7234876042307907, + "grad_norm": 0.9224835569109648, + "learning_rate": 3.74956549689342e-06, + "loss": 0.8005, + "step": 8080 + }, + { + "epoch": 0.7235771447758689, + "grad_norm": 0.9455182529160145, + "learning_rate": 3.7473018236164715e-06, + "loss": 0.806, + "step": 8081 + }, + { + "epoch": 0.7236666853209469, + "grad_norm": 1.0293908593967704, + "learning_rate": 3.7450386762961145e-06, + "loss": 0.8459, + "step": 8082 + }, + { + "epoch": 0.723756225866025, + "grad_norm": 0.9239862937412785, + "learning_rate": 3.742776055122721e-06, + "loss": 0.7544, + "step": 8083 + }, + { + "epoch": 0.723845766411103, + "grad_norm": 0.9302986884047778, + "learning_rate": 3.7405139602866146e-06, + "loss": 0.8017, + "step": 8084 + }, + { + "epoch": 0.7239353069561811, + "grad_norm": 0.9108004997925813, + "learning_rate": 3.7382523919780732e-06, + "loss": 0.7921, + "step": 8085 + }, + { + "epoch": 0.7240248475012592, + "grad_norm": 1.0932783116028644, + "learning_rate": 3.735991350387339e-06, + "loss": 0.7476, + "step": 8086 + }, + { + "epoch": 0.7241143880463372, + "grad_norm": 0.9335525755226466, + "learning_rate": 3.733730835704603e-06, + "loss": 0.8144, + "step": 8087 + }, + { + "epoch": 0.7242039285914152, + "grad_norm": 1.0327189325007675, + "learning_rate": 3.731470848120006e-06, + "loss": 0.8083, + "step": 8088 + }, + { + "epoch": 0.7242934691364934, + "grad_norm": 0.9840277520250201, + "learning_rate": 3.7292113878236537e-06, + "loss": 0.8565, + "step": 8089 + }, + { + "epoch": 0.7243830096815714, + "grad_norm": 1.0670242787033324, + "learning_rate": 3.7269524550056045e-06, + "loss": 0.8032, + "step": 8090 + }, + { + "epoch": 0.7244725502266495, + "grad_norm": 1.0434151671534462, + "learning_rate": 3.724694049855869e-06, + "loss": 0.8287, + "step": 8091 + }, + { + "epoch": 0.7245620907717276, + "grad_norm": 0.9723349670942161, + "learning_rate": 3.7224361725644285e-06, + "loss": 0.8419, + "step": 8092 + }, + { + "epoch": 0.7246516313168057, + "grad_norm": 1.023858203091878, + "learning_rate": 3.7201788233211965e-06, + "loss": 0.8014, + "step": 8093 + }, + { + "epoch": 0.7247411718618837, + "grad_norm": 1.0487199548722101, + "learning_rate": 3.717922002316059e-06, + "loss": 0.7957, + "step": 8094 + }, + { + "epoch": 0.7248307124069617, + "grad_norm": 0.9784360260851159, + "learning_rate": 3.7156657097388493e-06, + "loss": 0.8156, + "step": 8095 + }, + { + "epoch": 0.7249202529520399, + "grad_norm": 0.9399933535671251, + "learning_rate": 3.7134099457793625e-06, + "loss": 0.826, + "step": 8096 + }, + { + "epoch": 0.7250097934971179, + "grad_norm": 0.8641708179418636, + "learning_rate": 3.7111547106273448e-06, + "loss": 0.8166, + "step": 8097 + }, + { + "epoch": 0.725099334042196, + "grad_norm": 1.4610792170627893, + "learning_rate": 3.7089000044724997e-06, + "loss": 0.7741, + "step": 8098 + }, + { + "epoch": 0.7251888745872741, + "grad_norm": 0.9777267329792186, + "learning_rate": 3.706645827504485e-06, + "loss": 0.8278, + "step": 8099 + }, + { + "epoch": 0.7252784151323521, + "grad_norm": 0.8817027317092367, + "learning_rate": 3.7043921799129145e-06, + "loss": 0.8039, + "step": 8100 + }, + { + "epoch": 0.7253679556774302, + "grad_norm": 0.9451867599978477, + "learning_rate": 3.7021390618873587e-06, + "loss": 0.7534, + "step": 8101 + }, + { + "epoch": 0.7254574962225082, + "grad_norm": 0.9700691957493127, + "learning_rate": 3.6998864736173425e-06, + "loss": 0.811, + "step": 8102 + }, + { + "epoch": 0.7255470367675864, + "grad_norm": 0.9743847232684555, + "learning_rate": 3.697634415292346e-06, + "loss": 0.8426, + "step": 8103 + }, + { + "epoch": 0.7256365773126644, + "grad_norm": 0.9698954052937843, + "learning_rate": 3.695382887101805e-06, + "loss": 0.8023, + "step": 8104 + }, + { + "epoch": 0.7257261178577424, + "grad_norm": 0.9104559750589593, + "learning_rate": 3.69313188923511e-06, + "loss": 0.7699, + "step": 8105 + }, + { + "epoch": 0.7258156584028205, + "grad_norm": 0.905320770822798, + "learning_rate": 3.690881421881609e-06, + "loss": 0.8161, + "step": 8106 + }, + { + "epoch": 0.7259051989478986, + "grad_norm": 0.893614236010859, + "learning_rate": 3.6886314852306025e-06, + "loss": 0.8037, + "step": 8107 + }, + { + "epoch": 0.7259947394929767, + "grad_norm": 1.0413342803925896, + "learning_rate": 3.686382079471349e-06, + "loss": 0.7249, + "step": 8108 + }, + { + "epoch": 0.7260842800380547, + "grad_norm": 0.9729440231252229, + "learning_rate": 3.684133204793061e-06, + "loss": 0.7961, + "step": 8109 + }, + { + "epoch": 0.7261738205831328, + "grad_norm": 1.127014078092048, + "learning_rate": 3.6818848613849056e-06, + "loss": 0.7793, + "step": 8110 + }, + { + "epoch": 0.7262633611282109, + "grad_norm": 0.9326193113021066, + "learning_rate": 3.679637049436008e-06, + "loss": 0.8047, + "step": 8111 + }, + { + "epoch": 0.7263529016732889, + "grad_norm": 0.9335242891812642, + "learning_rate": 3.677389769135444e-06, + "loss": 0.8234, + "step": 8112 + }, + { + "epoch": 0.726442442218367, + "grad_norm": 0.9085982521571315, + "learning_rate": 3.6751430206722506e-06, + "loss": 0.8111, + "step": 8113 + }, + { + "epoch": 0.7265319827634451, + "grad_norm": 0.9367893990429778, + "learning_rate": 3.672896804235414e-06, + "loss": 0.8501, + "step": 8114 + }, + { + "epoch": 0.7266215233085231, + "grad_norm": 1.0104586939624385, + "learning_rate": 3.6706511200138807e-06, + "loss": 0.8373, + "step": 8115 + }, + { + "epoch": 0.7267110638536012, + "grad_norm": 0.9166733516354795, + "learning_rate": 3.66840596819655e-06, + "loss": 0.7828, + "step": 8116 + }, + { + "epoch": 0.7268006043986793, + "grad_norm": 0.8962816712159897, + "learning_rate": 3.666161348972277e-06, + "loss": 0.7993, + "step": 8117 + }, + { + "epoch": 0.7268901449437574, + "grad_norm": 0.9996413295607297, + "learning_rate": 3.6639172625298703e-06, + "loss": 0.8286, + "step": 8118 + }, + { + "epoch": 0.7269796854888354, + "grad_norm": 1.0523346870678778, + "learning_rate": 3.661673709058099e-06, + "loss": 0.7637, + "step": 8119 + }, + { + "epoch": 0.7270692260339134, + "grad_norm": 1.0060814989737494, + "learning_rate": 3.6594306887456744e-06, + "loss": 0.8259, + "step": 8120 + }, + { + "epoch": 0.7271587665789916, + "grad_norm": 1.021275517182984, + "learning_rate": 3.657188201781282e-06, + "loss": 0.8362, + "step": 8121 + }, + { + "epoch": 0.7272483071240696, + "grad_norm": 0.986303850086801, + "learning_rate": 3.654946248353548e-06, + "loss": 0.8212, + "step": 8122 + }, + { + "epoch": 0.7273378476691477, + "grad_norm": 1.083852868023282, + "learning_rate": 3.6527048286510604e-06, + "loss": 0.8105, + "step": 8123 + }, + { + "epoch": 0.7274273882142257, + "grad_norm": 1.081898490144128, + "learning_rate": 3.650463942862357e-06, + "loss": 0.8135, + "step": 8124 + }, + { + "epoch": 0.7275169287593038, + "grad_norm": 0.9548603089428934, + "learning_rate": 3.648223591175939e-06, + "loss": 0.8197, + "step": 8125 + }, + { + "epoch": 0.7276064693043819, + "grad_norm": 1.0177733505314792, + "learning_rate": 3.6459837737802484e-06, + "loss": 0.8166, + "step": 8126 + }, + { + "epoch": 0.7276960098494599, + "grad_norm": 0.891809750796513, + "learning_rate": 3.643744490863699e-06, + "loss": 0.8006, + "step": 8127 + }, + { + "epoch": 0.7277855503945381, + "grad_norm": 1.0402400784847927, + "learning_rate": 3.6415057426146504e-06, + "loss": 0.8434, + "step": 8128 + }, + { + "epoch": 0.7278750909396161, + "grad_norm": 1.0160968105500245, + "learning_rate": 3.6392675292214185e-06, + "loss": 0.8672, + "step": 8129 + }, + { + "epoch": 0.7279646314846941, + "grad_norm": 1.0061379297165198, + "learning_rate": 3.637029850872277e-06, + "loss": 0.8495, + "step": 8130 + }, + { + "epoch": 0.7280541720297722, + "grad_norm": 1.0300151491318532, + "learning_rate": 3.634792707755447e-06, + "loss": 0.7943, + "step": 8131 + }, + { + "epoch": 0.7281437125748503, + "grad_norm": 1.0234193868385502, + "learning_rate": 3.6325561000591082e-06, + "loss": 0.7727, + "step": 8132 + }, + { + "epoch": 0.7282332531199284, + "grad_norm": 1.0127265095035938, + "learning_rate": 3.6303200279714033e-06, + "loss": 0.8421, + "step": 8133 + }, + { + "epoch": 0.7283227936650064, + "grad_norm": 0.875944777756982, + "learning_rate": 3.6280844916804214e-06, + "loss": 0.7335, + "step": 8134 + }, + { + "epoch": 0.7284123342100846, + "grad_norm": 0.9626628362535917, + "learning_rate": 3.6258494913742083e-06, + "loss": 0.8109, + "step": 8135 + }, + { + "epoch": 0.7285018747551626, + "grad_norm": 0.9409644227030993, + "learning_rate": 3.6236150272407677e-06, + "loss": 0.7647, + "step": 8136 + }, + { + "epoch": 0.7285914153002406, + "grad_norm": 0.8959154973684125, + "learning_rate": 3.6213810994680487e-06, + "loss": 0.8267, + "step": 8137 + }, + { + "epoch": 0.7286809558453187, + "grad_norm": 0.9467169304626755, + "learning_rate": 3.619147708243965e-06, + "loss": 0.8219, + "step": 8138 + }, + { + "epoch": 0.7287704963903968, + "grad_norm": 1.0299178111567786, + "learning_rate": 3.61691485375638e-06, + "loss": 0.8373, + "step": 8139 + }, + { + "epoch": 0.7288600369354749, + "grad_norm": 1.018567088123488, + "learning_rate": 3.61468253619312e-06, + "loss": 0.8778, + "step": 8140 + }, + { + "epoch": 0.7289495774805529, + "grad_norm": 1.0796847496302113, + "learning_rate": 3.612450755741962e-06, + "loss": 0.8083, + "step": 8141 + }, + { + "epoch": 0.7290391180256309, + "grad_norm": 0.8703934020805227, + "learning_rate": 3.6102195125906257e-06, + "loss": 0.8146, + "step": 8142 + }, + { + "epoch": 0.7291286585707091, + "grad_norm": 1.0162685599689851, + "learning_rate": 3.6079888069268034e-06, + "loss": 0.8821, + "step": 8143 + }, + { + "epoch": 0.7292181991157871, + "grad_norm": 0.9106763349275075, + "learning_rate": 3.6057586389381326e-06, + "loss": 0.7899, + "step": 8144 + }, + { + "epoch": 0.7293077396608652, + "grad_norm": 0.9198185770642722, + "learning_rate": 3.6035290088122043e-06, + "loss": 0.8742, + "step": 8145 + }, + { + "epoch": 0.7293972802059433, + "grad_norm": 0.9760022955830061, + "learning_rate": 3.6012999167365746e-06, + "loss": 0.8226, + "step": 8146 + }, + { + "epoch": 0.7294868207510213, + "grad_norm": 0.9515393113527117, + "learning_rate": 3.599071362898748e-06, + "loss": 0.8136, + "step": 8147 + }, + { + "epoch": 0.7295763612960994, + "grad_norm": 0.9762557578995822, + "learning_rate": 3.5968433474861777e-06, + "loss": 0.8362, + "step": 8148 + }, + { + "epoch": 0.7296659018411774, + "grad_norm": 0.9915788824158718, + "learning_rate": 3.5946158706862776e-06, + "loss": 0.7976, + "step": 8149 + }, + { + "epoch": 0.7297554423862556, + "grad_norm": 1.0579424716388717, + "learning_rate": 3.592388932686417e-06, + "loss": 0.768, + "step": 8150 + }, + { + "epoch": 0.7298449829313336, + "grad_norm": 0.9470715447523234, + "learning_rate": 3.5901625336739167e-06, + "loss": 0.7374, + "step": 8151 + }, + { + "epoch": 0.7299345234764116, + "grad_norm": 0.9238397973121099, + "learning_rate": 3.587936673836062e-06, + "loss": 0.8296, + "step": 8152 + }, + { + "epoch": 0.7300240640214898, + "grad_norm": 0.9939585721757632, + "learning_rate": 3.585711353360076e-06, + "loss": 0.7991, + "step": 8153 + }, + { + "epoch": 0.7301136045665678, + "grad_norm": 0.9569908555159269, + "learning_rate": 3.583486572433149e-06, + "loss": 0.8115, + "step": 8154 + }, + { + "epoch": 0.7302031451116459, + "grad_norm": 0.8713856542147157, + "learning_rate": 3.5812623312424223e-06, + "loss": 0.8193, + "step": 8155 + }, + { + "epoch": 0.7302926856567239, + "grad_norm": 0.8595706673677564, + "learning_rate": 3.57903862997499e-06, + "loss": 0.7501, + "step": 8156 + }, + { + "epoch": 0.730382226201802, + "grad_norm": 0.9593305369643707, + "learning_rate": 3.5768154688179056e-06, + "loss": 0.8195, + "step": 8157 + }, + { + "epoch": 0.7304717667468801, + "grad_norm": 0.9067085189796982, + "learning_rate": 3.5745928479581726e-06, + "loss": 0.8047, + "step": 8158 + }, + { + "epoch": 0.7305613072919581, + "grad_norm": 0.9318275857191267, + "learning_rate": 3.57237076758275e-06, + "loss": 0.8187, + "step": 8159 + }, + { + "epoch": 0.7306508478370362, + "grad_norm": 0.8903758729513356, + "learning_rate": 3.5701492278785543e-06, + "loss": 0.8344, + "step": 8160 + }, + { + "epoch": 0.7307403883821143, + "grad_norm": 0.956221432404543, + "learning_rate": 3.567928229032451e-06, + "loss": 0.8488, + "step": 8161 + }, + { + "epoch": 0.7308299289271923, + "grad_norm": 0.9263486732008133, + "learning_rate": 3.565707771231265e-06, + "loss": 0.7958, + "step": 8162 + }, + { + "epoch": 0.7309194694722704, + "grad_norm": 0.9723045277236428, + "learning_rate": 3.5634878546617746e-06, + "loss": 0.7907, + "step": 8163 + }, + { + "epoch": 0.7310090100173485, + "grad_norm": 0.9952755754990151, + "learning_rate": 3.561268479510711e-06, + "loss": 0.8065, + "step": 8164 + }, + { + "epoch": 0.7310985505624266, + "grad_norm": 0.9237053099001223, + "learning_rate": 3.5590496459647605e-06, + "loss": 0.803, + "step": 8165 + }, + { + "epoch": 0.7311880911075046, + "grad_norm": 0.9788055402294681, + "learning_rate": 3.5568313542105648e-06, + "loss": 0.8774, + "step": 8166 + }, + { + "epoch": 0.7312776316525826, + "grad_norm": 0.9583853180914002, + "learning_rate": 3.554613604434719e-06, + "loss": 0.8117, + "step": 8167 + }, + { + "epoch": 0.7313671721976608, + "grad_norm": 0.975711563757069, + "learning_rate": 3.552396396823774e-06, + "loss": 0.806, + "step": 8168 + }, + { + "epoch": 0.7314567127427388, + "grad_norm": 1.0225837677503467, + "learning_rate": 3.550179731564233e-06, + "loss": 0.852, + "step": 8169 + }, + { + "epoch": 0.7315462532878169, + "grad_norm": 0.9560903169115398, + "learning_rate": 3.547963608842554e-06, + "loss": 0.8125, + "step": 8170 + }, + { + "epoch": 0.731635793832895, + "grad_norm": 0.9767869818696021, + "learning_rate": 3.5457480288451516e-06, + "loss": 0.8126, + "step": 8171 + }, + { + "epoch": 0.731725334377973, + "grad_norm": 1.1207696260589222, + "learning_rate": 3.5435329917583926e-06, + "loss": 0.8212, + "step": 8172 + }, + { + "epoch": 0.7318148749230511, + "grad_norm": 1.1384089660751477, + "learning_rate": 3.541318497768599e-06, + "loss": 0.7952, + "step": 8173 + }, + { + "epoch": 0.7319044154681291, + "grad_norm": 0.9187041238646247, + "learning_rate": 3.5391045470620454e-06, + "loss": 0.7865, + "step": 8174 + }, + { + "epoch": 0.7319939560132073, + "grad_norm": 0.9678929992019771, + "learning_rate": 3.536891139824964e-06, + "loss": 0.8374, + "step": 8175 + }, + { + "epoch": 0.7320834965582853, + "grad_norm": 0.9958138999542374, + "learning_rate": 3.5346782762435383e-06, + "loss": 0.8149, + "step": 8176 + }, + { + "epoch": 0.7321730371033633, + "grad_norm": 0.9293242013789866, + "learning_rate": 3.5324659565039078e-06, + "loss": 0.8544, + "step": 8177 + }, + { + "epoch": 0.7322625776484414, + "grad_norm": 0.9155204742731905, + "learning_rate": 3.5302541807921644e-06, + "loss": 0.7882, + "step": 8178 + }, + { + "epoch": 0.7323521181935195, + "grad_norm": 1.043025098766824, + "learning_rate": 3.5280429492943602e-06, + "loss": 0.8203, + "step": 8179 + }, + { + "epoch": 0.7324416587385976, + "grad_norm": 0.8430319324190177, + "learning_rate": 3.525832262196486e-06, + "loss": 0.7749, + "step": 8180 + }, + { + "epoch": 0.7325311992836756, + "grad_norm": 1.0473199493498606, + "learning_rate": 3.523622119684509e-06, + "loss": 0.7535, + "step": 8181 + }, + { + "epoch": 0.7326207398287538, + "grad_norm": 1.0438194644799894, + "learning_rate": 3.5214125219443328e-06, + "loss": 0.8316, + "step": 8182 + }, + { + "epoch": 0.7327102803738318, + "grad_norm": 0.9940286324236198, + "learning_rate": 3.5192034691618247e-06, + "loss": 0.7927, + "step": 8183 + }, + { + "epoch": 0.7327998209189098, + "grad_norm": 1.0244578356254466, + "learning_rate": 3.5169949615228016e-06, + "loss": 0.7781, + "step": 8184 + }, + { + "epoch": 0.7328893614639879, + "grad_norm": 0.9664108261905939, + "learning_rate": 3.514786999213039e-06, + "loss": 0.8569, + "step": 8185 + }, + { + "epoch": 0.732978902009066, + "grad_norm": 0.903907094128431, + "learning_rate": 3.512579582418254e-06, + "loss": 0.7914, + "step": 8186 + }, + { + "epoch": 0.733068442554144, + "grad_norm": 1.0154010232820232, + "learning_rate": 3.510372711324138e-06, + "loss": 0.8677, + "step": 8187 + }, + { + "epoch": 0.7331579830992221, + "grad_norm": 1.1255327513168671, + "learning_rate": 3.5081663861163217e-06, + "loss": 0.8379, + "step": 8188 + }, + { + "epoch": 0.7332475236443002, + "grad_norm": 0.958109867809121, + "learning_rate": 3.5059606069803932e-06, + "loss": 0.8045, + "step": 8189 + }, + { + "epoch": 0.7333370641893783, + "grad_norm": 1.1612352560884336, + "learning_rate": 3.5037553741019005e-06, + "loss": 0.7996, + "step": 8190 + }, + { + "epoch": 0.7334266047344563, + "grad_norm": 1.1031352294145034, + "learning_rate": 3.501550687666333e-06, + "loss": 0.7995, + "step": 8191 + }, + { + "epoch": 0.7335161452795343, + "grad_norm": 0.9585411595654155, + "learning_rate": 3.4993465478591447e-06, + "loss": 0.7996, + "step": 8192 + }, + { + "epoch": 0.7336056858246125, + "grad_norm": 0.9563541893254343, + "learning_rate": 3.4971429548657377e-06, + "loss": 0.8341, + "step": 8193 + }, + { + "epoch": 0.7336952263696905, + "grad_norm": 0.8964672147630822, + "learning_rate": 3.4949399088714776e-06, + "loss": 0.8141, + "step": 8194 + }, + { + "epoch": 0.7337847669147686, + "grad_norm": 1.2767614375930394, + "learning_rate": 3.492737410061675e-06, + "loss": 0.7792, + "step": 8195 + }, + { + "epoch": 0.7338743074598466, + "grad_norm": 0.9594438537396436, + "learning_rate": 3.490535458621599e-06, + "loss": 0.8206, + "step": 8196 + }, + { + "epoch": 0.7339638480049248, + "grad_norm": 1.0504216911660342, + "learning_rate": 3.488334054736464e-06, + "loss": 0.7863, + "step": 8197 + }, + { + "epoch": 0.7340533885500028, + "grad_norm": 1.052226561582015, + "learning_rate": 3.4861331985914504e-06, + "loss": 0.7882, + "step": 8198 + }, + { + "epoch": 0.7341429290950808, + "grad_norm": 1.0533131509887879, + "learning_rate": 3.483932890371681e-06, + "loss": 0.7675, + "step": 8199 + }, + { + "epoch": 0.734232469640159, + "grad_norm": 0.9560068421951312, + "learning_rate": 3.481733130262246e-06, + "loss": 0.8335, + "step": 8200 + }, + { + "epoch": 0.734322010185237, + "grad_norm": 0.8713721730947953, + "learning_rate": 3.4795339184481824e-06, + "loss": 0.812, + "step": 8201 + }, + { + "epoch": 0.734411550730315, + "grad_norm": 1.0522418663993582, + "learning_rate": 3.4773352551144746e-06, + "loss": 0.8525, + "step": 8202 + }, + { + "epoch": 0.7345010912753931, + "grad_norm": 1.4915087502357198, + "learning_rate": 3.4751371404460688e-06, + "loss": 0.8156, + "step": 8203 + }, + { + "epoch": 0.7345906318204712, + "grad_norm": 1.0304608190093065, + "learning_rate": 3.472939574627865e-06, + "loss": 0.7916, + "step": 8204 + }, + { + "epoch": 0.7346801723655493, + "grad_norm": 0.9986926282138018, + "learning_rate": 3.4707425578447106e-06, + "loss": 0.8014, + "step": 8205 + }, + { + "epoch": 0.7347697129106273, + "grad_norm": 1.0481875015911823, + "learning_rate": 3.4685460902814183e-06, + "loss": 0.822, + "step": 8206 + }, + { + "epoch": 0.7348592534557055, + "grad_norm": 0.880734983485274, + "learning_rate": 3.4663501721227487e-06, + "loss": 0.7807, + "step": 8207 + }, + { + "epoch": 0.7349487940007835, + "grad_norm": 0.9243619858786883, + "learning_rate": 3.464154803553408e-06, + "loss": 0.8437, + "step": 8208 + }, + { + "epoch": 0.7350383345458615, + "grad_norm": 0.9124630219284329, + "learning_rate": 3.4619599847580675e-06, + "loss": 0.8485, + "step": 8209 + }, + { + "epoch": 0.7351278750909396, + "grad_norm": 1.084160882421561, + "learning_rate": 3.459765715921346e-06, + "loss": 0.7848, + "step": 8210 + }, + { + "epoch": 0.7352174156360177, + "grad_norm": 0.870437785952094, + "learning_rate": 3.4575719972278177e-06, + "loss": 0.7736, + "step": 8211 + }, + { + "epoch": 0.7353069561810958, + "grad_norm": 0.9367461683382013, + "learning_rate": 3.4553788288620193e-06, + "loss": 0.805, + "step": 8212 + }, + { + "epoch": 0.7353964967261738, + "grad_norm": 1.0280746350918715, + "learning_rate": 3.4531862110084236e-06, + "loss": 0.8273, + "step": 8213 + }, + { + "epoch": 0.7354860372712518, + "grad_norm": 0.9744816678769256, + "learning_rate": 3.4509941438514707e-06, + "loss": 0.7713, + "step": 8214 + }, + { + "epoch": 0.73557557781633, + "grad_norm": 1.047145189395263, + "learning_rate": 3.448802627575548e-06, + "loss": 0.8391, + "step": 8215 + }, + { + "epoch": 0.735665118361408, + "grad_norm": 1.2554424241102236, + "learning_rate": 3.446611662364999e-06, + "loss": 0.8733, + "step": 8216 + }, + { + "epoch": 0.7357546589064861, + "grad_norm": 0.9275410024035535, + "learning_rate": 3.4444212484041194e-06, + "loss": 0.8506, + "step": 8217 + }, + { + "epoch": 0.7358441994515642, + "grad_norm": 0.8703564766269303, + "learning_rate": 3.4422313858771683e-06, + "loss": 0.8021, + "step": 8218 + }, + { + "epoch": 0.7359337399966422, + "grad_norm": 0.9375397539595276, + "learning_rate": 3.4400420749683395e-06, + "loss": 0.7777, + "step": 8219 + }, + { + "epoch": 0.7360232805417203, + "grad_norm": 0.9163161668713934, + "learning_rate": 3.4378533158617954e-06, + "loss": 0.7603, + "step": 8220 + }, + { + "epoch": 0.7361128210867983, + "grad_norm": 0.9211102763528913, + "learning_rate": 3.4356651087416447e-06, + "loss": 0.7876, + "step": 8221 + }, + { + "epoch": 0.7362023616318765, + "grad_norm": 1.1034000847252037, + "learning_rate": 3.4334774537919547e-06, + "loss": 0.7386, + "step": 8222 + }, + { + "epoch": 0.7362919021769545, + "grad_norm": 0.9352820283075752, + "learning_rate": 3.4312903511967432e-06, + "loss": 0.8079, + "step": 8223 + }, + { + "epoch": 0.7363814427220325, + "grad_norm": 0.9345038174381147, + "learning_rate": 3.429103801139981e-06, + "loss": 0.7898, + "step": 8224 + }, + { + "epoch": 0.7364709832671107, + "grad_norm": 0.9202191709313174, + "learning_rate": 3.426917803805595e-06, + "loss": 0.8209, + "step": 8225 + }, + { + "epoch": 0.7365605238121887, + "grad_norm": 1.0134994917447437, + "learning_rate": 3.424732359377464e-06, + "loss": 0.8231, + "step": 8226 + }, + { + "epoch": 0.7366500643572668, + "grad_norm": 0.9265484595296583, + "learning_rate": 3.422547468039419e-06, + "loss": 0.7356, + "step": 8227 + }, + { + "epoch": 0.7367396049023448, + "grad_norm": 1.124737798633363, + "learning_rate": 3.420363129975248e-06, + "loss": 0.8426, + "step": 8228 + }, + { + "epoch": 0.736829145447423, + "grad_norm": 1.108652783298048, + "learning_rate": 3.4181793453686885e-06, + "loss": 0.8504, + "step": 8229 + }, + { + "epoch": 0.736918685992501, + "grad_norm": 0.9386557896952514, + "learning_rate": 3.4159961144034347e-06, + "loss": 0.8181, + "step": 8230 + }, + { + "epoch": 0.737008226537579, + "grad_norm": 1.0556093076937823, + "learning_rate": 3.4138134372631327e-06, + "loss": 0.7706, + "step": 8231 + }, + { + "epoch": 0.7370977670826571, + "grad_norm": 0.98189646961218, + "learning_rate": 3.4116313141313815e-06, + "loss": 0.8141, + "step": 8232 + }, + { + "epoch": 0.7371873076277352, + "grad_norm": 1.791806398031152, + "learning_rate": 3.409449745191735e-06, + "loss": 0.7728, + "step": 8233 + }, + { + "epoch": 0.7372768481728132, + "grad_norm": 0.9903009613172046, + "learning_rate": 3.4072687306276995e-06, + "loss": 0.8258, + "step": 8234 + }, + { + "epoch": 0.7373663887178913, + "grad_norm": 1.0208752947815167, + "learning_rate": 3.4050882706227338e-06, + "loss": 0.8204, + "step": 8235 + }, + { + "epoch": 0.7374559292629694, + "grad_norm": 1.1574628832313596, + "learning_rate": 3.4029083653602535e-06, + "loss": 0.8684, + "step": 8236 + }, + { + "epoch": 0.7375454698080475, + "grad_norm": 0.9469080357704458, + "learning_rate": 3.4007290150236214e-06, + "loss": 0.834, + "step": 8237 + }, + { + "epoch": 0.7376350103531255, + "grad_norm": 0.9880452783230189, + "learning_rate": 3.3985502197961605e-06, + "loss": 0.8487, + "step": 8238 + }, + { + "epoch": 0.7377245508982035, + "grad_norm": 7.943878173367735, + "learning_rate": 3.3963719798611474e-06, + "loss": 0.8229, + "step": 8239 + }, + { + "epoch": 0.7378140914432817, + "grad_norm": 0.9053647361343301, + "learning_rate": 3.394194295401796e-06, + "loss": 0.7973, + "step": 8240 + }, + { + "epoch": 0.7379036319883597, + "grad_norm": 0.9493044923646228, + "learning_rate": 3.3920171666012978e-06, + "loss": 0.8365, + "step": 8241 + }, + { + "epoch": 0.7379931725334378, + "grad_norm": 1.0500582612165192, + "learning_rate": 3.3898405936427814e-06, + "loss": 0.808, + "step": 8242 + }, + { + "epoch": 0.7380827130785159, + "grad_norm": 1.0450332562406779, + "learning_rate": 3.387664576709335e-06, + "loss": 0.8018, + "step": 8243 + }, + { + "epoch": 0.738172253623594, + "grad_norm": 0.9578536646991703, + "learning_rate": 3.3854891159839965e-06, + "loss": 0.838, + "step": 8244 + }, + { + "epoch": 0.738261794168672, + "grad_norm": 1.041649060160065, + "learning_rate": 3.383314211649761e-06, + "loss": 0.8394, + "step": 8245 + }, + { + "epoch": 0.73835133471375, + "grad_norm": 0.9661561659406418, + "learning_rate": 3.3811398638895697e-06, + "loss": 0.8153, + "step": 8246 + }, + { + "epoch": 0.7384408752588282, + "grad_norm": 0.974278763520402, + "learning_rate": 3.3789660728863204e-06, + "loss": 0.8168, + "step": 8247 + }, + { + "epoch": 0.7385304158039062, + "grad_norm": 0.9414369291356697, + "learning_rate": 3.376792838822873e-06, + "loss": 0.8015, + "step": 8248 + }, + { + "epoch": 0.7386199563489843, + "grad_norm": 0.9573638806725929, + "learning_rate": 3.3746201618820286e-06, + "loss": 0.7854, + "step": 8249 + }, + { + "epoch": 0.7387094968940623, + "grad_norm": 0.9534568312356602, + "learning_rate": 3.37244804224655e-06, + "loss": 0.7748, + "step": 8250 + }, + { + "epoch": 0.7387990374391404, + "grad_norm": 0.9728086830258825, + "learning_rate": 3.3702764800991405e-06, + "loss": 0.8363, + "step": 8251 + }, + { + "epoch": 0.7388885779842185, + "grad_norm": 0.9153508446705969, + "learning_rate": 3.3681054756224697e-06, + "loss": 0.7498, + "step": 8252 + }, + { + "epoch": 0.7389781185292965, + "grad_norm": 0.9573004423223903, + "learning_rate": 3.3659350289991523e-06, + "loss": 0.8511, + "step": 8253 + }, + { + "epoch": 0.7390676590743747, + "grad_norm": 1.01705265721414, + "learning_rate": 3.363765140411763e-06, + "loss": 0.7911, + "step": 8254 + }, + { + "epoch": 0.7391571996194527, + "grad_norm": 0.9584731284549515, + "learning_rate": 3.361595810042827e-06, + "loss": 0.7737, + "step": 8255 + }, + { + "epoch": 0.7392467401645307, + "grad_norm": 0.9995214922800939, + "learning_rate": 3.3594270380748205e-06, + "loss": 0.789, + "step": 8256 + }, + { + "epoch": 0.7393362807096088, + "grad_norm": 0.8860714813982932, + "learning_rate": 3.3572588246901694e-06, + "loss": 0.807, + "step": 8257 + }, + { + "epoch": 0.7394258212546869, + "grad_norm": 0.9595655434043556, + "learning_rate": 3.3550911700712594e-06, + "loss": 0.8274, + "step": 8258 + }, + { + "epoch": 0.739515361799765, + "grad_norm": 0.9403281503000278, + "learning_rate": 3.352924074400422e-06, + "loss": 0.8342, + "step": 8259 + }, + { + "epoch": 0.739604902344843, + "grad_norm": 1.04432666518782, + "learning_rate": 3.3507575378599555e-06, + "loss": 0.809, + "step": 8260 + }, + { + "epoch": 0.7396944428899211, + "grad_norm": 0.9242927600914393, + "learning_rate": 3.3485915606320986e-06, + "loss": 0.8265, + "step": 8261 + }, + { + "epoch": 0.7397839834349992, + "grad_norm": 1.0292663424614346, + "learning_rate": 3.346426142899043e-06, + "loss": 0.8165, + "step": 8262 + }, + { + "epoch": 0.7398735239800772, + "grad_norm": 0.9259371979760177, + "learning_rate": 3.3442612848429368e-06, + "loss": 0.7998, + "step": 8263 + }, + { + "epoch": 0.7399630645251553, + "grad_norm": 0.9071690403584297, + "learning_rate": 3.342096986645883e-06, + "loss": 0.8313, + "step": 8264 + }, + { + "epoch": 0.7400526050702334, + "grad_norm": 0.9716342819850818, + "learning_rate": 3.339933248489932e-06, + "loss": 0.7908, + "step": 8265 + }, + { + "epoch": 0.7401421456153114, + "grad_norm": 0.9131591642538947, + "learning_rate": 3.337770070557095e-06, + "loss": 0.7915, + "step": 8266 + }, + { + "epoch": 0.7402316861603895, + "grad_norm": 0.9469414609468296, + "learning_rate": 3.3356074530293325e-06, + "loss": 0.8017, + "step": 8267 + }, + { + "epoch": 0.7403212267054675, + "grad_norm": 0.9528157289533642, + "learning_rate": 3.3334453960885514e-06, + "loss": 0.8155, + "step": 8268 + }, + { + "epoch": 0.7404107672505457, + "grad_norm": 1.0458907385901584, + "learning_rate": 3.3312838999166187e-06, + "loss": 0.8195, + "step": 8269 + }, + { + "epoch": 0.7405003077956237, + "grad_norm": 1.2002683688510003, + "learning_rate": 3.3291229646953525e-06, + "loss": 0.7916, + "step": 8270 + }, + { + "epoch": 0.7405898483407017, + "grad_norm": 1.0474982791372098, + "learning_rate": 3.326962590606522e-06, + "loss": 0.7822, + "step": 8271 + }, + { + "epoch": 0.7406793888857799, + "grad_norm": 0.9641383347371756, + "learning_rate": 3.3248027778318593e-06, + "loss": 0.8016, + "step": 8272 + }, + { + "epoch": 0.7407689294308579, + "grad_norm": 0.8769795023598519, + "learning_rate": 3.322643526553031e-06, + "loss": 0.7627, + "step": 8273 + }, + { + "epoch": 0.740858469975936, + "grad_norm": 0.9256998559472221, + "learning_rate": 3.3204848369516697e-06, + "loss": 0.8313, + "step": 8274 + }, + { + "epoch": 0.740948010521014, + "grad_norm": 0.9738964176071728, + "learning_rate": 3.3183267092093563e-06, + "loss": 0.8203, + "step": 8275 + }, + { + "epoch": 0.7410375510660921, + "grad_norm": 1.013427918713693, + "learning_rate": 3.316169143507628e-06, + "loss": 0.8653, + "step": 8276 + }, + { + "epoch": 0.7411270916111702, + "grad_norm": 0.9601294184935731, + "learning_rate": 3.3140121400279702e-06, + "loss": 0.7914, + "step": 8277 + }, + { + "epoch": 0.7412166321562482, + "grad_norm": 0.9400360606224476, + "learning_rate": 3.3118556989518237e-06, + "loss": 0.8516, + "step": 8278 + }, + { + "epoch": 0.7413061727013264, + "grad_norm": 0.9453311104685804, + "learning_rate": 3.30969982046058e-06, + "loss": 0.8288, + "step": 8279 + }, + { + "epoch": 0.7413957132464044, + "grad_norm": 0.9454192638486407, + "learning_rate": 3.307544504735587e-06, + "loss": 0.7747, + "step": 8280 + }, + { + "epoch": 0.7414852537914824, + "grad_norm": 1.0597763387997936, + "learning_rate": 3.305389751958141e-06, + "loss": 0.8186, + "step": 8281 + }, + { + "epoch": 0.7415747943365605, + "grad_norm": 1.1142102209547495, + "learning_rate": 3.3032355623094936e-06, + "loss": 0.8569, + "step": 8282 + }, + { + "epoch": 0.7416643348816386, + "grad_norm": 0.9599979307735721, + "learning_rate": 3.301081935970848e-06, + "loss": 0.8257, + "step": 8283 + }, + { + "epoch": 0.7417538754267167, + "grad_norm": 1.3132447208396074, + "learning_rate": 3.2989288731233592e-06, + "loss": 0.8129, + "step": 8284 + }, + { + "epoch": 0.7418434159717947, + "grad_norm": 0.9748835229342114, + "learning_rate": 3.2967763739481383e-06, + "loss": 0.8263, + "step": 8285 + }, + { + "epoch": 0.7419329565168727, + "grad_norm": 0.9959029124218913, + "learning_rate": 3.2946244386262438e-06, + "loss": 0.7881, + "step": 8286 + }, + { + "epoch": 0.7420224970619509, + "grad_norm": 0.9290108029565046, + "learning_rate": 3.292473067338691e-06, + "loss": 0.7884, + "step": 8287 + }, + { + "epoch": 0.7421120376070289, + "grad_norm": 1.0188359216583187, + "learning_rate": 3.2903222602664464e-06, + "loss": 0.7809, + "step": 8288 + }, + { + "epoch": 0.742201578152107, + "grad_norm": 0.9196518046064179, + "learning_rate": 3.2881720175904274e-06, + "loss": 0.825, + "step": 8289 + }, + { + "epoch": 0.7422911186971851, + "grad_norm": 0.9527855218030232, + "learning_rate": 3.286022339491508e-06, + "loss": 0.7736, + "step": 8290 + }, + { + "epoch": 0.7423806592422632, + "grad_norm": 0.877622294462354, + "learning_rate": 3.283873226150509e-06, + "loss": 0.8266, + "step": 8291 + }, + { + "epoch": 0.7424701997873412, + "grad_norm": 0.9837888578373631, + "learning_rate": 3.281724677748209e-06, + "loss": 0.7498, + "step": 8292 + }, + { + "epoch": 0.7425597403324192, + "grad_norm": 0.9672394340247271, + "learning_rate": 3.279576694465336e-06, + "loss": 0.8009, + "step": 8293 + }, + { + "epoch": 0.7426492808774974, + "grad_norm": 0.9810656893013797, + "learning_rate": 3.277429276482572e-06, + "loss": 0.7649, + "step": 8294 + }, + { + "epoch": 0.7427388214225754, + "grad_norm": 0.9511414330818468, + "learning_rate": 3.2752824239805504e-06, + "loss": 0.7725, + "step": 8295 + }, + { + "epoch": 0.7428283619676534, + "grad_norm": 0.9908390841167228, + "learning_rate": 3.273136137139857e-06, + "loss": 0.8288, + "step": 8296 + }, + { + "epoch": 0.7429179025127316, + "grad_norm": 0.8869941995233392, + "learning_rate": 3.270990416141031e-06, + "loss": 0.7828, + "step": 8297 + }, + { + "epoch": 0.7430074430578096, + "grad_norm": 1.0694115423000443, + "learning_rate": 3.268845261164564e-06, + "loss": 0.8165, + "step": 8298 + }, + { + "epoch": 0.7430969836028877, + "grad_norm": 0.9404369614063781, + "learning_rate": 3.2667006723909014e-06, + "loss": 0.7785, + "step": 8299 + }, + { + "epoch": 0.7431865241479657, + "grad_norm": 1.1396583546098442, + "learning_rate": 3.2645566500004334e-06, + "loss": 0.787, + "step": 8300 + }, + { + "epoch": 0.7432760646930439, + "grad_norm": 0.9255876397539137, + "learning_rate": 3.262413194173507e-06, + "loss": 0.7973, + "step": 8301 + }, + { + "epoch": 0.7433656052381219, + "grad_norm": 1.0034392427249323, + "learning_rate": 3.2602703050904315e-06, + "loss": 0.8044, + "step": 8302 + }, + { + "epoch": 0.7434551457831999, + "grad_norm": 0.9071280343504933, + "learning_rate": 3.258127982931454e-06, + "loss": 0.7853, + "step": 8303 + }, + { + "epoch": 0.743544686328278, + "grad_norm": 0.9165223718636158, + "learning_rate": 3.255986227876782e-06, + "loss": 0.8288, + "step": 8304 + }, + { + "epoch": 0.7436342268733561, + "grad_norm": 0.9089590849353633, + "learning_rate": 3.2538450401065745e-06, + "loss": 0.7967, + "step": 8305 + }, + { + "epoch": 0.7437237674184342, + "grad_norm": 0.8895118995758451, + "learning_rate": 3.251704419800935e-06, + "loss": 0.8232, + "step": 8306 + }, + { + "epoch": 0.7438133079635122, + "grad_norm": 1.3388120775999515, + "learning_rate": 3.249564367139926e-06, + "loss": 0.7757, + "step": 8307 + }, + { + "epoch": 0.7439028485085903, + "grad_norm": 0.9431627672642698, + "learning_rate": 3.247424882303568e-06, + "loss": 0.7998, + "step": 8308 + }, + { + "epoch": 0.7439923890536684, + "grad_norm": 0.9477567715952222, + "learning_rate": 3.245285965471824e-06, + "loss": 0.795, + "step": 8309 + }, + { + "epoch": 0.7440819295987464, + "grad_norm": 1.0388825824578114, + "learning_rate": 3.243147616824617e-06, + "loss": 0.7755, + "step": 8310 + }, + { + "epoch": 0.7441714701438245, + "grad_norm": 0.9623783182561384, + "learning_rate": 3.2410098365418098e-06, + "loss": 0.8691, + "step": 8311 + }, + { + "epoch": 0.7442610106889026, + "grad_norm": 0.9858334468392603, + "learning_rate": 3.2388726248032297e-06, + "loss": 0.8367, + "step": 8312 + }, + { + "epoch": 0.7443505512339806, + "grad_norm": 1.0151182194361599, + "learning_rate": 3.236735981788649e-06, + "loss": 0.8263, + "step": 8313 + }, + { + "epoch": 0.7444400917790587, + "grad_norm": 0.9238849114024604, + "learning_rate": 3.2345999076778e-06, + "loss": 0.7988, + "step": 8314 + }, + { + "epoch": 0.7445296323241368, + "grad_norm": 1.289704456511458, + "learning_rate": 3.2324644026503614e-06, + "loss": 0.8274, + "step": 8315 + }, + { + "epoch": 0.7446191728692149, + "grad_norm": 0.9765533074547375, + "learning_rate": 3.2303294668859674e-06, + "loss": 0.8381, + "step": 8316 + }, + { + "epoch": 0.7447087134142929, + "grad_norm": 0.952563596789054, + "learning_rate": 3.2281951005641954e-06, + "loss": 0.8342, + "step": 8317 + }, + { + "epoch": 0.7447982539593709, + "grad_norm": 0.9178244778747817, + "learning_rate": 3.2260613038645837e-06, + "loss": 0.7686, + "step": 8318 + }, + { + "epoch": 0.7448877945044491, + "grad_norm": 1.0643299747917072, + "learning_rate": 3.223928076966617e-06, + "loss": 0.8913, + "step": 8319 + }, + { + "epoch": 0.7449773350495271, + "grad_norm": 0.9637961667295508, + "learning_rate": 3.221795420049744e-06, + "loss": 0.7909, + "step": 8320 + }, + { + "epoch": 0.7450668755946052, + "grad_norm": 0.9344466150189342, + "learning_rate": 3.2196633332933535e-06, + "loss": 0.8107, + "step": 8321 + }, + { + "epoch": 0.7451564161396832, + "grad_norm": 0.9367505553082477, + "learning_rate": 3.2175318168767853e-06, + "loss": 0.7866, + "step": 8322 + }, + { + "epoch": 0.7452459566847613, + "grad_norm": 1.1725460898164488, + "learning_rate": 3.2154008709793392e-06, + "loss": 0.8304, + "step": 8323 + }, + { + "epoch": 0.7453354972298394, + "grad_norm": 1.1318478775889105, + "learning_rate": 3.213270495780264e-06, + "loss": 0.7718, + "step": 8324 + }, + { + "epoch": 0.7454250377749174, + "grad_norm": 0.9221397698631435, + "learning_rate": 3.211140691458754e-06, + "loss": 0.8466, + "step": 8325 + }, + { + "epoch": 0.7455145783199956, + "grad_norm": 0.9973973311867955, + "learning_rate": 3.20901145819397e-06, + "loss": 0.8552, + "step": 8326 + }, + { + "epoch": 0.7456041188650736, + "grad_norm": 1.0122414036798697, + "learning_rate": 3.206882796165015e-06, + "loss": 0.7386, + "step": 8327 + }, + { + "epoch": 0.7456936594101516, + "grad_norm": 0.9556754250325548, + "learning_rate": 3.20475470555094e-06, + "loss": 0.783, + "step": 8328 + }, + { + "epoch": 0.7457831999552297, + "grad_norm": 0.9425563684471793, + "learning_rate": 3.2026271865307544e-06, + "loss": 0.7687, + "step": 8329 + }, + { + "epoch": 0.7458727405003078, + "grad_norm": 0.9309863280223316, + "learning_rate": 3.2005002392834196e-06, + "loss": 0.8104, + "step": 8330 + }, + { + "epoch": 0.7459622810453859, + "grad_norm": 1.0441749089542567, + "learning_rate": 3.1983738639878483e-06, + "loss": 0.7847, + "step": 8331 + }, + { + "epoch": 0.7460518215904639, + "grad_norm": 0.9056614491582808, + "learning_rate": 3.1962480608229017e-06, + "loss": 0.8024, + "step": 8332 + }, + { + "epoch": 0.746141362135542, + "grad_norm": 0.9073466972676839, + "learning_rate": 3.1941228299673965e-06, + "loss": 0.802, + "step": 8333 + }, + { + "epoch": 0.7462309026806201, + "grad_norm": 0.9784283026300207, + "learning_rate": 3.1919981716001016e-06, + "loss": 0.8014, + "step": 8334 + }, + { + "epoch": 0.7463204432256981, + "grad_norm": 0.9926652964775603, + "learning_rate": 3.1898740858997346e-06, + "loss": 0.8004, + "step": 8335 + }, + { + "epoch": 0.7464099837707762, + "grad_norm": 1.054792116854774, + "learning_rate": 3.1877505730449677e-06, + "loss": 0.8271, + "step": 8336 + }, + { + "epoch": 0.7464995243158543, + "grad_norm": 0.8924070783798097, + "learning_rate": 3.185627633214424e-06, + "loss": 0.7897, + "step": 8337 + }, + { + "epoch": 0.7465890648609323, + "grad_norm": 1.0089858966306902, + "learning_rate": 3.1835052665866774e-06, + "loss": 0.7608, + "step": 8338 + }, + { + "epoch": 0.7466786054060104, + "grad_norm": 1.0251058748060222, + "learning_rate": 3.181383473340254e-06, + "loss": 0.7893, + "step": 8339 + }, + { + "epoch": 0.7467681459510884, + "grad_norm": 0.9161314403257049, + "learning_rate": 3.1792622536536333e-06, + "loss": 0.817, + "step": 8340 + }, + { + "epoch": 0.7468576864961666, + "grad_norm": 1.0804600589225808, + "learning_rate": 3.1771416077052454e-06, + "loss": 0.8287, + "step": 8341 + }, + { + "epoch": 0.7469472270412446, + "grad_norm": 1.0656056986648266, + "learning_rate": 3.1750215356734716e-06, + "loss": 0.8455, + "step": 8342 + }, + { + "epoch": 0.7470367675863226, + "grad_norm": 0.9757441302350184, + "learning_rate": 3.172902037736646e-06, + "loss": 0.7786, + "step": 8343 + }, + { + "epoch": 0.7471263081314008, + "grad_norm": 1.143715192036921, + "learning_rate": 3.1707831140730538e-06, + "loss": 0.8079, + "step": 8344 + }, + { + "epoch": 0.7472158486764788, + "grad_norm": 0.8733022446612078, + "learning_rate": 3.16866476486093e-06, + "loss": 0.7849, + "step": 8345 + }, + { + "epoch": 0.7473053892215569, + "grad_norm": 1.0435459056011203, + "learning_rate": 3.1665469902784664e-06, + "loss": 0.8446, + "step": 8346 + }, + { + "epoch": 0.7473949297666349, + "grad_norm": 0.9662162117237109, + "learning_rate": 3.1644297905038012e-06, + "loss": 0.8088, + "step": 8347 + }, + { + "epoch": 0.7474844703117131, + "grad_norm": 0.977194786880148, + "learning_rate": 3.1623131657150275e-06, + "loss": 0.8111, + "step": 8348 + }, + { + "epoch": 0.7475740108567911, + "grad_norm": 0.9072252917028317, + "learning_rate": 3.160197116090188e-06, + "loss": 0.7743, + "step": 8349 + }, + { + "epoch": 0.7476635514018691, + "grad_norm": 0.9288365160415224, + "learning_rate": 3.158081641807278e-06, + "loss": 0.7983, + "step": 8350 + }, + { + "epoch": 0.7477530919469473, + "grad_norm": 1.0802897151028696, + "learning_rate": 3.155966743044244e-06, + "loss": 0.8651, + "step": 8351 + }, + { + "epoch": 0.7478426324920253, + "grad_norm": 1.1862089531882507, + "learning_rate": 3.1538524199789853e-06, + "loss": 0.8152, + "step": 8352 + }, + { + "epoch": 0.7479321730371034, + "grad_norm": 1.3582774338340178, + "learning_rate": 3.1517386727893516e-06, + "loss": 0.8241, + "step": 8353 + }, + { + "epoch": 0.7480217135821814, + "grad_norm": 0.8494561354719177, + "learning_rate": 3.1496255016531483e-06, + "loss": 0.7855, + "step": 8354 + }, + { + "epoch": 0.7481112541272595, + "grad_norm": 0.9490660304926756, + "learning_rate": 3.147512906748117e-06, + "loss": 0.765, + "step": 8355 + }, + { + "epoch": 0.7482007946723376, + "grad_norm": 1.1648714895839236, + "learning_rate": 3.145400888251974e-06, + "loss": 0.8246, + "step": 8356 + }, + { + "epoch": 0.7482903352174156, + "grad_norm": 0.9618483499329786, + "learning_rate": 3.1432894463423704e-06, + "loss": 0.7783, + "step": 8357 + }, + { + "epoch": 0.7483798757624937, + "grad_norm": 0.9957417654626594, + "learning_rate": 3.141178581196914e-06, + "loss": 0.8149, + "step": 8358 + }, + { + "epoch": 0.7484694163075718, + "grad_norm": 0.9365264971830646, + "learning_rate": 3.139068292993168e-06, + "loss": 0.8468, + "step": 8359 + }, + { + "epoch": 0.7485589568526498, + "grad_norm": 1.0186652536239151, + "learning_rate": 3.1369585819086366e-06, + "loss": 0.7706, + "step": 8360 + }, + { + "epoch": 0.7486484973977279, + "grad_norm": 1.0573329532095415, + "learning_rate": 3.1348494481207812e-06, + "loss": 0.8164, + "step": 8361 + }, + { + "epoch": 0.748738037942806, + "grad_norm": 0.8885511023560523, + "learning_rate": 3.1327408918070224e-06, + "loss": 0.7116, + "step": 8362 + }, + { + "epoch": 0.7488275784878841, + "grad_norm": 0.9595784244249952, + "learning_rate": 3.130632913144721e-06, + "loss": 0.7563, + "step": 8363 + }, + { + "epoch": 0.7489171190329621, + "grad_norm": 0.9106877528156478, + "learning_rate": 3.128525512311195e-06, + "loss": 0.7873, + "step": 8364 + }, + { + "epoch": 0.7490066595780401, + "grad_norm": 0.9477113948004295, + "learning_rate": 3.1264186894837123e-06, + "loss": 0.8328, + "step": 8365 + }, + { + "epoch": 0.7490962001231183, + "grad_norm": 0.908704787715687, + "learning_rate": 3.124312444839488e-06, + "loss": 0.744, + "step": 8366 + }, + { + "epoch": 0.7491857406681963, + "grad_norm": 0.9710452999531055, + "learning_rate": 3.122206778555691e-06, + "loss": 0.7876, + "step": 8367 + }, + { + "epoch": 0.7492752812132744, + "grad_norm": 1.255770075813098, + "learning_rate": 3.1201016908094518e-06, + "loss": 0.8078, + "step": 8368 + }, + { + "epoch": 0.7493648217583525, + "grad_norm": 1.0848826269333336, + "learning_rate": 3.1179971817778374e-06, + "loss": 0.8222, + "step": 8369 + }, + { + "epoch": 0.7494543623034305, + "grad_norm": 1.0097975940198562, + "learning_rate": 3.115893251637877e-06, + "loss": 0.8263, + "step": 8370 + }, + { + "epoch": 0.7495439028485086, + "grad_norm": 0.9733497416007205, + "learning_rate": 3.1137899005665405e-06, + "loss": 0.8324, + "step": 8371 + }, + { + "epoch": 0.7496334433935866, + "grad_norm": 0.9777212017128502, + "learning_rate": 3.1116871287407567e-06, + "loss": 0.7789, + "step": 8372 + }, + { + "epoch": 0.7497229839386648, + "grad_norm": 0.9912906253252568, + "learning_rate": 3.109584936337402e-06, + "loss": 0.7699, + "step": 8373 + }, + { + "epoch": 0.7498125244837428, + "grad_norm": 0.9842793058831869, + "learning_rate": 3.1074833235333123e-06, + "loss": 0.8075, + "step": 8374 + }, + { + "epoch": 0.7499020650288208, + "grad_norm": 0.9809210354261523, + "learning_rate": 3.1053822905052643e-06, + "loss": 0.8368, + "step": 8375 + }, + { + "epoch": 0.7499916055738989, + "grad_norm": 1.1409334755096951, + "learning_rate": 3.1032818374299934e-06, + "loss": 0.8064, + "step": 8376 + }, + { + "epoch": 0.750081146118977, + "grad_norm": 1.3023911315722125, + "learning_rate": 3.1011819644841766e-06, + "loss": 0.8194, + "step": 8377 + }, + { + "epoch": 0.7501706866640551, + "grad_norm": 1.0037651508068588, + "learning_rate": 3.099082671844452e-06, + "loss": 0.7731, + "step": 8378 + }, + { + "epoch": 0.7502602272091331, + "grad_norm": 1.0820138743440917, + "learning_rate": 3.096983959687403e-06, + "loss": 0.8363, + "step": 8379 + }, + { + "epoch": 0.7503497677542112, + "grad_norm": 0.9876822930021091, + "learning_rate": 3.09488582818957e-06, + "loss": 0.8233, + "step": 8380 + }, + { + "epoch": 0.7504393082992893, + "grad_norm": 0.9042398358661778, + "learning_rate": 3.092788277527443e-06, + "loss": 0.7778, + "step": 8381 + }, + { + "epoch": 0.7505288488443673, + "grad_norm": 1.0156283836289686, + "learning_rate": 3.090691307877455e-06, + "loss": 0.7972, + "step": 8382 + }, + { + "epoch": 0.7506183893894454, + "grad_norm": 1.0536718460703651, + "learning_rate": 3.088594919415998e-06, + "loss": 0.7673, + "step": 8383 + }, + { + "epoch": 0.7507079299345235, + "grad_norm": 1.2055677266840024, + "learning_rate": 3.086499112319414e-06, + "loss": 0.7942, + "step": 8384 + }, + { + "epoch": 0.7507974704796015, + "grad_norm": 1.0473403562125527, + "learning_rate": 3.084403886763997e-06, + "loss": 0.755, + "step": 8385 + }, + { + "epoch": 0.7508870110246796, + "grad_norm": 1.19806486344036, + "learning_rate": 3.082309242925985e-06, + "loss": 0.8151, + "step": 8386 + }, + { + "epoch": 0.7509765515697577, + "grad_norm": 0.914038864349572, + "learning_rate": 3.0802151809815826e-06, + "loss": 0.8028, + "step": 8387 + }, + { + "epoch": 0.7510660921148358, + "grad_norm": 0.9571492498524934, + "learning_rate": 3.0781217011069274e-06, + "loss": 0.8048, + "step": 8388 + }, + { + "epoch": 0.7511556326599138, + "grad_norm": 0.9892350382828197, + "learning_rate": 3.076028803478118e-06, + "loss": 0.8104, + "step": 8389 + }, + { + "epoch": 0.7512451732049918, + "grad_norm": 0.8525923809982836, + "learning_rate": 3.073936488271203e-06, + "loss": 0.7166, + "step": 8390 + }, + { + "epoch": 0.75133471375007, + "grad_norm": 0.9949521001063397, + "learning_rate": 3.07184475566218e-06, + "loss": 0.7811, + "step": 8391 + }, + { + "epoch": 0.751424254295148, + "grad_norm": 0.9475080141521904, + "learning_rate": 3.0697536058269993e-06, + "loss": 0.8069, + "step": 8392 + }, + { + "epoch": 0.7515137948402261, + "grad_norm": 1.0350788817504553, + "learning_rate": 3.0676630389415617e-06, + "loss": 0.7953, + "step": 8393 + }, + { + "epoch": 0.7516033353853041, + "grad_norm": 1.0370464847915886, + "learning_rate": 3.0655730551817188e-06, + "loss": 0.8295, + "step": 8394 + }, + { + "epoch": 0.7516928759303823, + "grad_norm": 1.0298302371131696, + "learning_rate": 3.063483654723274e-06, + "loss": 0.7865, + "step": 8395 + }, + { + "epoch": 0.7517824164754603, + "grad_norm": 0.901665792095309, + "learning_rate": 3.0613948377419787e-06, + "loss": 0.8001, + "step": 8396 + }, + { + "epoch": 0.7518719570205383, + "grad_norm": 0.9113509578230589, + "learning_rate": 3.05930660441354e-06, + "loss": 0.8123, + "step": 8397 + }, + { + "epoch": 0.7519614975656165, + "grad_norm": 1.0283593087312342, + "learning_rate": 3.0572189549136124e-06, + "loss": 0.7833, + "step": 8398 + }, + { + "epoch": 0.7520510381106945, + "grad_norm": 1.0107979620028282, + "learning_rate": 3.0551318894178004e-06, + "loss": 0.8597, + "step": 8399 + }, + { + "epoch": 0.7521405786557726, + "grad_norm": 0.9031408046901314, + "learning_rate": 3.0530454081016637e-06, + "loss": 0.8204, + "step": 8400 + }, + { + "epoch": 0.7522301192008506, + "grad_norm": 0.9897790600934279, + "learning_rate": 3.0509595111407086e-06, + "loss": 0.7766, + "step": 8401 + }, + { + "epoch": 0.7523196597459287, + "grad_norm": 0.9047802970964851, + "learning_rate": 3.048874198710394e-06, + "loss": 0.7555, + "step": 8402 + }, + { + "epoch": 0.7524092002910068, + "grad_norm": 1.1169892624186948, + "learning_rate": 3.0467894709861313e-06, + "loss": 0.8214, + "step": 8403 + }, + { + "epoch": 0.7524987408360848, + "grad_norm": 0.9671192783308427, + "learning_rate": 3.044705328143279e-06, + "loss": 0.8121, + "step": 8404 + }, + { + "epoch": 0.752588281381163, + "grad_norm": 1.0940444370670752, + "learning_rate": 3.0426217703571505e-06, + "loss": 0.8324, + "step": 8405 + }, + { + "epoch": 0.752677821926241, + "grad_norm": 1.000378236730116, + "learning_rate": 3.0405387978030054e-06, + "loss": 0.7435, + "step": 8406 + }, + { + "epoch": 0.752767362471319, + "grad_norm": 0.9281160540672754, + "learning_rate": 3.0384564106560586e-06, + "loss": 0.7912, + "step": 8407 + }, + { + "epoch": 0.7528569030163971, + "grad_norm": 0.9446364400380358, + "learning_rate": 3.0363746090914723e-06, + "loss": 0.8419, + "step": 8408 + }, + { + "epoch": 0.7529464435614752, + "grad_norm": 0.995166448511503, + "learning_rate": 3.034293393284362e-06, + "loss": 0.83, + "step": 8409 + }, + { + "epoch": 0.7530359841065533, + "grad_norm": 0.9448969415260732, + "learning_rate": 3.032212763409792e-06, + "loss": 0.7756, + "step": 8410 + }, + { + "epoch": 0.7531255246516313, + "grad_norm": 1.0395443660310903, + "learning_rate": 3.030132719642779e-06, + "loss": 0.8314, + "step": 8411 + }, + { + "epoch": 0.7532150651967093, + "grad_norm": 1.0004157133881215, + "learning_rate": 3.028053262158288e-06, + "loss": 0.8237, + "step": 8412 + }, + { + "epoch": 0.7533046057417875, + "grad_norm": 0.9262750826013264, + "learning_rate": 3.025974391131238e-06, + "loss": 0.8387, + "step": 8413 + }, + { + "epoch": 0.7533941462868655, + "grad_norm": 0.9543870966400738, + "learning_rate": 3.023896106736498e-06, + "loss": 0.8457, + "step": 8414 + }, + { + "epoch": 0.7534836868319436, + "grad_norm": 0.998653815959704, + "learning_rate": 3.021818409148879e-06, + "loss": 0.8097, + "step": 8415 + }, + { + "epoch": 0.7535732273770217, + "grad_norm": 0.9807664080726413, + "learning_rate": 3.0197412985431584e-06, + "loss": 0.7657, + "step": 8416 + }, + { + "epoch": 0.7536627679220997, + "grad_norm": 0.9939136806932819, + "learning_rate": 3.0176647750940526e-06, + "loss": 0.8155, + "step": 8417 + }, + { + "epoch": 0.7537523084671778, + "grad_norm": 1.0442352207198478, + "learning_rate": 3.0155888389762334e-06, + "loss": 0.7517, + "step": 8418 + }, + { + "epoch": 0.7538418490122558, + "grad_norm": 0.9184536765693112, + "learning_rate": 3.0135134903643204e-06, + "loss": 0.7366, + "step": 8419 + }, + { + "epoch": 0.753931389557334, + "grad_norm": 1.2751573368812699, + "learning_rate": 3.0114387294328896e-06, + "loss": 0.755, + "step": 8420 + }, + { + "epoch": 0.754020930102412, + "grad_norm": 0.922604355428223, + "learning_rate": 3.0093645563564523e-06, + "loss": 0.8097, + "step": 8421 + }, + { + "epoch": 0.75411047064749, + "grad_norm": 0.9469872345746867, + "learning_rate": 3.007290971309491e-06, + "loss": 0.795, + "step": 8422 + }, + { + "epoch": 0.7542000111925682, + "grad_norm": 0.9309059319052506, + "learning_rate": 3.0052179744664265e-06, + "loss": 0.8012, + "step": 8423 + }, + { + "epoch": 0.7542895517376462, + "grad_norm": 0.9867986761268118, + "learning_rate": 3.003145566001632e-06, + "loss": 0.7759, + "step": 8424 + }, + { + "epoch": 0.7543790922827243, + "grad_norm": 1.1042394309888715, + "learning_rate": 3.0010737460894346e-06, + "loss": 0.8355, + "step": 8425 + }, + { + "epoch": 0.7544686328278023, + "grad_norm": 0.949768977194555, + "learning_rate": 2.9990025149041035e-06, + "loss": 0.783, + "step": 8426 + }, + { + "epoch": 0.7545581733728804, + "grad_norm": 1.0032264365816737, + "learning_rate": 2.996931872619864e-06, + "loss": 0.7943, + "step": 8427 + }, + { + "epoch": 0.7546477139179585, + "grad_norm": 1.0038270446779733, + "learning_rate": 2.994861819410897e-06, + "loss": 0.8153, + "step": 8428 + }, + { + "epoch": 0.7547372544630365, + "grad_norm": 0.8706594779828497, + "learning_rate": 2.992792355451326e-06, + "loss": 0.7565, + "step": 8429 + }, + { + "epoch": 0.7548267950081146, + "grad_norm": 0.9378330973836738, + "learning_rate": 2.9907234809152306e-06, + "loss": 0.8377, + "step": 8430 + }, + { + "epoch": 0.7549163355531927, + "grad_norm": 0.9910203596675979, + "learning_rate": 2.988655195976632e-06, + "loss": 0.8116, + "step": 8431 + }, + { + "epoch": 0.7550058760982707, + "grad_norm": 0.9453265425499182, + "learning_rate": 2.9865875008095114e-06, + "loss": 0.7542, + "step": 8432 + }, + { + "epoch": 0.7550954166433488, + "grad_norm": 1.0254615842493653, + "learning_rate": 2.9845203955877913e-06, + "loss": 0.8086, + "step": 8433 + }, + { + "epoch": 0.7551849571884269, + "grad_norm": 0.9252447191795289, + "learning_rate": 2.9824538804853577e-06, + "loss": 0.8318, + "step": 8434 + }, + { + "epoch": 0.755274497733505, + "grad_norm": 0.8951620879551295, + "learning_rate": 2.980387955676035e-06, + "loss": 0.8203, + "step": 8435 + }, + { + "epoch": 0.755364038278583, + "grad_norm": 1.0639385900118499, + "learning_rate": 2.9783226213336058e-06, + "loss": 0.836, + "step": 8436 + }, + { + "epoch": 0.755453578823661, + "grad_norm": 0.9748128156033251, + "learning_rate": 2.976257877631793e-06, + "loss": 0.8872, + "step": 8437 + }, + { + "epoch": 0.7555431193687392, + "grad_norm": 1.0606488709344801, + "learning_rate": 2.9741937247442797e-06, + "loss": 0.8086, + "step": 8438 + }, + { + "epoch": 0.7556326599138172, + "grad_norm": 0.9444580818823709, + "learning_rate": 2.9721301628446954e-06, + "loss": 0.8125, + "step": 8439 + }, + { + "epoch": 0.7557222004588953, + "grad_norm": 1.0933936311538284, + "learning_rate": 2.970067192106617e-06, + "loss": 0.8006, + "step": 8440 + }, + { + "epoch": 0.7558117410039734, + "grad_norm": 1.0285499377574334, + "learning_rate": 2.968004812703583e-06, + "loss": 0.7836, + "step": 8441 + }, + { + "epoch": 0.7559012815490515, + "grad_norm": 1.0843926935492594, + "learning_rate": 2.965943024809067e-06, + "loss": 0.8278, + "step": 8442 + }, + { + "epoch": 0.7559908220941295, + "grad_norm": 0.9450764761526654, + "learning_rate": 2.963881828596502e-06, + "loss": 0.759, + "step": 8443 + }, + { + "epoch": 0.7560803626392075, + "grad_norm": 0.9966843234082728, + "learning_rate": 2.9618212242392687e-06, + "loss": 0.8432, + "step": 8444 + }, + { + "epoch": 0.7561699031842857, + "grad_norm": 0.9892037217108254, + "learning_rate": 2.9597612119106977e-06, + "loss": 0.8362, + "step": 8445 + }, + { + "epoch": 0.7562594437293637, + "grad_norm": 1.0925176311561264, + "learning_rate": 2.957701791784069e-06, + "loss": 0.7332, + "step": 8446 + }, + { + "epoch": 0.7563489842744417, + "grad_norm": 1.0633876066346057, + "learning_rate": 2.9556429640326236e-06, + "loss": 0.7839, + "step": 8447 + }, + { + "epoch": 0.7564385248195198, + "grad_norm": 0.9854212257470317, + "learning_rate": 2.953584728829533e-06, + "loss": 0.7987, + "step": 8448 + }, + { + "epoch": 0.7565280653645979, + "grad_norm": 0.9155916635040601, + "learning_rate": 2.951527086347933e-06, + "loss": 0.7909, + "step": 8449 + }, + { + "epoch": 0.756617605909676, + "grad_norm": 0.8965571066251745, + "learning_rate": 2.9494700367609054e-06, + "loss": 0.8122, + "step": 8450 + }, + { + "epoch": 0.756707146454754, + "grad_norm": 0.9888177551818268, + "learning_rate": 2.947413580241483e-06, + "loss": 0.7871, + "step": 8451 + }, + { + "epoch": 0.7567966869998322, + "grad_norm": 0.9124739663774152, + "learning_rate": 2.9453577169626467e-06, + "loss": 0.8412, + "step": 8452 + }, + { + "epoch": 0.7568862275449102, + "grad_norm": 0.9745502663343589, + "learning_rate": 2.9433024470973316e-06, + "loss": 0.7841, + "step": 8453 + }, + { + "epoch": 0.7569757680899882, + "grad_norm": 1.061356773543484, + "learning_rate": 2.9412477708184182e-06, + "loss": 0.864, + "step": 8454 + }, + { + "epoch": 0.7570653086350663, + "grad_norm": 1.0667769891271757, + "learning_rate": 2.9391936882987415e-06, + "loss": 0.8043, + "step": 8455 + }, + { + "epoch": 0.7571548491801444, + "grad_norm": 1.075565501366885, + "learning_rate": 2.9371401997110817e-06, + "loss": 0.7653, + "step": 8456 + }, + { + "epoch": 0.7572443897252225, + "grad_norm": 1.0313659440218141, + "learning_rate": 2.9350873052281713e-06, + "loss": 0.8536, + "step": 8457 + }, + { + "epoch": 0.7573339302703005, + "grad_norm": 1.007847630917006, + "learning_rate": 2.933035005022696e-06, + "loss": 0.8135, + "step": 8458 + }, + { + "epoch": 0.7574234708153786, + "grad_norm": 0.9265063600269383, + "learning_rate": 2.930983299267286e-06, + "loss": 0.8207, + "step": 8459 + }, + { + "epoch": 0.7575130113604567, + "grad_norm": 0.9868171272970366, + "learning_rate": 2.9289321881345257e-06, + "loss": 0.7892, + "step": 8460 + }, + { + "epoch": 0.7576025519055347, + "grad_norm": 0.9485422584043367, + "learning_rate": 2.9268816717969475e-06, + "loss": 0.8266, + "step": 8461 + }, + { + "epoch": 0.7576920924506128, + "grad_norm": 1.0525898326478405, + "learning_rate": 2.924831750427033e-06, + "loss": 0.8465, + "step": 8462 + }, + { + "epoch": 0.7577816329956909, + "grad_norm": 0.9486414196052384, + "learning_rate": 2.922782424197216e-06, + "loss": 0.8417, + "step": 8463 + }, + { + "epoch": 0.7578711735407689, + "grad_norm": 0.8798180519380967, + "learning_rate": 2.920733693279879e-06, + "loss": 0.8156, + "step": 8464 + }, + { + "epoch": 0.757960714085847, + "grad_norm": 1.056914318111195, + "learning_rate": 2.9186855578473537e-06, + "loss": 0.7809, + "step": 8465 + }, + { + "epoch": 0.758050254630925, + "grad_norm": 0.8849132676657065, + "learning_rate": 2.9166380180719243e-06, + "loss": 0.7481, + "step": 8466 + }, + { + "epoch": 0.7581397951760032, + "grad_norm": 1.0730683733670445, + "learning_rate": 2.914591074125822e-06, + "loss": 0.82, + "step": 8467 + }, + { + "epoch": 0.7582293357210812, + "grad_norm": 0.9620797464507241, + "learning_rate": 2.9125447261812302e-06, + "loss": 0.8565, + "step": 8468 + }, + { + "epoch": 0.7583188762661592, + "grad_norm": 0.9857609816079624, + "learning_rate": 2.9104989744102784e-06, + "loss": 0.8337, + "step": 8469 + }, + { + "epoch": 0.7584084168112374, + "grad_norm": 1.0004489367076872, + "learning_rate": 2.9084538189850508e-06, + "loss": 0.8004, + "step": 8470 + }, + { + "epoch": 0.7584979573563154, + "grad_norm": 1.0499643798689031, + "learning_rate": 2.9064092600775797e-06, + "loss": 0.836, + "step": 8471 + }, + { + "epoch": 0.7585874979013935, + "grad_norm": 0.8951616811749844, + "learning_rate": 2.9043652978598446e-06, + "loss": 0.7894, + "step": 8472 + }, + { + "epoch": 0.7586770384464715, + "grad_norm": 1.1106370355419521, + "learning_rate": 2.902321932503779e-06, + "loss": 0.7958, + "step": 8473 + }, + { + "epoch": 0.7587665789915496, + "grad_norm": 1.0214101881203135, + "learning_rate": 2.9002791641812657e-06, + "loss": 0.7891, + "step": 8474 + }, + { + "epoch": 0.7588561195366277, + "grad_norm": 0.9800844037363966, + "learning_rate": 2.8982369930641275e-06, + "loss": 0.8227, + "step": 8475 + }, + { + "epoch": 0.7589456600817057, + "grad_norm": 0.8756657185287371, + "learning_rate": 2.896195419324154e-06, + "loss": 0.8011, + "step": 8476 + }, + { + "epoch": 0.7590352006267839, + "grad_norm": 0.9430827458942261, + "learning_rate": 2.8941544431330716e-06, + "loss": 0.8252, + "step": 8477 + }, + { + "epoch": 0.7591247411718619, + "grad_norm": 1.0000061697920135, + "learning_rate": 2.8921140646625623e-06, + "loss": 0.7649, + "step": 8478 + }, + { + "epoch": 0.7592142817169399, + "grad_norm": 1.0134399891363568, + "learning_rate": 2.8900742840842556e-06, + "loss": 0.7902, + "step": 8479 + }, + { + "epoch": 0.759303822262018, + "grad_norm": 0.9825489454156966, + "learning_rate": 2.8880351015697337e-06, + "loss": 0.7316, + "step": 8480 + }, + { + "epoch": 0.7593933628070961, + "grad_norm": 0.9981363148845781, + "learning_rate": 2.885996517290517e-06, + "loss": 0.8486, + "step": 8481 + }, + { + "epoch": 0.7594829033521742, + "grad_norm": 1.0997368388530167, + "learning_rate": 2.8839585314180953e-06, + "loss": 0.8207, + "step": 8482 + }, + { + "epoch": 0.7595724438972522, + "grad_norm": 0.9021681120950972, + "learning_rate": 2.8819211441238916e-06, + "loss": 0.7708, + "step": 8483 + }, + { + "epoch": 0.7596619844423302, + "grad_norm": 0.976818004156447, + "learning_rate": 2.8798843555792857e-06, + "loss": 0.8126, + "step": 8484 + }, + { + "epoch": 0.7597515249874084, + "grad_norm": 1.0398684251879042, + "learning_rate": 2.877848165955608e-06, + "loss": 0.7914, + "step": 8485 + }, + { + "epoch": 0.7598410655324864, + "grad_norm": 0.987795395646323, + "learning_rate": 2.8758125754241306e-06, + "loss": 0.801, + "step": 8486 + }, + { + "epoch": 0.7599306060775645, + "grad_norm": 0.9012149443854951, + "learning_rate": 2.8737775841560844e-06, + "loss": 0.841, + "step": 8487 + }, + { + "epoch": 0.7600201466226426, + "grad_norm": 0.9493776186737061, + "learning_rate": 2.8717431923226424e-06, + "loss": 0.7544, + "step": 8488 + }, + { + "epoch": 0.7601096871677206, + "grad_norm": 1.0592989727412336, + "learning_rate": 2.8697094000949376e-06, + "loss": 0.8129, + "step": 8489 + }, + { + "epoch": 0.7601992277127987, + "grad_norm": 1.0430297480155186, + "learning_rate": 2.8676762076440414e-06, + "loss": 0.8331, + "step": 8490 + }, + { + "epoch": 0.7602887682578767, + "grad_norm": 0.9673249354304414, + "learning_rate": 2.865643615140985e-06, + "loss": 0.8501, + "step": 8491 + }, + { + "epoch": 0.7603783088029549, + "grad_norm": 0.9106925941006304, + "learning_rate": 2.8636116227567346e-06, + "loss": 0.8095, + "step": 8492 + }, + { + "epoch": 0.7604678493480329, + "grad_norm": 0.9417541724704757, + "learning_rate": 2.8615802306622196e-06, + "loss": 0.7601, + "step": 8493 + }, + { + "epoch": 0.760557389893111, + "grad_norm": 1.0114451636520094, + "learning_rate": 2.8595494390283106e-06, + "loss": 0.8226, + "step": 8494 + }, + { + "epoch": 0.7606469304381891, + "grad_norm": 1.0133891626469809, + "learning_rate": 2.857519248025837e-06, + "loss": 0.7733, + "step": 8495 + }, + { + "epoch": 0.7607364709832671, + "grad_norm": 1.064258340458245, + "learning_rate": 2.855489657825573e-06, + "loss": 0.8499, + "step": 8496 + }, + { + "epoch": 0.7608260115283452, + "grad_norm": 1.1668892552714307, + "learning_rate": 2.8534606685982326e-06, + "loss": 0.7892, + "step": 8497 + }, + { + "epoch": 0.7609155520734232, + "grad_norm": 0.9722154078220108, + "learning_rate": 2.8514322805144934e-06, + "loss": 0.8226, + "step": 8498 + }, + { + "epoch": 0.7610050926185014, + "grad_norm": 1.086653490234758, + "learning_rate": 2.849404493744975e-06, + "loss": 0.8292, + "step": 8499 + }, + { + "epoch": 0.7610946331635794, + "grad_norm": 1.055138191046296, + "learning_rate": 2.8473773084602463e-06, + "loss": 0.7375, + "step": 8500 + }, + { + "epoch": 0.7611841737086574, + "grad_norm": 0.88952226372476, + "learning_rate": 2.8453507248308367e-06, + "loss": 0.769, + "step": 8501 + }, + { + "epoch": 0.7612737142537355, + "grad_norm": 0.9332149827773796, + "learning_rate": 2.843324743027206e-06, + "loss": 0.7784, + "step": 8502 + }, + { + "epoch": 0.7613632547988136, + "grad_norm": 0.9916400972608397, + "learning_rate": 2.841299363219776e-06, + "loss": 0.8018, + "step": 8503 + }, + { + "epoch": 0.7614527953438917, + "grad_norm": 0.9695069068441983, + "learning_rate": 2.839274585578915e-06, + "loss": 0.8025, + "step": 8504 + }, + { + "epoch": 0.7615423358889697, + "grad_norm": 1.0313757240343981, + "learning_rate": 2.837250410274942e-06, + "loss": 0.8276, + "step": 8505 + }, + { + "epoch": 0.7616318764340478, + "grad_norm": 1.2706135518112773, + "learning_rate": 2.83522683747812e-06, + "loss": 0.8045, + "step": 8506 + }, + { + "epoch": 0.7617214169791259, + "grad_norm": 1.0372167997640347, + "learning_rate": 2.833203867358675e-06, + "loss": 0.8665, + "step": 8507 + }, + { + "epoch": 0.7618109575242039, + "grad_norm": 0.9373774118567355, + "learning_rate": 2.8311815000867628e-06, + "loss": 0.8054, + "step": 8508 + }, + { + "epoch": 0.761900498069282, + "grad_norm": 0.9770215701025963, + "learning_rate": 2.8291597358325005e-06, + "loss": 0.7938, + "step": 8509 + }, + { + "epoch": 0.7619900386143601, + "grad_norm": 1.0808950831152446, + "learning_rate": 2.8271385747659553e-06, + "loss": 0.8106, + "step": 8510 + }, + { + "epoch": 0.7620795791594381, + "grad_norm": 0.957244939947962, + "learning_rate": 2.8251180170571378e-06, + "loss": 0.7921, + "step": 8511 + }, + { + "epoch": 0.7621691197045162, + "grad_norm": 1.0522251369668427, + "learning_rate": 2.823098062876013e-06, + "loss": 0.761, + "step": 8512 + }, + { + "epoch": 0.7622586602495943, + "grad_norm": 1.030016738537877, + "learning_rate": 2.821078712392491e-06, + "loss": 0.8361, + "step": 8513 + }, + { + "epoch": 0.7623482007946724, + "grad_norm": 1.0304283408745756, + "learning_rate": 2.8190599657764338e-06, + "loss": 0.8324, + "step": 8514 + }, + { + "epoch": 0.7624377413397504, + "grad_norm": 1.126219644220213, + "learning_rate": 2.8170418231976527e-06, + "loss": 0.8628, + "step": 8515 + }, + { + "epoch": 0.7625272818848284, + "grad_norm": 0.9299680228717754, + "learning_rate": 2.8150242848259056e-06, + "loss": 0.7911, + "step": 8516 + }, + { + "epoch": 0.7626168224299066, + "grad_norm": 0.9169723825136841, + "learning_rate": 2.813007350830902e-06, + "loss": 0.8484, + "step": 8517 + }, + { + "epoch": 0.7627063629749846, + "grad_norm": 1.092752544019851, + "learning_rate": 2.810991021382299e-06, + "loss": 0.8313, + "step": 8518 + }, + { + "epoch": 0.7627959035200627, + "grad_norm": 0.8974944729752725, + "learning_rate": 2.808975296649705e-06, + "loss": 0.8121, + "step": 8519 + }, + { + "epoch": 0.7628854440651407, + "grad_norm": 0.9710999246449759, + "learning_rate": 2.8069601768026767e-06, + "loss": 0.7903, + "step": 8520 + }, + { + "epoch": 0.7629749846102188, + "grad_norm": 0.9326181821066316, + "learning_rate": 2.804945662010716e-06, + "loss": 0.768, + "step": 8521 + }, + { + "epoch": 0.7630645251552969, + "grad_norm": 0.9739257624114248, + "learning_rate": 2.802931752443282e-06, + "loss": 0.8051, + "step": 8522 + }, + { + "epoch": 0.7631540657003749, + "grad_norm": 1.024883664860179, + "learning_rate": 2.800918448269775e-06, + "loss": 0.8046, + "step": 8523 + }, + { + "epoch": 0.7632436062454531, + "grad_norm": 0.9336058310182836, + "learning_rate": 2.7989057496595486e-06, + "loss": 0.8338, + "step": 8524 + }, + { + "epoch": 0.7633331467905311, + "grad_norm": 0.9927860225759481, + "learning_rate": 2.796893656781904e-06, + "loss": 0.8195, + "step": 8525 + }, + { + "epoch": 0.7634226873356091, + "grad_norm": 0.9551141362776654, + "learning_rate": 2.7948821698060913e-06, + "loss": 0.8288, + "step": 8526 + }, + { + "epoch": 0.7635122278806872, + "grad_norm": 0.9972085425335548, + "learning_rate": 2.792871288901312e-06, + "loss": 0.8183, + "step": 8527 + }, + { + "epoch": 0.7636017684257653, + "grad_norm": 1.1372744300789777, + "learning_rate": 2.7908610142367144e-06, + "loss": 0.8439, + "step": 8528 + }, + { + "epoch": 0.7636913089708434, + "grad_norm": 0.8931759740171602, + "learning_rate": 2.7888513459813958e-06, + "loss": 0.8028, + "step": 8529 + }, + { + "epoch": 0.7637808495159214, + "grad_norm": 0.9798708303713464, + "learning_rate": 2.786842284304402e-06, + "loss": 0.8384, + "step": 8530 + }, + { + "epoch": 0.7638703900609995, + "grad_norm": 0.9291650963671254, + "learning_rate": 2.78483382937473e-06, + "loss": 0.7851, + "step": 8531 + }, + { + "epoch": 0.7639599306060776, + "grad_norm": 0.8988447956775906, + "learning_rate": 2.7828259813613256e-06, + "loss": 0.78, + "step": 8532 + }, + { + "epoch": 0.7640494711511556, + "grad_norm": 1.038150509737125, + "learning_rate": 2.78081874043308e-06, + "loss": 0.8476, + "step": 8533 + }, + { + "epoch": 0.7641390116962337, + "grad_norm": 1.012935214353084, + "learning_rate": 2.778812106758839e-06, + "loss": 0.8279, + "step": 8534 + }, + { + "epoch": 0.7642285522413118, + "grad_norm": 0.9427401280508876, + "learning_rate": 2.776806080507387e-06, + "loss": 0.7675, + "step": 8535 + }, + { + "epoch": 0.7643180927863898, + "grad_norm": 1.2935688983187228, + "learning_rate": 2.774800661847472e-06, + "loss": 0.8107, + "step": 8536 + }, + { + "epoch": 0.7644076333314679, + "grad_norm": 0.9651724826167283, + "learning_rate": 2.7727958509477802e-06, + "loss": 0.8223, + "step": 8537 + }, + { + "epoch": 0.7644971738765459, + "grad_norm": 1.0190535489483015, + "learning_rate": 2.7707916479769505e-06, + "loss": 0.8645, + "step": 8538 + }, + { + "epoch": 0.7645867144216241, + "grad_norm": 1.2364880327157546, + "learning_rate": 2.7687880531035695e-06, + "loss": 0.8928, + "step": 8539 + }, + { + "epoch": 0.7646762549667021, + "grad_norm": 0.9650447301309327, + "learning_rate": 2.766785066496176e-06, + "loss": 0.8353, + "step": 8540 + }, + { + "epoch": 0.7647657955117801, + "grad_norm": 1.1032427887851581, + "learning_rate": 2.7647826883232486e-06, + "loss": 0.8319, + "step": 8541 + }, + { + "epoch": 0.7648553360568583, + "grad_norm": 0.9794727183701555, + "learning_rate": 2.7627809187532207e-06, + "loss": 0.8145, + "step": 8542 + }, + { + "epoch": 0.7649448766019363, + "grad_norm": 1.0282006022761396, + "learning_rate": 2.7607797579544817e-06, + "loss": 0.8378, + "step": 8543 + }, + { + "epoch": 0.7650344171470144, + "grad_norm": 1.0281428883831272, + "learning_rate": 2.758779206095359e-06, + "loss": 0.7916, + "step": 8544 + }, + { + "epoch": 0.7651239576920924, + "grad_norm": 0.9233451945498561, + "learning_rate": 2.756779263344135e-06, + "loss": 0.8492, + "step": 8545 + }, + { + "epoch": 0.7652134982371706, + "grad_norm": 0.9468718500892725, + "learning_rate": 2.7547799298690327e-06, + "loss": 0.8198, + "step": 8546 + }, + { + "epoch": 0.7653030387822486, + "grad_norm": 1.0053103798748328, + "learning_rate": 2.752781205838233e-06, + "loss": 0.8293, + "step": 8547 + }, + { + "epoch": 0.7653925793273266, + "grad_norm": 1.0536730418913196, + "learning_rate": 2.7507830914198587e-06, + "loss": 0.8053, + "step": 8548 + }, + { + "epoch": 0.7654821198724048, + "grad_norm": 0.9979288096554082, + "learning_rate": 2.74878558678199e-06, + "loss": 0.8034, + "step": 8549 + }, + { + "epoch": 0.7655716604174828, + "grad_norm": 0.9112349997538397, + "learning_rate": 2.74678869209265e-06, + "loss": 0.7328, + "step": 8550 + }, + { + "epoch": 0.7656612009625609, + "grad_norm": 0.9286807378027299, + "learning_rate": 2.7447924075198106e-06, + "loss": 0.8197, + "step": 8551 + }, + { + "epoch": 0.7657507415076389, + "grad_norm": 1.0547527058165194, + "learning_rate": 2.7427967332313888e-06, + "loss": 0.84, + "step": 8552 + }, + { + "epoch": 0.765840282052717, + "grad_norm": 1.0300520442858276, + "learning_rate": 2.7408016693952566e-06, + "loss": 0.8293, + "step": 8553 + }, + { + "epoch": 0.7659298225977951, + "grad_norm": 1.0297481236913109, + "learning_rate": 2.73880721617923e-06, + "loss": 0.8173, + "step": 8554 + }, + { + "epoch": 0.7660193631428731, + "grad_norm": 1.0369250982490426, + "learning_rate": 2.7368133737510805e-06, + "loss": 0.7719, + "step": 8555 + }, + { + "epoch": 0.7661089036879511, + "grad_norm": 0.9969617654196644, + "learning_rate": 2.734820142278525e-06, + "loss": 0.7703, + "step": 8556 + }, + { + "epoch": 0.7661984442330293, + "grad_norm": 0.969076635777658, + "learning_rate": 2.73282752192922e-06, + "loss": 0.8118, + "step": 8557 + }, + { + "epoch": 0.7662879847781073, + "grad_norm": 0.9400732764710739, + "learning_rate": 2.730835512870783e-06, + "loss": 0.7868, + "step": 8558 + }, + { + "epoch": 0.7663775253231854, + "grad_norm": 0.9448544286211332, + "learning_rate": 2.7288441152707745e-06, + "loss": 0.8105, + "step": 8559 + }, + { + "epoch": 0.7664670658682635, + "grad_norm": 0.9504827667935589, + "learning_rate": 2.7268533292967026e-06, + "loss": 0.7651, + "step": 8560 + }, + { + "epoch": 0.7665566064133416, + "grad_norm": 0.9786735043913761, + "learning_rate": 2.724863155116029e-06, + "loss": 0.8043, + "step": 8561 + }, + { + "epoch": 0.7666461469584196, + "grad_norm": 0.9500121806982903, + "learning_rate": 2.7228735928961635e-06, + "loss": 0.8419, + "step": 8562 + }, + { + "epoch": 0.7667356875034976, + "grad_norm": 0.9330501277953063, + "learning_rate": 2.7208846428044535e-06, + "loss": 0.8081, + "step": 8563 + }, + { + "epoch": 0.7668252280485758, + "grad_norm": 1.0052201909769134, + "learning_rate": 2.7188963050082073e-06, + "loss": 0.8322, + "step": 8564 + }, + { + "epoch": 0.7669147685936538, + "grad_norm": 0.8694345321107568, + "learning_rate": 2.7169085796746762e-06, + "loss": 0.7741, + "step": 8565 + }, + { + "epoch": 0.7670043091387319, + "grad_norm": 1.4664512120990643, + "learning_rate": 2.71492146697106e-06, + "loss": 0.8614, + "step": 8566 + }, + { + "epoch": 0.76709384968381, + "grad_norm": 0.986184825106137, + "learning_rate": 2.7129349670645157e-06, + "loss": 0.8379, + "step": 8567 + }, + { + "epoch": 0.767183390228888, + "grad_norm": 1.000471154686253, + "learning_rate": 2.7109490801221327e-06, + "loss": 0.8277, + "step": 8568 + }, + { + "epoch": 0.7672729307739661, + "grad_norm": 0.938506133035383, + "learning_rate": 2.7089638063109602e-06, + "loss": 0.7814, + "step": 8569 + }, + { + "epoch": 0.7673624713190441, + "grad_norm": 0.9630635762015237, + "learning_rate": 2.706979145797992e-06, + "loss": 0.7754, + "step": 8570 + }, + { + "epoch": 0.7674520118641223, + "grad_norm": 0.8987277568057228, + "learning_rate": 2.704995098750174e-06, + "loss": 0.8084, + "step": 8571 + }, + { + "epoch": 0.7675415524092003, + "grad_norm": 0.9122576028411004, + "learning_rate": 2.703011665334395e-06, + "loss": 0.7934, + "step": 8572 + }, + { + "epoch": 0.7676310929542783, + "grad_norm": 1.0925721029013176, + "learning_rate": 2.701028845717496e-06, + "loss": 0.8161, + "step": 8573 + }, + { + "epoch": 0.7677206334993564, + "grad_norm": 1.242002011819233, + "learning_rate": 2.699046640066265e-06, + "loss": 0.7935, + "step": 8574 + }, + { + "epoch": 0.7678101740444345, + "grad_norm": 1.003307596054991, + "learning_rate": 2.6970650485474393e-06, + "loss": 0.8031, + "step": 8575 + }, + { + "epoch": 0.7678997145895126, + "grad_norm": 0.9841436045079488, + "learning_rate": 2.6950840713277037e-06, + "loss": 0.7751, + "step": 8576 + }, + { + "epoch": 0.7679892551345906, + "grad_norm": 0.9193788398396291, + "learning_rate": 2.693103708573692e-06, + "loss": 0.7863, + "step": 8577 + }, + { + "epoch": 0.7680787956796687, + "grad_norm": 0.9064801866426804, + "learning_rate": 2.6911239604519844e-06, + "loss": 0.7897, + "step": 8578 + }, + { + "epoch": 0.7681683362247468, + "grad_norm": 0.9564495393890579, + "learning_rate": 2.6891448271291123e-06, + "loss": 0.8131, + "step": 8579 + }, + { + "epoch": 0.7682578767698248, + "grad_norm": 0.9185102027209784, + "learning_rate": 2.687166308771554e-06, + "loss": 0.7708, + "step": 8580 + }, + { + "epoch": 0.7683474173149029, + "grad_norm": 0.9633800838468224, + "learning_rate": 2.6851884055457343e-06, + "loss": 0.7998, + "step": 8581 + }, + { + "epoch": 0.768436957859981, + "grad_norm": 0.8807658926947759, + "learning_rate": 2.68321111761803e-06, + "loss": 0.7775, + "step": 8582 + }, + { + "epoch": 0.768526498405059, + "grad_norm": 1.0827544074731394, + "learning_rate": 2.6812344451547624e-06, + "loss": 0.8483, + "step": 8583 + }, + { + "epoch": 0.7686160389501371, + "grad_norm": 0.9802224528998077, + "learning_rate": 2.6792583883222047e-06, + "loss": 0.7957, + "step": 8584 + }, + { + "epoch": 0.7687055794952152, + "grad_norm": 0.9359662322678803, + "learning_rate": 2.6772829472865735e-06, + "loss": 0.8064, + "step": 8585 + }, + { + "epoch": 0.7687951200402933, + "grad_norm": 1.0056466047699095, + "learning_rate": 2.6753081222140398e-06, + "loss": 0.7758, + "step": 8586 + }, + { + "epoch": 0.7688846605853713, + "grad_norm": 0.853240631544896, + "learning_rate": 2.6733339132707172e-06, + "loss": 0.8019, + "step": 8587 + }, + { + "epoch": 0.7689742011304493, + "grad_norm": 0.9046056721612803, + "learning_rate": 2.67136032062267e-06, + "loss": 0.7818, + "step": 8588 + }, + { + "epoch": 0.7690637416755275, + "grad_norm": 1.0591530838030743, + "learning_rate": 2.669387344435912e-06, + "loss": 0.7652, + "step": 8589 + }, + { + "epoch": 0.7691532822206055, + "grad_norm": 0.9905679236283128, + "learning_rate": 2.6674149848764006e-06, + "loss": 0.8008, + "step": 8590 + }, + { + "epoch": 0.7692428227656836, + "grad_norm": 0.8860448283298954, + "learning_rate": 2.6654432421100472e-06, + "loss": 0.7957, + "step": 8591 + }, + { + "epoch": 0.7693323633107616, + "grad_norm": 1.0735306758648655, + "learning_rate": 2.6634721163027076e-06, + "loss": 0.7717, + "step": 8592 + }, + { + "epoch": 0.7694219038558398, + "grad_norm": 1.2491509821121964, + "learning_rate": 2.661501607620185e-06, + "loss": 0.8152, + "step": 8593 + }, + { + "epoch": 0.7695114444009178, + "grad_norm": 0.9978549067224076, + "learning_rate": 2.6595317162282364e-06, + "loss": 0.7837, + "step": 8594 + }, + { + "epoch": 0.7696009849459958, + "grad_norm": 0.9619042373968957, + "learning_rate": 2.657562442292556e-06, + "loss": 0.7608, + "step": 8595 + }, + { + "epoch": 0.769690525491074, + "grad_norm": 1.0156562907666078, + "learning_rate": 2.655593785978794e-06, + "loss": 0.8023, + "step": 8596 + }, + { + "epoch": 0.769780066036152, + "grad_norm": 1.0592335041965242, + "learning_rate": 2.6536257474525517e-06, + "loss": 0.8163, + "step": 8597 + }, + { + "epoch": 0.76986960658123, + "grad_norm": 1.056145414382865, + "learning_rate": 2.651658326879373e-06, + "loss": 0.7745, + "step": 8598 + }, + { + "epoch": 0.7699591471263081, + "grad_norm": 0.9076650119450872, + "learning_rate": 2.649691524424749e-06, + "loss": 0.8355, + "step": 8599 + }, + { + "epoch": 0.7700486876713862, + "grad_norm": 0.9457089439781576, + "learning_rate": 2.6477253402541235e-06, + "loss": 0.8201, + "step": 8600 + }, + { + "epoch": 0.7701382282164643, + "grad_norm": 1.016497694013363, + "learning_rate": 2.645759774532882e-06, + "loss": 0.8064, + "step": 8601 + }, + { + "epoch": 0.7702277687615423, + "grad_norm": 0.8821943593236058, + "learning_rate": 2.643794827426359e-06, + "loss": 0.7756, + "step": 8602 + }, + { + "epoch": 0.7703173093066205, + "grad_norm": 1.0412009355697802, + "learning_rate": 2.6418304990998466e-06, + "loss": 0.7973, + "step": 8603 + }, + { + "epoch": 0.7704068498516985, + "grad_norm": 1.0756177128252604, + "learning_rate": 2.6398667897185758e-06, + "loss": 0.8292, + "step": 8604 + }, + { + "epoch": 0.7704963903967765, + "grad_norm": 1.0205422362926408, + "learning_rate": 2.6379036994477282e-06, + "loss": 0.7534, + "step": 8605 + }, + { + "epoch": 0.7705859309418546, + "grad_norm": 0.9621012562133423, + "learning_rate": 2.6359412284524266e-06, + "loss": 0.8486, + "step": 8606 + }, + { + "epoch": 0.7706754714869327, + "grad_norm": 0.9917432518805662, + "learning_rate": 2.6339793768977527e-06, + "loss": 0.8123, + "step": 8607 + }, + { + "epoch": 0.7707650120320108, + "grad_norm": 0.9275201768664162, + "learning_rate": 2.632018144948727e-06, + "loss": 0.8086, + "step": 8608 + }, + { + "epoch": 0.7708545525770888, + "grad_norm": 1.017321377763287, + "learning_rate": 2.630057532770327e-06, + "loss": 0.8096, + "step": 8609 + }, + { + "epoch": 0.7709440931221668, + "grad_norm": 1.1293951149719799, + "learning_rate": 2.628097540527471e-06, + "loss": 0.8036, + "step": 8610 + }, + { + "epoch": 0.771033633667245, + "grad_norm": 0.9229212662475096, + "learning_rate": 2.626138168385031e-06, + "loss": 0.7612, + "step": 8611 + }, + { + "epoch": 0.771123174212323, + "grad_norm": 0.951957383852106, + "learning_rate": 2.6241794165078162e-06, + "loss": 0.7888, + "step": 8612 + }, + { + "epoch": 0.771212714757401, + "grad_norm": 0.9839710966832312, + "learning_rate": 2.622221285060592e-06, + "loss": 0.7828, + "step": 8613 + }, + { + "epoch": 0.7713022553024792, + "grad_norm": 0.9169230820937256, + "learning_rate": 2.6202637742080684e-06, + "loss": 0.8064, + "step": 8614 + }, + { + "epoch": 0.7713917958475572, + "grad_norm": 0.9736040219292256, + "learning_rate": 2.618306884114912e-06, + "loss": 0.83, + "step": 8615 + }, + { + "epoch": 0.7714813363926353, + "grad_norm": 1.0769632309149675, + "learning_rate": 2.6163506149457274e-06, + "loss": 0.8611, + "step": 8616 + }, + { + "epoch": 0.7715708769377133, + "grad_norm": 0.9154192542953049, + "learning_rate": 2.614394966865066e-06, + "loss": 0.7357, + "step": 8617 + }, + { + "epoch": 0.7716604174827915, + "grad_norm": 0.8808401062705739, + "learning_rate": 2.612439940037431e-06, + "loss": 0.7555, + "step": 8618 + }, + { + "epoch": 0.7717499580278695, + "grad_norm": 0.9340499473620993, + "learning_rate": 2.6104855346272763e-06, + "loss": 0.8069, + "step": 8619 + }, + { + "epoch": 0.7718394985729475, + "grad_norm": 0.919452992391543, + "learning_rate": 2.6085317507989938e-06, + "loss": 0.8092, + "step": 8620 + }, + { + "epoch": 0.7719290391180257, + "grad_norm": 0.9815207998760314, + "learning_rate": 2.606578588716937e-06, + "loss": 0.7625, + "step": 8621 + }, + { + "epoch": 0.7720185796631037, + "grad_norm": 1.0263188570960775, + "learning_rate": 2.6046260485454e-06, + "loss": 0.7891, + "step": 8622 + }, + { + "epoch": 0.7721081202081818, + "grad_norm": 0.9985707736808533, + "learning_rate": 2.602674130448617e-06, + "loss": 0.8262, + "step": 8623 + }, + { + "epoch": 0.7721976607532598, + "grad_norm": 0.9519739733291744, + "learning_rate": 2.600722834590781e-06, + "loss": 0.812, + "step": 8624 + }, + { + "epoch": 0.7722872012983379, + "grad_norm": 1.0450559177726395, + "learning_rate": 2.5987721611360273e-06, + "loss": 0.7996, + "step": 8625 + }, + { + "epoch": 0.772376741843416, + "grad_norm": 0.8817484448659242, + "learning_rate": 2.5968221102484413e-06, + "loss": 0.7654, + "step": 8626 + }, + { + "epoch": 0.772466282388494, + "grad_norm": 1.0282925047988678, + "learning_rate": 2.5948726820920544e-06, + "loss": 0.8012, + "step": 8627 + }, + { + "epoch": 0.7725558229335721, + "grad_norm": 0.9839203186674594, + "learning_rate": 2.5929238768308474e-06, + "loss": 0.7944, + "step": 8628 + }, + { + "epoch": 0.7726453634786502, + "grad_norm": 0.9604644007233709, + "learning_rate": 2.5909756946287458e-06, + "loss": 0.7681, + "step": 8629 + }, + { + "epoch": 0.7727349040237282, + "grad_norm": 0.9623383898855488, + "learning_rate": 2.5890281356496237e-06, + "loss": 0.8399, + "step": 8630 + }, + { + "epoch": 0.7728244445688063, + "grad_norm": 1.1080714755499659, + "learning_rate": 2.5870812000573066e-06, + "loss": 0.7437, + "step": 8631 + }, + { + "epoch": 0.7729139851138844, + "grad_norm": 0.9397860484066614, + "learning_rate": 2.5851348880155612e-06, + "loss": 0.8003, + "step": 8632 + }, + { + "epoch": 0.7730035256589625, + "grad_norm": 0.8662947339045861, + "learning_rate": 2.5831891996881063e-06, + "loss": 0.7849, + "step": 8633 + }, + { + "epoch": 0.7730930662040405, + "grad_norm": 0.9343143596506978, + "learning_rate": 2.5812441352386076e-06, + "loss": 0.7767, + "step": 8634 + }, + { + "epoch": 0.7731826067491185, + "grad_norm": 1.043604919326881, + "learning_rate": 2.579299694830676e-06, + "loss": 0.8174, + "step": 8635 + }, + { + "epoch": 0.7732721472941967, + "grad_norm": 0.9293076407546806, + "learning_rate": 2.577355878627872e-06, + "loss": 0.7409, + "step": 8636 + }, + { + "epoch": 0.7733616878392747, + "grad_norm": 0.9715274564245949, + "learning_rate": 2.5754126867937033e-06, + "loss": 0.7939, + "step": 8637 + }, + { + "epoch": 0.7734512283843528, + "grad_norm": 1.0010773935681752, + "learning_rate": 2.5734701194916257e-06, + "loss": 0.8328, + "step": 8638 + }, + { + "epoch": 0.7735407689294309, + "grad_norm": 0.990816679536554, + "learning_rate": 2.5715281768850397e-06, + "loss": 0.7491, + "step": 8639 + }, + { + "epoch": 0.773630309474509, + "grad_norm": 0.9479352493736147, + "learning_rate": 2.5695868591372975e-06, + "loss": 0.841, + "step": 8640 + }, + { + "epoch": 0.773719850019587, + "grad_norm": 1.1221524788483135, + "learning_rate": 2.5676461664116946e-06, + "loss": 0.813, + "step": 8641 + }, + { + "epoch": 0.773809390564665, + "grad_norm": 0.9913798272793234, + "learning_rate": 2.5657060988714755e-06, + "loss": 0.8236, + "step": 8642 + }, + { + "epoch": 0.7738989311097432, + "grad_norm": 0.9334447308920091, + "learning_rate": 2.5637666566798347e-06, + "loss": 0.7842, + "step": 8643 + }, + { + "epoch": 0.7739884716548212, + "grad_norm": 0.9167462086416046, + "learning_rate": 2.5618278399999097e-06, + "loss": 0.7818, + "step": 8644 + }, + { + "epoch": 0.7740780121998992, + "grad_norm": 0.9553280856509895, + "learning_rate": 2.5598896489947877e-06, + "loss": 0.76, + "step": 8645 + }, + { + "epoch": 0.7741675527449773, + "grad_norm": 0.8856535569954458, + "learning_rate": 2.5579520838275027e-06, + "loss": 0.8351, + "step": 8646 + }, + { + "epoch": 0.7742570932900554, + "grad_norm": 1.044037521820496, + "learning_rate": 2.556015144661038e-06, + "loss": 0.7466, + "step": 8647 + }, + { + "epoch": 0.7743466338351335, + "grad_norm": 1.0215521099309144, + "learning_rate": 2.554078831658321e-06, + "loss": 0.7982, + "step": 8648 + }, + { + "epoch": 0.7744361743802115, + "grad_norm": 0.9898693360606619, + "learning_rate": 2.552143144982232e-06, + "loss": 0.8005, + "step": 8649 + }, + { + "epoch": 0.7745257149252897, + "grad_norm": 1.6898269850714511, + "learning_rate": 2.5502080847955857e-06, + "loss": 0.752, + "step": 8650 + }, + { + "epoch": 0.7746152554703677, + "grad_norm": 0.8779736606091741, + "learning_rate": 2.5482736512611606e-06, + "loss": 0.7768, + "step": 8651 + }, + { + "epoch": 0.7747047960154457, + "grad_norm": 1.018725861726274, + "learning_rate": 2.5463398445416744e-06, + "loss": 0.8374, + "step": 8652 + }, + { + "epoch": 0.7747943365605238, + "grad_norm": 0.8882064886574702, + "learning_rate": 2.54440666479979e-06, + "loss": 0.8264, + "step": 8653 + }, + { + "epoch": 0.7748838771056019, + "grad_norm": 0.970085593463449, + "learning_rate": 2.5424741121981243e-06, + "loss": 0.848, + "step": 8654 + }, + { + "epoch": 0.77497341765068, + "grad_norm": 1.1033980180626324, + "learning_rate": 2.5405421868992318e-06, + "loss": 0.8382, + "step": 8655 + }, + { + "epoch": 0.775062958195758, + "grad_norm": 1.1602708014260483, + "learning_rate": 2.538610889065619e-06, + "loss": 0.7939, + "step": 8656 + }, + { + "epoch": 0.7751524987408361, + "grad_norm": 0.9576070804071292, + "learning_rate": 2.536680218859747e-06, + "loss": 0.7762, + "step": 8657 + }, + { + "epoch": 0.7752420392859142, + "grad_norm": 0.9755052719125886, + "learning_rate": 2.534750176444015e-06, + "loss": 0.8112, + "step": 8658 + }, + { + "epoch": 0.7753315798309922, + "grad_norm": 0.9200417005596881, + "learning_rate": 2.532820761980771e-06, + "loss": 0.8018, + "step": 8659 + }, + { + "epoch": 0.7754211203760702, + "grad_norm": 0.9136067069660301, + "learning_rate": 2.5308919756323135e-06, + "loss": 0.7958, + "step": 8660 + }, + { + "epoch": 0.7755106609211484, + "grad_norm": 1.0342810366916786, + "learning_rate": 2.52896381756088e-06, + "loss": 0.825, + "step": 8661 + }, + { + "epoch": 0.7756002014662264, + "grad_norm": 0.9800098989806436, + "learning_rate": 2.5270362879286625e-06, + "loss": 0.8397, + "step": 8662 + }, + { + "epoch": 0.7756897420113045, + "grad_norm": 0.9277957497916605, + "learning_rate": 2.5251093868978025e-06, + "loss": 0.7876, + "step": 8663 + }, + { + "epoch": 0.7757792825563825, + "grad_norm": 0.9164352253695796, + "learning_rate": 2.523183114630382e-06, + "loss": 0.7573, + "step": 8664 + }, + { + "epoch": 0.7758688231014607, + "grad_norm": 1.0015859512173726, + "learning_rate": 2.5212574712884375e-06, + "loss": 0.8197, + "step": 8665 + }, + { + "epoch": 0.7759583636465387, + "grad_norm": 1.000380341334665, + "learning_rate": 2.5193324570339394e-06, + "loss": 0.7878, + "step": 8666 + }, + { + "epoch": 0.7760479041916167, + "grad_norm": 1.0145045593940272, + "learning_rate": 2.5174080720288185e-06, + "loss": 0.7861, + "step": 8667 + }, + { + "epoch": 0.7761374447366949, + "grad_norm": 1.0461682919502595, + "learning_rate": 2.515484316434943e-06, + "loss": 0.8145, + "step": 8668 + }, + { + "epoch": 0.7762269852817729, + "grad_norm": 1.0542460641806677, + "learning_rate": 2.513561190414141e-06, + "loss": 0.8029, + "step": 8669 + }, + { + "epoch": 0.776316525826851, + "grad_norm": 0.8988684672442186, + "learning_rate": 2.5116386941281745e-06, + "loss": 0.7902, + "step": 8670 + }, + { + "epoch": 0.776406066371929, + "grad_norm": 0.968524869194405, + "learning_rate": 2.509716827738763e-06, + "loss": 0.7804, + "step": 8671 + }, + { + "epoch": 0.7764956069170071, + "grad_norm": 0.9576889324243132, + "learning_rate": 2.507795591407559e-06, + "loss": 0.8193, + "step": 8672 + }, + { + "epoch": 0.7765851474620852, + "grad_norm": 0.9261099870586427, + "learning_rate": 2.5058749852961763e-06, + "loss": 0.7644, + "step": 8673 + }, + { + "epoch": 0.7766746880071632, + "grad_norm": 0.8266529068042214, + "learning_rate": 2.5039550095661647e-06, + "loss": 0.713, + "step": 8674 + }, + { + "epoch": 0.7767642285522414, + "grad_norm": 0.932759042317134, + "learning_rate": 2.5020356643790342e-06, + "loss": 0.8135, + "step": 8675 + }, + { + "epoch": 0.7768537690973194, + "grad_norm": 0.9924550749297483, + "learning_rate": 2.500116949896232e-06, + "loss": 0.8383, + "step": 8676 + }, + { + "epoch": 0.7769433096423974, + "grad_norm": 0.9772352184536196, + "learning_rate": 2.4981988662791503e-06, + "loss": 0.8462, + "step": 8677 + }, + { + "epoch": 0.7770328501874755, + "grad_norm": 0.838097212027536, + "learning_rate": 2.4962814136891324e-06, + "loss": 0.6846, + "step": 8678 + }, + { + "epoch": 0.7771223907325536, + "grad_norm": 0.8953152298828604, + "learning_rate": 2.4943645922874704e-06, + "loss": 0.8032, + "step": 8679 + }, + { + "epoch": 0.7772119312776317, + "grad_norm": 0.9674460783736636, + "learning_rate": 2.4924484022354003e-06, + "loss": 0.7579, + "step": 8680 + }, + { + "epoch": 0.7773014718227097, + "grad_norm": 1.0726600574331795, + "learning_rate": 2.4905328436941024e-06, + "loss": 0.8596, + "step": 8681 + }, + { + "epoch": 0.7773910123677877, + "grad_norm": 0.9409641449162625, + "learning_rate": 2.488617916824716e-06, + "loss": 0.7395, + "step": 8682 + }, + { + "epoch": 0.7774805529128659, + "grad_norm": 1.0238950124004955, + "learning_rate": 2.4867036217883113e-06, + "loss": 0.8299, + "step": 8683 + }, + { + "epoch": 0.7775700934579439, + "grad_norm": 1.0944642125293673, + "learning_rate": 2.4847899587459134e-06, + "loss": 0.7797, + "step": 8684 + }, + { + "epoch": 0.777659634003022, + "grad_norm": 1.0121175565873832, + "learning_rate": 2.4828769278584952e-06, + "loss": 0.864, + "step": 8685 + }, + { + "epoch": 0.7777491745481001, + "grad_norm": 1.019195156547706, + "learning_rate": 2.480964529286973e-06, + "loss": 0.7968, + "step": 8686 + }, + { + "epoch": 0.7778387150931781, + "grad_norm": 0.995580144602024, + "learning_rate": 2.4790527631922125e-06, + "loss": 0.7789, + "step": 8687 + }, + { + "epoch": 0.7779282556382562, + "grad_norm": 0.9295724075330994, + "learning_rate": 2.477141629735025e-06, + "loss": 0.794, + "step": 8688 + }, + { + "epoch": 0.7780177961833342, + "grad_norm": 0.9389635970758421, + "learning_rate": 2.4752311290761688e-06, + "loss": 0.842, + "step": 8689 + }, + { + "epoch": 0.7781073367284124, + "grad_norm": 0.9013828602665985, + "learning_rate": 2.473321261376349e-06, + "loss": 0.7776, + "step": 8690 + }, + { + "epoch": 0.7781968772734904, + "grad_norm": 0.9423517718232737, + "learning_rate": 2.4714120267962173e-06, + "loss": 0.7674, + "step": 8691 + }, + { + "epoch": 0.7782864178185684, + "grad_norm": 0.9082063303114358, + "learning_rate": 2.4695034254963734e-06, + "loss": 0.8213, + "step": 8692 + }, + { + "epoch": 0.7783759583636466, + "grad_norm": 1.0097603361206131, + "learning_rate": 2.4675954576373608e-06, + "loss": 0.7884, + "step": 8693 + }, + { + "epoch": 0.7784654989087246, + "grad_norm": 1.0091109306547712, + "learning_rate": 2.4656881233796725e-06, + "loss": 0.7757, + "step": 8694 + }, + { + "epoch": 0.7785550394538027, + "grad_norm": 0.9571119416811313, + "learning_rate": 2.4637814228837474e-06, + "loss": 0.8706, + "step": 8695 + }, + { + "epoch": 0.7786445799988807, + "grad_norm": 0.9738450728011351, + "learning_rate": 2.4618753563099705e-06, + "loss": 0.8174, + "step": 8696 + }, + { + "epoch": 0.7787341205439589, + "grad_norm": 0.96139900373006, + "learning_rate": 2.4599699238186747e-06, + "loss": 0.7825, + "step": 8697 + }, + { + "epoch": 0.7788236610890369, + "grad_norm": 0.9695645553768653, + "learning_rate": 2.4580651255701373e-06, + "loss": 0.7718, + "step": 8698 + }, + { + "epoch": 0.7789132016341149, + "grad_norm": 1.2431225661471146, + "learning_rate": 2.456160961724585e-06, + "loss": 0.7784, + "step": 8699 + }, + { + "epoch": 0.779002742179193, + "grad_norm": 1.1021443597540335, + "learning_rate": 2.45425743244219e-06, + "loss": 0.826, + "step": 8700 + }, + { + "epoch": 0.7790922827242711, + "grad_norm": 1.1710146063721463, + "learning_rate": 2.4523545378830693e-06, + "loss": 0.8076, + "step": 8701 + }, + { + "epoch": 0.7791818232693491, + "grad_norm": 1.174422142434489, + "learning_rate": 2.4504522782072905e-06, + "loss": 0.8443, + "step": 8702 + }, + { + "epoch": 0.7792713638144272, + "grad_norm": 0.9695273151706497, + "learning_rate": 2.4485506535748658e-06, + "loss": 0.7689, + "step": 8703 + }, + { + "epoch": 0.7793609043595053, + "grad_norm": 1.3197561015419235, + "learning_rate": 2.4466496641457483e-06, + "loss": 0.7784, + "step": 8704 + }, + { + "epoch": 0.7794504449045834, + "grad_norm": 0.9335034165544284, + "learning_rate": 2.444749310079848e-06, + "loss": 0.7907, + "step": 8705 + }, + { + "epoch": 0.7795399854496614, + "grad_norm": 0.9685182898566673, + "learning_rate": 2.4428495915370165e-06, + "loss": 0.8384, + "step": 8706 + }, + { + "epoch": 0.7796295259947394, + "grad_norm": 0.939756671441516, + "learning_rate": 2.44095050867705e-06, + "loss": 0.7957, + "step": 8707 + }, + { + "epoch": 0.7797190665398176, + "grad_norm": 0.868974422322578, + "learning_rate": 2.439052061659695e-06, + "loss": 0.818, + "step": 8708 + }, + { + "epoch": 0.7798086070848956, + "grad_norm": 0.9491204767267132, + "learning_rate": 2.4371542506446446e-06, + "loss": 0.7585, + "step": 8709 + }, + { + "epoch": 0.7798981476299737, + "grad_norm": 0.9615964751158518, + "learning_rate": 2.4352570757915273e-06, + "loss": 0.8055, + "step": 8710 + }, + { + "epoch": 0.7799876881750518, + "grad_norm": 1.1089166193866478, + "learning_rate": 2.4333605372599355e-06, + "loss": 0.8208, + "step": 8711 + }, + { + "epoch": 0.7800772287201299, + "grad_norm": 0.9875479566492662, + "learning_rate": 2.4314646352093997e-06, + "loss": 0.8524, + "step": 8712 + }, + { + "epoch": 0.7801667692652079, + "grad_norm": 1.0527589074095396, + "learning_rate": 2.429569369799394e-06, + "loss": 0.817, + "step": 8713 + }, + { + "epoch": 0.7802563098102859, + "grad_norm": 0.9777616013113768, + "learning_rate": 2.4276747411893464e-06, + "loss": 0.8212, + "step": 8714 + }, + { + "epoch": 0.7803458503553641, + "grad_norm": 0.9719598362925369, + "learning_rate": 2.425780749538621e-06, + "loss": 0.8217, + "step": 8715 + }, + { + "epoch": 0.7804353909004421, + "grad_norm": 0.9838348057068431, + "learning_rate": 2.4238873950065335e-06, + "loss": 0.8156, + "step": 8716 + }, + { + "epoch": 0.7805249314455202, + "grad_norm": 0.9378831730612278, + "learning_rate": 2.421994677752353e-06, + "loss": 0.7874, + "step": 8717 + }, + { + "epoch": 0.7806144719905982, + "grad_norm": 0.9826384840592557, + "learning_rate": 2.4201025979352857e-06, + "loss": 0.781, + "step": 8718 + }, + { + "epoch": 0.7807040125356763, + "grad_norm": 0.9987453383325858, + "learning_rate": 2.418211155714486e-06, + "loss": 0.8232, + "step": 8719 + }, + { + "epoch": 0.7807935530807544, + "grad_norm": 0.9292814822179866, + "learning_rate": 2.416320351249062e-06, + "loss": 0.8008, + "step": 8720 + }, + { + "epoch": 0.7808830936258324, + "grad_norm": 0.9817358904005138, + "learning_rate": 2.4144301846980533e-06, + "loss": 0.7657, + "step": 8721 + }, + { + "epoch": 0.7809726341709106, + "grad_norm": 1.019932249549998, + "learning_rate": 2.4125406562204554e-06, + "loss": 0.8098, + "step": 8722 + }, + { + "epoch": 0.7810621747159886, + "grad_norm": 0.9687145054773424, + "learning_rate": 2.4106517659752148e-06, + "loss": 0.8052, + "step": 8723 + }, + { + "epoch": 0.7811517152610666, + "grad_norm": 1.0484305597442376, + "learning_rate": 2.408763514121216e-06, + "loss": 0.8214, + "step": 8724 + }, + { + "epoch": 0.7812412558061447, + "grad_norm": 0.9894091661346851, + "learning_rate": 2.406875900817297e-06, + "loss": 0.7598, + "step": 8725 + }, + { + "epoch": 0.7813307963512228, + "grad_norm": 1.043930387999368, + "learning_rate": 2.4049889262222302e-06, + "loss": 0.8381, + "step": 8726 + }, + { + "epoch": 0.7814203368963009, + "grad_norm": 1.0237127488413573, + "learning_rate": 2.4031025904947445e-06, + "loss": 0.7931, + "step": 8727 + }, + { + "epoch": 0.7815098774413789, + "grad_norm": 0.9325259836035235, + "learning_rate": 2.40121689379351e-06, + "loss": 0.8027, + "step": 8728 + }, + { + "epoch": 0.781599417986457, + "grad_norm": 0.990468417700911, + "learning_rate": 2.3993318362771512e-06, + "loss": 0.7892, + "step": 8729 + }, + { + "epoch": 0.7816889585315351, + "grad_norm": 0.862094648680522, + "learning_rate": 2.3974474181042308e-06, + "loss": 0.8154, + "step": 8730 + }, + { + "epoch": 0.7817784990766131, + "grad_norm": 0.9584993276031846, + "learning_rate": 2.3955636394332602e-06, + "loss": 0.8547, + "step": 8731 + }, + { + "epoch": 0.7818680396216912, + "grad_norm": 1.1391455130256374, + "learning_rate": 2.393680500422695e-06, + "loss": 0.8048, + "step": 8732 + }, + { + "epoch": 0.7819575801667693, + "grad_norm": 0.9174764319765369, + "learning_rate": 2.391798001230937e-06, + "loss": 0.8021, + "step": 8733 + }, + { + "epoch": 0.7820471207118473, + "grad_norm": 1.0884402618014684, + "learning_rate": 2.3899161420163398e-06, + "loss": 0.7758, + "step": 8734 + }, + { + "epoch": 0.7821366612569254, + "grad_norm": 1.0108327963843435, + "learning_rate": 2.3880349229371946e-06, + "loss": 0.8339, + "step": 8735 + }, + { + "epoch": 0.7822262018020034, + "grad_norm": 1.0535519498263965, + "learning_rate": 2.386154344151752e-06, + "loss": 0.8265, + "step": 8736 + }, + { + "epoch": 0.7823157423470816, + "grad_norm": 1.1526385851654188, + "learning_rate": 2.3842744058181923e-06, + "loss": 0.7772, + "step": 8737 + }, + { + "epoch": 0.7824052828921596, + "grad_norm": 0.9876798554462964, + "learning_rate": 2.3823951080946516e-06, + "loss": 0.8221, + "step": 8738 + }, + { + "epoch": 0.7824948234372376, + "grad_norm": 0.9898243017443573, + "learning_rate": 2.380516451139212e-06, + "loss": 0.8665, + "step": 8739 + }, + { + "epoch": 0.7825843639823158, + "grad_norm": 0.9042842363854605, + "learning_rate": 2.378638435109898e-06, + "loss": 0.7334, + "step": 8740 + }, + { + "epoch": 0.7826739045273938, + "grad_norm": 0.9500000541992688, + "learning_rate": 2.3767610601646798e-06, + "loss": 0.8287, + "step": 8741 + }, + { + "epoch": 0.7827634450724719, + "grad_norm": 0.9404061186406021, + "learning_rate": 2.3748843264614864e-06, + "loss": 0.8269, + "step": 8742 + }, + { + "epoch": 0.7828529856175499, + "grad_norm": 1.0806817404180178, + "learning_rate": 2.3730082341581715e-06, + "loss": 0.8391, + "step": 8743 + }, + { + "epoch": 0.782942526162628, + "grad_norm": 1.0017549328595794, + "learning_rate": 2.3711327834125496e-06, + "loss": 0.8186, + "step": 8744 + }, + { + "epoch": 0.7830320667077061, + "grad_norm": 1.010073845125027, + "learning_rate": 2.3692579743823783e-06, + "loss": 0.8298, + "step": 8745 + }, + { + "epoch": 0.7831216072527841, + "grad_norm": 0.9549761052982769, + "learning_rate": 2.3673838072253597e-06, + "loss": 0.8596, + "step": 8746 + }, + { + "epoch": 0.7832111477978623, + "grad_norm": 1.0207355898438168, + "learning_rate": 2.3655102820991425e-06, + "loss": 0.7556, + "step": 8747 + }, + { + "epoch": 0.7833006883429403, + "grad_norm": 0.9624512074377601, + "learning_rate": 2.3636373991613225e-06, + "loss": 0.8222, + "step": 8748 + }, + { + "epoch": 0.7833902288880183, + "grad_norm": 1.0519269400205644, + "learning_rate": 2.36176515856944e-06, + "loss": 0.8427, + "step": 8749 + }, + { + "epoch": 0.7834797694330964, + "grad_norm": 1.0441377955891853, + "learning_rate": 2.3598935604809813e-06, + "loss": 0.7933, + "step": 8750 + }, + { + "epoch": 0.7835693099781745, + "grad_norm": 0.8989804098882979, + "learning_rate": 2.3580226050533794e-06, + "loss": 0.7599, + "step": 8751 + }, + { + "epoch": 0.7836588505232526, + "grad_norm": 0.9307537421470434, + "learning_rate": 2.3561522924440127e-06, + "loss": 0.8091, + "step": 8752 + }, + { + "epoch": 0.7837483910683306, + "grad_norm": 1.1672075585219102, + "learning_rate": 2.354282622810207e-06, + "loss": 0.8267, + "step": 8753 + }, + { + "epoch": 0.7838379316134086, + "grad_norm": 0.9321849038589167, + "learning_rate": 2.352413596309231e-06, + "loss": 0.8009, + "step": 8754 + }, + { + "epoch": 0.7839274721584868, + "grad_norm": 1.1401846708248895, + "learning_rate": 2.3505452130983018e-06, + "loss": 0.7609, + "step": 8755 + }, + { + "epoch": 0.7840170127035648, + "grad_norm": 1.0086536537345712, + "learning_rate": 2.348677473334583e-06, + "loss": 0.8246, + "step": 8756 + }, + { + "epoch": 0.7841065532486429, + "grad_norm": 1.0960619415607866, + "learning_rate": 2.3468103771751816e-06, + "loss": 0.7877, + "step": 8757 + }, + { + "epoch": 0.784196093793721, + "grad_norm": 0.9493553029955952, + "learning_rate": 2.344943924777151e-06, + "loss": 0.7995, + "step": 8758 + }, + { + "epoch": 0.784285634338799, + "grad_norm": 0.9784209525735732, + "learning_rate": 2.3430781162974927e-06, + "loss": 0.8373, + "step": 8759 + }, + { + "epoch": 0.7843751748838771, + "grad_norm": 0.9656322004647505, + "learning_rate": 2.3412129518931516e-06, + "loss": 0.7997, + "step": 8760 + }, + { + "epoch": 0.7844647154289551, + "grad_norm": 0.9494327500637705, + "learning_rate": 2.3393484317210192e-06, + "loss": 0.8395, + "step": 8761 + }, + { + "epoch": 0.7845542559740333, + "grad_norm": 0.9726676120228631, + "learning_rate": 2.3374845559379323e-06, + "loss": 0.7657, + "step": 8762 + }, + { + "epoch": 0.7846437965191113, + "grad_norm": 0.9296199793875822, + "learning_rate": 2.3356213247006754e-06, + "loss": 0.811, + "step": 8763 + }, + { + "epoch": 0.7847333370641894, + "grad_norm": 1.0542117574625105, + "learning_rate": 2.3337587381659753e-06, + "loss": 0.7798, + "step": 8764 + }, + { + "epoch": 0.7848228776092675, + "grad_norm": 1.0146806637316026, + "learning_rate": 2.3318967964905103e-06, + "loss": 0.8857, + "step": 8765 + }, + { + "epoch": 0.7849124181543455, + "grad_norm": 0.9455980437618184, + "learning_rate": 2.3300354998308972e-06, + "loss": 0.7791, + "step": 8766 + }, + { + "epoch": 0.7850019586994236, + "grad_norm": 0.8931486512684882, + "learning_rate": 2.3281748483437038e-06, + "loss": 0.8029, + "step": 8767 + }, + { + "epoch": 0.7850914992445016, + "grad_norm": 0.9451687590167771, + "learning_rate": 2.326314842185443e-06, + "loss": 0.7983, + "step": 8768 + }, + { + "epoch": 0.7851810397895798, + "grad_norm": 1.1189137871939476, + "learning_rate": 2.3244554815125732e-06, + "loss": 0.7663, + "step": 8769 + }, + { + "epoch": 0.7852705803346578, + "grad_norm": 1.0008957545276058, + "learning_rate": 2.3225967664814907e-06, + "loss": 0.817, + "step": 8770 + }, + { + "epoch": 0.7853601208797358, + "grad_norm": 1.0052841692325039, + "learning_rate": 2.3207386972485522e-06, + "loss": 0.8393, + "step": 8771 + }, + { + "epoch": 0.7854496614248139, + "grad_norm": 0.9977413844293204, + "learning_rate": 2.3188812739700506e-06, + "loss": 0.7778, + "step": 8772 + }, + { + "epoch": 0.785539201969892, + "grad_norm": 1.0365196226117177, + "learning_rate": 2.317024496802226e-06, + "loss": 0.8226, + "step": 8773 + }, + { + "epoch": 0.7856287425149701, + "grad_norm": 1.1630771621425773, + "learning_rate": 2.315168365901267e-06, + "loss": 0.7628, + "step": 8774 + }, + { + "epoch": 0.7857182830600481, + "grad_norm": 1.1337964037027655, + "learning_rate": 2.3133128814232988e-06, + "loss": 0.7727, + "step": 8775 + }, + { + "epoch": 0.7858078236051262, + "grad_norm": 0.9107756358290092, + "learning_rate": 2.3114580435244004e-06, + "loss": 0.8009, + "step": 8776 + }, + { + "epoch": 0.7858973641502043, + "grad_norm": 1.0592945362549007, + "learning_rate": 2.309603852360599e-06, + "loss": 0.7827, + "step": 8777 + }, + { + "epoch": 0.7859869046952823, + "grad_norm": 0.926739927611948, + "learning_rate": 2.3077503080878605e-06, + "loss": 0.7934, + "step": 8778 + }, + { + "epoch": 0.7860764452403604, + "grad_norm": 1.0627083194969547, + "learning_rate": 2.3058974108621003e-06, + "loss": 0.7852, + "step": 8779 + }, + { + "epoch": 0.7861659857854385, + "grad_norm": 1.0507656737132343, + "learning_rate": 2.304045160839179e-06, + "loss": 0.799, + "step": 8780 + }, + { + "epoch": 0.7862555263305165, + "grad_norm": 0.9610498882128611, + "learning_rate": 2.3021935581748978e-06, + "loss": 0.8268, + "step": 8781 + }, + { + "epoch": 0.7863450668755946, + "grad_norm": 0.9235347897084841, + "learning_rate": 2.3003426030250064e-06, + "loss": 0.7788, + "step": 8782 + }, + { + "epoch": 0.7864346074206727, + "grad_norm": 1.1127204532451767, + "learning_rate": 2.298492295545207e-06, + "loss": 0.8619, + "step": 8783 + }, + { + "epoch": 0.7865241479657508, + "grad_norm": 0.9592300023531104, + "learning_rate": 2.2966426358911387e-06, + "loss": 0.8194, + "step": 8784 + }, + { + "epoch": 0.7866136885108288, + "grad_norm": 1.0030501380640002, + "learning_rate": 2.294793624218392e-06, + "loss": 0.8237, + "step": 8785 + }, + { + "epoch": 0.7867032290559068, + "grad_norm": 1.1028807924671524, + "learning_rate": 2.2929452606824942e-06, + "loss": 0.8019, + "step": 8786 + }, + { + "epoch": 0.786792769600985, + "grad_norm": 0.9820773594965431, + "learning_rate": 2.291097545438926e-06, + "loss": 0.8298, + "step": 8787 + }, + { + "epoch": 0.786882310146063, + "grad_norm": 1.0210859607733827, + "learning_rate": 2.28925047864311e-06, + "loss": 0.7826, + "step": 8788 + }, + { + "epoch": 0.7869718506911411, + "grad_norm": 0.946124897122373, + "learning_rate": 2.2874040604504155e-06, + "loss": 0.8366, + "step": 8789 + }, + { + "epoch": 0.7870613912362191, + "grad_norm": 0.8881763926749735, + "learning_rate": 2.285558291016161e-06, + "loss": 0.8333, + "step": 8790 + }, + { + "epoch": 0.7871509317812972, + "grad_norm": 0.907528679723277, + "learning_rate": 2.283713170495606e-06, + "loss": 0.7641, + "step": 8791 + }, + { + "epoch": 0.7872404723263753, + "grad_norm": 0.8472856997477702, + "learning_rate": 2.281868699043951e-06, + "loss": 0.7623, + "step": 8792 + }, + { + "epoch": 0.7873300128714533, + "grad_norm": 1.0218533312874023, + "learning_rate": 2.2800248768163515e-06, + "loss": 0.8351, + "step": 8793 + }, + { + "epoch": 0.7874195534165315, + "grad_norm": 1.0179797540669078, + "learning_rate": 2.278181703967901e-06, + "loss": 0.7974, + "step": 8794 + }, + { + "epoch": 0.7875090939616095, + "grad_norm": 0.9597173283575153, + "learning_rate": 2.2763391806536396e-06, + "loss": 0.7763, + "step": 8795 + }, + { + "epoch": 0.7875986345066875, + "grad_norm": 0.9481685366579282, + "learning_rate": 2.2744973070285624e-06, + "loss": 0.7761, + "step": 8796 + }, + { + "epoch": 0.7876881750517656, + "grad_norm": 0.9775912472727575, + "learning_rate": 2.2726560832475952e-06, + "loss": 0.8477, + "step": 8797 + }, + { + "epoch": 0.7877777155968437, + "grad_norm": 1.0247270170899692, + "learning_rate": 2.270815509465616e-06, + "loss": 0.822, + "step": 8798 + }, + { + "epoch": 0.7878672561419218, + "grad_norm": 1.0284337356477788, + "learning_rate": 2.2689755858374497e-06, + "loss": 0.8085, + "step": 8799 + }, + { + "epoch": 0.7879567966869998, + "grad_norm": 0.9872958708900921, + "learning_rate": 2.2671363125178635e-06, + "loss": 0.8171, + "step": 8800 + }, + { + "epoch": 0.788046337232078, + "grad_norm": 0.9854110917532096, + "learning_rate": 2.2652976896615684e-06, + "loss": 0.8073, + "step": 8801 + }, + { + "epoch": 0.788135877777156, + "grad_norm": 0.9548908592913122, + "learning_rate": 2.263459717423233e-06, + "loss": 0.7974, + "step": 8802 + }, + { + "epoch": 0.788225418322234, + "grad_norm": 1.0316180066778164, + "learning_rate": 2.2616223959574523e-06, + "loss": 0.7137, + "step": 8803 + }, + { + "epoch": 0.7883149588673121, + "grad_norm": 1.0002898413091361, + "learning_rate": 2.2597857254187783e-06, + "loss": 0.7828, + "step": 8804 + }, + { + "epoch": 0.7884044994123902, + "grad_norm": 0.9420785300864903, + "learning_rate": 2.257949705961706e-06, + "loss": 0.7276, + "step": 8805 + }, + { + "epoch": 0.7884940399574683, + "grad_norm": 0.9974899413573534, + "learning_rate": 2.256114337740676e-06, + "loss": 0.8173, + "step": 8806 + }, + { + "epoch": 0.7885835805025463, + "grad_norm": 2.0828067823459424, + "learning_rate": 2.2542796209100716e-06, + "loss": 0.8174, + "step": 8807 + }, + { + "epoch": 0.7886731210476243, + "grad_norm": 0.9630039001867484, + "learning_rate": 2.252445555624225e-06, + "loss": 0.8426, + "step": 8808 + }, + { + "epoch": 0.7887626615927025, + "grad_norm": 1.311208445544868, + "learning_rate": 2.2506121420374116e-06, + "loss": 0.7796, + "step": 8809 + }, + { + "epoch": 0.7888522021377805, + "grad_norm": 0.9750142899042925, + "learning_rate": 2.2487793803038516e-06, + "loss": 0.8166, + "step": 8810 + }, + { + "epoch": 0.7889417426828585, + "grad_norm": 1.0921116353647442, + "learning_rate": 2.2469472705777105e-06, + "loss": 0.8466, + "step": 8811 + }, + { + "epoch": 0.7890312832279367, + "grad_norm": 1.0269712688705133, + "learning_rate": 2.245115813013101e-06, + "loss": 0.8698, + "step": 8812 + }, + { + "epoch": 0.7891208237730147, + "grad_norm": 0.9456547808577754, + "learning_rate": 2.243285007764079e-06, + "loss": 0.7754, + "step": 8813 + }, + { + "epoch": 0.7892103643180928, + "grad_norm": 0.9033694835512854, + "learning_rate": 2.241454854984645e-06, + "loss": 0.7539, + "step": 8814 + }, + { + "epoch": 0.7892999048631708, + "grad_norm": 1.0013098745570665, + "learning_rate": 2.239625354828745e-06, + "loss": 0.7933, + "step": 8815 + }, + { + "epoch": 0.789389445408249, + "grad_norm": 0.9801371057762093, + "learning_rate": 2.237796507450272e-06, + "loss": 0.788, + "step": 8816 + }, + { + "epoch": 0.789478985953327, + "grad_norm": 1.012532582309637, + "learning_rate": 2.235968313003062e-06, + "loss": 0.8404, + "step": 8817 + }, + { + "epoch": 0.789568526498405, + "grad_norm": 0.9723675348770959, + "learning_rate": 2.2341407716408957e-06, + "loss": 0.8311, + "step": 8818 + }, + { + "epoch": 0.7896580670434832, + "grad_norm": 1.0135581393841304, + "learning_rate": 2.2323138835175027e-06, + "loss": 0.8223, + "step": 8819 + }, + { + "epoch": 0.7897476075885612, + "grad_norm": 1.0367338273330169, + "learning_rate": 2.2304876487865524e-06, + "loss": 0.8708, + "step": 8820 + }, + { + "epoch": 0.7898371481336393, + "grad_norm": 0.9618332907325252, + "learning_rate": 2.2286620676016624e-06, + "loss": 0.7893, + "step": 8821 + }, + { + "epoch": 0.7899266886787173, + "grad_norm": 0.9289094126116735, + "learning_rate": 2.226837140116396e-06, + "loss": 0.8499, + "step": 8822 + }, + { + "epoch": 0.7900162292237954, + "grad_norm": 1.000094770991562, + "learning_rate": 2.2250128664842574e-06, + "loss": 0.7873, + "step": 8823 + }, + { + "epoch": 0.7901057697688735, + "grad_norm": 1.13759964390537, + "learning_rate": 2.223189246858701e-06, + "loss": 0.8009, + "step": 8824 + }, + { + "epoch": 0.7901953103139515, + "grad_norm": 1.0365054008241492, + "learning_rate": 2.2213662813931224e-06, + "loss": 0.7318, + "step": 8825 + }, + { + "epoch": 0.7902848508590296, + "grad_norm": 1.045021585803547, + "learning_rate": 2.2195439702408637e-06, + "loss": 0.8301, + "step": 8826 + }, + { + "epoch": 0.7903743914041077, + "grad_norm": 0.9923981155938767, + "learning_rate": 2.2177223135552126e-06, + "loss": 0.8186, + "step": 8827 + }, + { + "epoch": 0.7904639319491857, + "grad_norm": 0.9499573148857462, + "learning_rate": 2.2159013114894e-06, + "loss": 0.7703, + "step": 8828 + }, + { + "epoch": 0.7905534724942638, + "grad_norm": 0.9107601572419948, + "learning_rate": 2.2140809641966066e-06, + "loss": 0.7942, + "step": 8829 + }, + { + "epoch": 0.7906430130393419, + "grad_norm": 1.0292158207018305, + "learning_rate": 2.2122612718299443e-06, + "loss": 0.8129, + "step": 8830 + }, + { + "epoch": 0.79073255358442, + "grad_norm": 1.148734373913572, + "learning_rate": 2.210442234542488e-06, + "loss": 0.764, + "step": 8831 + }, + { + "epoch": 0.790822094129498, + "grad_norm": 1.0255395463226753, + "learning_rate": 2.208623852487248e-06, + "loss": 0.783, + "step": 8832 + }, + { + "epoch": 0.790911634674576, + "grad_norm": 0.970354735831638, + "learning_rate": 2.206806125817179e-06, + "loss": 0.7439, + "step": 8833 + }, + { + "epoch": 0.7910011752196542, + "grad_norm": 1.0097089662494023, + "learning_rate": 2.204989054685187e-06, + "loss": 0.8105, + "step": 8834 + }, + { + "epoch": 0.7910907157647322, + "grad_norm": 0.9924486497518542, + "learning_rate": 2.20317263924411e-06, + "loss": 0.8284, + "step": 8835 + }, + { + "epoch": 0.7911802563098103, + "grad_norm": 0.9655739240678225, + "learning_rate": 2.201356879646741e-06, + "loss": 0.7851, + "step": 8836 + }, + { + "epoch": 0.7912697968548884, + "grad_norm": 1.1058994333531043, + "learning_rate": 2.1995417760458205e-06, + "loss": 0.8207, + "step": 8837 + }, + { + "epoch": 0.7913593373999664, + "grad_norm": 1.0276176191339472, + "learning_rate": 2.197727328594026e-06, + "loss": 0.8757, + "step": 8838 + }, + { + "epoch": 0.7914488779450445, + "grad_norm": 1.101754550237192, + "learning_rate": 2.1959135374439832e-06, + "loss": 0.7547, + "step": 8839 + }, + { + "epoch": 0.7915384184901225, + "grad_norm": 1.0565682849241695, + "learning_rate": 2.194100402748266e-06, + "loss": 0.8221, + "step": 8840 + }, + { + "epoch": 0.7916279590352007, + "grad_norm": 1.0560905693258091, + "learning_rate": 2.192287924659383e-06, + "loss": 0.8038, + "step": 8841 + }, + { + "epoch": 0.7917174995802787, + "grad_norm": 0.9582270705261191, + "learning_rate": 2.190476103329796e-06, + "loss": 0.8415, + "step": 8842 + }, + { + "epoch": 0.7918070401253567, + "grad_norm": 1.0203777687067934, + "learning_rate": 2.1886649389119084e-06, + "loss": 0.7785, + "step": 8843 + }, + { + "epoch": 0.7918965806704348, + "grad_norm": 0.9166993743527946, + "learning_rate": 2.186854431558073e-06, + "loss": 0.8424, + "step": 8844 + }, + { + "epoch": 0.7919861212155129, + "grad_norm": 1.0649461166358671, + "learning_rate": 2.185044581420586e-06, + "loss": 0.8246, + "step": 8845 + }, + { + "epoch": 0.792075661760591, + "grad_norm": 0.9771693558322117, + "learning_rate": 2.183235388651679e-06, + "loss": 0.8385, + "step": 8846 + }, + { + "epoch": 0.792165202305669, + "grad_norm": 0.8922495877768892, + "learning_rate": 2.181426853403538e-06, + "loss": 0.7821, + "step": 8847 + }, + { + "epoch": 0.7922547428507472, + "grad_norm": 0.9537647602461077, + "learning_rate": 2.1796189758282917e-06, + "loss": 0.7645, + "step": 8848 + }, + { + "epoch": 0.7923442833958252, + "grad_norm": 1.0698966323901165, + "learning_rate": 2.177811756078011e-06, + "loss": 0.8485, + "step": 8849 + }, + { + "epoch": 0.7924338239409032, + "grad_norm": 0.9191909929695842, + "learning_rate": 2.176005194304718e-06, + "loss": 0.828, + "step": 8850 + }, + { + "epoch": 0.7925233644859813, + "grad_norm": 0.9389178614805662, + "learning_rate": 2.1741992906603736e-06, + "loss": 0.8278, + "step": 8851 + }, + { + "epoch": 0.7926129050310594, + "grad_norm": 1.0511934024051504, + "learning_rate": 2.1723940452968804e-06, + "loss": 0.8288, + "step": 8852 + }, + { + "epoch": 0.7927024455761374, + "grad_norm": 0.9805535410851165, + "learning_rate": 2.1705894583660924e-06, + "loss": 0.7853, + "step": 8853 + }, + { + "epoch": 0.7927919861212155, + "grad_norm": 0.9429170712915458, + "learning_rate": 2.168785530019806e-06, + "loss": 0.8176, + "step": 8854 + }, + { + "epoch": 0.7928815266662936, + "grad_norm": 0.9868937450701486, + "learning_rate": 2.166982260409758e-06, + "loss": 0.844, + "step": 8855 + }, + { + "epoch": 0.7929710672113717, + "grad_norm": 0.9716747338511501, + "learning_rate": 2.165179649687642e-06, + "loss": 0.7673, + "step": 8856 + }, + { + "epoch": 0.7930606077564497, + "grad_norm": 0.9581162629847151, + "learning_rate": 2.16337769800508e-06, + "loss": 0.7605, + "step": 8857 + }, + { + "epoch": 0.7931501483015277, + "grad_norm": 0.9541289463155737, + "learning_rate": 2.161576405513649e-06, + "loss": 0.8244, + "step": 8858 + }, + { + "epoch": 0.7932396888466059, + "grad_norm": 0.9793815598484333, + "learning_rate": 2.159775772364868e-06, + "loss": 0.7841, + "step": 8859 + }, + { + "epoch": 0.7933292293916839, + "grad_norm": 0.9282901114744271, + "learning_rate": 2.157975798710199e-06, + "loss": 0.7872, + "step": 8860 + }, + { + "epoch": 0.793418769936762, + "grad_norm": 0.9648132712096085, + "learning_rate": 2.156176484701049e-06, + "loss": 0.8012, + "step": 8861 + }, + { + "epoch": 0.79350831048184, + "grad_norm": 1.1146016129785001, + "learning_rate": 2.1543778304887786e-06, + "loss": 0.764, + "step": 8862 + }, + { + "epoch": 0.7935978510269182, + "grad_norm": 1.002962446634905, + "learning_rate": 2.1525798362246743e-06, + "loss": 0.8195, + "step": 8863 + }, + { + "epoch": 0.7936873915719962, + "grad_norm": 0.9510714212136187, + "learning_rate": 2.1507825020599827e-06, + "loss": 0.8275, + "step": 8864 + }, + { + "epoch": 0.7937769321170742, + "grad_norm": 0.9522354776051893, + "learning_rate": 2.1489858281458886e-06, + "loss": 0.7642, + "step": 8865 + }, + { + "epoch": 0.7938664726621524, + "grad_norm": 1.0518491796279594, + "learning_rate": 2.1471898146335223e-06, + "loss": 0.784, + "step": 8866 + }, + { + "epoch": 0.7939560132072304, + "grad_norm": 0.8939040459416904, + "learning_rate": 2.1453944616739587e-06, + "loss": 0.7981, + "step": 8867 + }, + { + "epoch": 0.7940455537523085, + "grad_norm": 1.2042825864351896, + "learning_rate": 2.1435997694182174e-06, + "loss": 0.7992, + "step": 8868 + }, + { + "epoch": 0.7941350942973865, + "grad_norm": 1.029196072443649, + "learning_rate": 2.141805738017262e-06, + "loss": 0.796, + "step": 8869 + }, + { + "epoch": 0.7942246348424646, + "grad_norm": 0.9254921620057439, + "learning_rate": 2.1400123676219995e-06, + "loss": 0.773, + "step": 8870 + }, + { + "epoch": 0.7943141753875427, + "grad_norm": 0.879414169996277, + "learning_rate": 2.1382196583832838e-06, + "loss": 0.7702, + "step": 8871 + }, + { + "epoch": 0.7944037159326207, + "grad_norm": 1.0247312099828798, + "learning_rate": 2.136427610451912e-06, + "loss": 0.8186, + "step": 8872 + }, + { + "epoch": 0.7944932564776989, + "grad_norm": 0.9132595674668879, + "learning_rate": 2.1346362239786234e-06, + "loss": 0.7755, + "step": 8873 + }, + { + "epoch": 0.7945827970227769, + "grad_norm": 0.9751940031190726, + "learning_rate": 2.1328454991141056e-06, + "loss": 0.7762, + "step": 8874 + }, + { + "epoch": 0.7946723375678549, + "grad_norm": 1.0362840050223117, + "learning_rate": 2.1310554360089874e-06, + "loss": 0.7835, + "step": 8875 + }, + { + "epoch": 0.794761878112933, + "grad_norm": 1.0399341139820528, + "learning_rate": 2.1292660348138427e-06, + "loss": 0.8115, + "step": 8876 + }, + { + "epoch": 0.7948514186580111, + "grad_norm": 0.9718358730389632, + "learning_rate": 2.127477295679191e-06, + "loss": 0.7593, + "step": 8877 + }, + { + "epoch": 0.7949409592030892, + "grad_norm": 0.8816905002650758, + "learning_rate": 2.1256892187554957e-06, + "loss": 0.7934, + "step": 8878 + }, + { + "epoch": 0.7950304997481672, + "grad_norm": 1.0407617644966412, + "learning_rate": 2.1239018041931636e-06, + "loss": 0.7352, + "step": 8879 + }, + { + "epoch": 0.7951200402932452, + "grad_norm": 0.9152238276073582, + "learning_rate": 2.122115052142545e-06, + "loss": 0.7771, + "step": 8880 + }, + { + "epoch": 0.7952095808383234, + "grad_norm": 0.9640855152198113, + "learning_rate": 2.120328962753936e-06, + "loss": 0.8457, + "step": 8881 + }, + { + "epoch": 0.7952991213834014, + "grad_norm": 0.9292131675962387, + "learning_rate": 2.1185435361775784e-06, + "loss": 0.8155, + "step": 8882 + }, + { + "epoch": 0.7953886619284795, + "grad_norm": 0.9879104841689254, + "learning_rate": 2.116758772563654e-06, + "loss": 0.7743, + "step": 8883 + }, + { + "epoch": 0.7954782024735576, + "grad_norm": 0.9745975647515067, + "learning_rate": 2.114974672062293e-06, + "loss": 0.8067, + "step": 8884 + }, + { + "epoch": 0.7955677430186356, + "grad_norm": 0.9658721146486333, + "learning_rate": 2.1131912348235686e-06, + "loss": 0.7727, + "step": 8885 + }, + { + "epoch": 0.7956572835637137, + "grad_norm": 0.9305853784472153, + "learning_rate": 2.111408460997495e-06, + "loss": 0.8008, + "step": 8886 + }, + { + "epoch": 0.7957468241087917, + "grad_norm": 0.8027246211015022, + "learning_rate": 2.1096263507340364e-06, + "loss": 0.7533, + "step": 8887 + }, + { + "epoch": 0.7958363646538699, + "grad_norm": 1.0265060236723729, + "learning_rate": 2.107844904183096e-06, + "loss": 0.8112, + "step": 8888 + }, + { + "epoch": 0.7959259051989479, + "grad_norm": 1.1915036697364327, + "learning_rate": 2.1060641214945277e-06, + "loss": 0.7856, + "step": 8889 + }, + { + "epoch": 0.7960154457440259, + "grad_norm": 1.0771954716619745, + "learning_rate": 2.1042840028181154e-06, + "loss": 0.7831, + "step": 8890 + }, + { + "epoch": 0.7961049862891041, + "grad_norm": 1.0424067683201574, + "learning_rate": 2.1025045483036056e-06, + "loss": 0.8087, + "step": 8891 + }, + { + "epoch": 0.7961945268341821, + "grad_norm": 0.9047816933166197, + "learning_rate": 2.100725758100678e-06, + "loss": 0.7841, + "step": 8892 + }, + { + "epoch": 0.7962840673792602, + "grad_norm": 1.1216797578559359, + "learning_rate": 2.0989476323589577e-06, + "loss": 0.8016, + "step": 8893 + }, + { + "epoch": 0.7963736079243382, + "grad_norm": 0.9040761294760578, + "learning_rate": 2.0971701712280157e-06, + "loss": 0.8009, + "step": 8894 + }, + { + "epoch": 0.7964631484694163, + "grad_norm": 0.9593532458777572, + "learning_rate": 2.0953933748573686e-06, + "loss": 0.8137, + "step": 8895 + }, + { + "epoch": 0.7965526890144944, + "grad_norm": 0.9672365130167049, + "learning_rate": 2.0936172433964696e-06, + "loss": 0.7526, + "step": 8896 + }, + { + "epoch": 0.7966422295595724, + "grad_norm": 0.9674436620913189, + "learning_rate": 2.0918417769947207e-06, + "loss": 0.8305, + "step": 8897 + }, + { + "epoch": 0.7967317701046505, + "grad_norm": 1.022019894307431, + "learning_rate": 2.0900669758014734e-06, + "loss": 0.8555, + "step": 8898 + }, + { + "epoch": 0.7968213106497286, + "grad_norm": 0.9647428995115607, + "learning_rate": 2.0882928399660165e-06, + "loss": 0.8157, + "step": 8899 + }, + { + "epoch": 0.7969108511948066, + "grad_norm": 1.0221131979223792, + "learning_rate": 2.0865193696375864e-06, + "loss": 0.857, + "step": 8900 + }, + { + "epoch": 0.7970003917398847, + "grad_norm": 1.086049933322398, + "learning_rate": 2.0847465649653563e-06, + "loss": 0.8008, + "step": 8901 + }, + { + "epoch": 0.7970899322849628, + "grad_norm": 0.9341295784050314, + "learning_rate": 2.082974426098452e-06, + "loss": 0.7696, + "step": 8902 + }, + { + "epoch": 0.7971794728300409, + "grad_norm": 1.014916977125944, + "learning_rate": 2.081202953185937e-06, + "loss": 0.8024, + "step": 8903 + }, + { + "epoch": 0.7972690133751189, + "grad_norm": 1.1244790021383773, + "learning_rate": 2.0794321463768275e-06, + "loss": 0.7744, + "step": 8904 + }, + { + "epoch": 0.7973585539201969, + "grad_norm": 1.0609299785461552, + "learning_rate": 2.077662005820078e-06, + "loss": 0.719, + "step": 8905 + }, + { + "epoch": 0.7974480944652751, + "grad_norm": 0.8813540731635965, + "learning_rate": 2.075892531664581e-06, + "loss": 0.8562, + "step": 8906 + }, + { + "epoch": 0.7975376350103531, + "grad_norm": 1.0129547571339297, + "learning_rate": 2.0741237240591816e-06, + "loss": 0.8284, + "step": 8907 + }, + { + "epoch": 0.7976271755554312, + "grad_norm": 1.026752532385267, + "learning_rate": 2.0723555831526664e-06, + "loss": 0.7533, + "step": 8908 + }, + { + "epoch": 0.7977167161005093, + "grad_norm": 1.0082881740929979, + "learning_rate": 2.070588109093763e-06, + "loss": 0.7799, + "step": 8909 + }, + { + "epoch": 0.7978062566455874, + "grad_norm": 1.0222125820743238, + "learning_rate": 2.068821302031151e-06, + "loss": 0.859, + "step": 8910 + }, + { + "epoch": 0.7978957971906654, + "grad_norm": 0.8406768313365586, + "learning_rate": 2.0670551621134493e-06, + "loss": 0.7588, + "step": 8911 + }, + { + "epoch": 0.7979853377357434, + "grad_norm": 0.940715655258229, + "learning_rate": 2.065289689489213e-06, + "loss": 0.8142, + "step": 8912 + }, + { + "epoch": 0.7980748782808216, + "grad_norm": 0.9908633358188143, + "learning_rate": 2.063524884306951e-06, + "loss": 0.7465, + "step": 8913 + }, + { + "epoch": 0.7981644188258996, + "grad_norm": 0.9587871217646229, + "learning_rate": 2.0617607467151122e-06, + "loss": 0.7797, + "step": 8914 + }, + { + "epoch": 0.7982539593709777, + "grad_norm": 0.9133146776474791, + "learning_rate": 2.0599972768620903e-06, + "loss": 0.831, + "step": 8915 + }, + { + "epoch": 0.7983434999160557, + "grad_norm": 0.9565861570919098, + "learning_rate": 2.058234474896227e-06, + "loss": 0.7946, + "step": 8916 + }, + { + "epoch": 0.7984330404611338, + "grad_norm": 0.9473138511540742, + "learning_rate": 2.056472340965798e-06, + "loss": 0.7643, + "step": 8917 + }, + { + "epoch": 0.7985225810062119, + "grad_norm": 0.9523408903439556, + "learning_rate": 2.05471087521903e-06, + "loss": 0.7912, + "step": 8918 + }, + { + "epoch": 0.7986121215512899, + "grad_norm": 1.0343372038253384, + "learning_rate": 2.052950077804091e-06, + "loss": 0.775, + "step": 8919 + }, + { + "epoch": 0.7987016620963681, + "grad_norm": 0.8707703942501248, + "learning_rate": 2.0511899488690955e-06, + "loss": 0.8002, + "step": 8920 + }, + { + "epoch": 0.7987912026414461, + "grad_norm": 1.084775374225361, + "learning_rate": 2.049430488562095e-06, + "loss": 0.806, + "step": 8921 + }, + { + "epoch": 0.7988807431865241, + "grad_norm": 1.0462282722156777, + "learning_rate": 2.0476716970310993e-06, + "loss": 0.8717, + "step": 8922 + }, + { + "epoch": 0.7989702837316022, + "grad_norm": 0.9354454866462218, + "learning_rate": 2.0459135744240443e-06, + "loss": 0.8414, + "step": 8923 + }, + { + "epoch": 0.7990598242766803, + "grad_norm": 0.9536108262320696, + "learning_rate": 2.0441561208888183e-06, + "loss": 0.8418, + "step": 8924 + }, + { + "epoch": 0.7991493648217584, + "grad_norm": 0.9476826742219421, + "learning_rate": 2.0423993365732544e-06, + "loss": 0.8164, + "step": 8925 + }, + { + "epoch": 0.7992389053668364, + "grad_norm": 1.0427614582132403, + "learning_rate": 2.040643221625126e-06, + "loss": 0.761, + "step": 8926 + }, + { + "epoch": 0.7993284459119145, + "grad_norm": 1.002837024706317, + "learning_rate": 2.038887776192152e-06, + "loss": 0.7974, + "step": 8927 + }, + { + "epoch": 0.7994179864569926, + "grad_norm": 0.9533197788703245, + "learning_rate": 2.037133000421997e-06, + "loss": 0.7787, + "step": 8928 + }, + { + "epoch": 0.7995075270020706, + "grad_norm": 1.0013106881363134, + "learning_rate": 2.0353788944622643e-06, + "loss": 0.7879, + "step": 8929 + }, + { + "epoch": 0.7995970675471487, + "grad_norm": 1.2136168670820995, + "learning_rate": 2.0336254584605053e-06, + "loss": 0.8189, + "step": 8930 + }, + { + "epoch": 0.7996866080922268, + "grad_norm": 1.0670456884612995, + "learning_rate": 2.0318726925642116e-06, + "loss": 0.8563, + "step": 8931 + }, + { + "epoch": 0.7997761486373048, + "grad_norm": 1.0565358854782514, + "learning_rate": 2.0301205969208227e-06, + "loss": 0.8094, + "step": 8932 + }, + { + "epoch": 0.7998656891823829, + "grad_norm": 0.9343082196443558, + "learning_rate": 2.0283691716777166e-06, + "loss": 0.7268, + "step": 8933 + }, + { + "epoch": 0.7999552297274609, + "grad_norm": 0.9297123089909098, + "learning_rate": 2.026618416982219e-06, + "loss": 0.7345, + "step": 8934 + }, + { + "epoch": 0.8000447702725391, + "grad_norm": 1.086878060051482, + "learning_rate": 2.024868332981598e-06, + "loss": 0.7605, + "step": 8935 + }, + { + "epoch": 0.8001343108176171, + "grad_norm": 1.0291050125375094, + "learning_rate": 2.0231189198230626e-06, + "loss": 0.8069, + "step": 8936 + }, + { + "epoch": 0.8002238513626951, + "grad_norm": 0.967943902030107, + "learning_rate": 2.021370177653771e-06, + "loss": 0.8317, + "step": 8937 + }, + { + "epoch": 0.8003133919077733, + "grad_norm": 0.9247849716532679, + "learning_rate": 2.019622106620819e-06, + "loss": 0.8312, + "step": 8938 + }, + { + "epoch": 0.8004029324528513, + "grad_norm": 1.0434874446655396, + "learning_rate": 2.01787470687125e-06, + "loss": 0.8228, + "step": 8939 + }, + { + "epoch": 0.8004924729979294, + "grad_norm": 0.9616706510975945, + "learning_rate": 2.016127978552049e-06, + "loss": 0.825, + "step": 8940 + }, + { + "epoch": 0.8005820135430074, + "grad_norm": 1.0410328633357984, + "learning_rate": 2.014381921810147e-06, + "loss": 0.7771, + "step": 8941 + }, + { + "epoch": 0.8006715540880855, + "grad_norm": 0.9339190201088139, + "learning_rate": 2.012636536792413e-06, + "loss": 0.7539, + "step": 8942 + }, + { + "epoch": 0.8007610946331636, + "grad_norm": 0.9730528227189571, + "learning_rate": 2.0108918236456654e-06, + "loss": 0.8447, + "step": 8943 + }, + { + "epoch": 0.8008506351782416, + "grad_norm": 0.9509085097253794, + "learning_rate": 2.0091477825166637e-06, + "loss": 0.8135, + "step": 8944 + }, + { + "epoch": 0.8009401757233198, + "grad_norm": 1.0525816281768863, + "learning_rate": 2.007404413552112e-06, + "loss": 0.8386, + "step": 8945 + }, + { + "epoch": 0.8010297162683978, + "grad_norm": 0.94800814523983, + "learning_rate": 2.005661716898654e-06, + "loss": 0.8122, + "step": 8946 + }, + { + "epoch": 0.8011192568134758, + "grad_norm": 0.9973954804133057, + "learning_rate": 2.0039196927028813e-06, + "loss": 0.8486, + "step": 8947 + }, + { + "epoch": 0.8012087973585539, + "grad_norm": 0.9492069303956361, + "learning_rate": 2.002178341111327e-06, + "loss": 0.8136, + "step": 8948 + }, + { + "epoch": 0.801298337903632, + "grad_norm": 0.8953903843025304, + "learning_rate": 2.000437662270471e-06, + "loss": 0.7751, + "step": 8949 + }, + { + "epoch": 0.8013878784487101, + "grad_norm": 1.0461058352497297, + "learning_rate": 1.998697656326729e-06, + "loss": 0.7899, + "step": 8950 + }, + { + "epoch": 0.8014774189937881, + "grad_norm": 1.0657325396807649, + "learning_rate": 1.9969583234264635e-06, + "loss": 0.8365, + "step": 8951 + }, + { + "epoch": 0.8015669595388661, + "grad_norm": 1.0461092662547886, + "learning_rate": 1.9952196637159858e-06, + "loss": 0.7823, + "step": 8952 + }, + { + "epoch": 0.8016565000839443, + "grad_norm": 1.0027703698822077, + "learning_rate": 1.9934816773415457e-06, + "loss": 0.7849, + "step": 8953 + }, + { + "epoch": 0.8017460406290223, + "grad_norm": 0.912991787207638, + "learning_rate": 1.9917443644493352e-06, + "loss": 0.8102, + "step": 8954 + }, + { + "epoch": 0.8018355811741004, + "grad_norm": 0.9053533387917336, + "learning_rate": 1.9900077251854955e-06, + "loss": 0.8204, + "step": 8955 + }, + { + "epoch": 0.8019251217191785, + "grad_norm": 1.0362582077310218, + "learning_rate": 1.9882717596961e-06, + "loss": 0.836, + "step": 8956 + }, + { + "epoch": 0.8020146622642566, + "grad_norm": 0.9850006238838357, + "learning_rate": 1.986536468127175e-06, + "loss": 0.7874, + "step": 8957 + }, + { + "epoch": 0.8021042028093346, + "grad_norm": 1.1007564617007124, + "learning_rate": 1.9848018506246904e-06, + "loss": 0.7908, + "step": 8958 + }, + { + "epoch": 0.8021937433544126, + "grad_norm": 1.0173632481032941, + "learning_rate": 1.983067907334556e-06, + "loss": 0.7868, + "step": 8959 + }, + { + "epoch": 0.8022832838994908, + "grad_norm": 0.9528036035216374, + "learning_rate": 1.9813346384026266e-06, + "loss": 0.7655, + "step": 8960 + }, + { + "epoch": 0.8023728244445688, + "grad_norm": 0.8933264277553895, + "learning_rate": 1.9796020439746943e-06, + "loss": 0.7737, + "step": 8961 + }, + { + "epoch": 0.8024623649896468, + "grad_norm": 1.0618710977185855, + "learning_rate": 1.9778701241965017e-06, + "loss": 0.8419, + "step": 8962 + }, + { + "epoch": 0.802551905534725, + "grad_norm": 0.9342727698834351, + "learning_rate": 1.9761388792137303e-06, + "loss": 0.7727, + "step": 8963 + }, + { + "epoch": 0.802641446079803, + "grad_norm": 0.9471890502671254, + "learning_rate": 1.9744083091720113e-06, + "loss": 0.8067, + "step": 8964 + }, + { + "epoch": 0.8027309866248811, + "grad_norm": 0.9572770499155245, + "learning_rate": 1.972678414216912e-06, + "loss": 0.8307, + "step": 8965 + }, + { + "epoch": 0.8028205271699591, + "grad_norm": 1.0299877446627645, + "learning_rate": 1.9709491944939485e-06, + "loss": 0.7562, + "step": 8966 + }, + { + "epoch": 0.8029100677150373, + "grad_norm": 1.3289082813277708, + "learning_rate": 1.9692206501485724e-06, + "loss": 0.727, + "step": 8967 + }, + { + "epoch": 0.8029996082601153, + "grad_norm": 0.9556713289414934, + "learning_rate": 1.967492781326186e-06, + "loss": 0.8191, + "step": 8968 + }, + { + "epoch": 0.8030891488051933, + "grad_norm": 0.9903434912599169, + "learning_rate": 1.9657655881721272e-06, + "loss": 0.7727, + "step": 8969 + }, + { + "epoch": 0.8031786893502714, + "grad_norm": 0.9714167184849704, + "learning_rate": 1.964039070831689e-06, + "loss": 0.8093, + "step": 8970 + }, + { + "epoch": 0.8032682298953495, + "grad_norm": 0.9616262558505945, + "learning_rate": 1.9623132294501e-06, + "loss": 0.762, + "step": 8971 + }, + { + "epoch": 0.8033577704404276, + "grad_norm": 0.926812601022747, + "learning_rate": 1.9605880641725273e-06, + "loss": 0.7901, + "step": 8972 + }, + { + "epoch": 0.8034473109855056, + "grad_norm": 0.973963233507621, + "learning_rate": 1.958863575144089e-06, + "loss": 0.7921, + "step": 8973 + }, + { + "epoch": 0.8035368515305837, + "grad_norm": 0.9438660338460594, + "learning_rate": 1.957139762509842e-06, + "loss": 0.7852, + "step": 8974 + }, + { + "epoch": 0.8036263920756618, + "grad_norm": 1.0748574364098864, + "learning_rate": 1.955416626414787e-06, + "loss": 0.8176, + "step": 8975 + }, + { + "epoch": 0.8037159326207398, + "grad_norm": 1.0185709993695307, + "learning_rate": 1.9536941670038745e-06, + "loss": 0.8195, + "step": 8976 + }, + { + "epoch": 0.8038054731658179, + "grad_norm": 0.9936771906554822, + "learning_rate": 1.9519723844219875e-06, + "loss": 0.7944, + "step": 8977 + }, + { + "epoch": 0.803895013710896, + "grad_norm": 0.9189253310546502, + "learning_rate": 1.950251278813956e-06, + "loss": 0.8333, + "step": 8978 + }, + { + "epoch": 0.803984554255974, + "grad_norm": 0.9987581782225002, + "learning_rate": 1.948530850324556e-06, + "loss": 0.8034, + "step": 8979 + }, + { + "epoch": 0.8040740948010521, + "grad_norm": 1.0702214711120264, + "learning_rate": 1.946811099098502e-06, + "loss": 0.8843, + "step": 8980 + }, + { + "epoch": 0.8041636353461302, + "grad_norm": 0.9673717659861186, + "learning_rate": 1.9450920252804573e-06, + "loss": 0.7986, + "step": 8981 + }, + { + "epoch": 0.8042531758912083, + "grad_norm": 1.0194964070380141, + "learning_rate": 1.943373629015022e-06, + "loss": 0.8358, + "step": 8982 + }, + { + "epoch": 0.8043427164362863, + "grad_norm": 0.9341431057917803, + "learning_rate": 1.9416559104467425e-06, + "loss": 0.8095, + "step": 8983 + }, + { + "epoch": 0.8044322569813643, + "grad_norm": 0.9701940667830611, + "learning_rate": 1.939938869720108e-06, + "loss": 0.7714, + "step": 8984 + }, + { + "epoch": 0.8045217975264425, + "grad_norm": 0.9386588546553041, + "learning_rate": 1.9382225069795513e-06, + "loss": 0.7655, + "step": 8985 + }, + { + "epoch": 0.8046113380715205, + "grad_norm": 0.9701659143995255, + "learning_rate": 1.936506822369446e-06, + "loss": 0.7828, + "step": 8986 + }, + { + "epoch": 0.8047008786165986, + "grad_norm": 1.0617948837381164, + "learning_rate": 1.9347918160341105e-06, + "loss": 0.816, + "step": 8987 + }, + { + "epoch": 0.8047904191616766, + "grad_norm": 1.013032603969619, + "learning_rate": 1.9330774881178047e-06, + "loss": 0.7807, + "step": 8988 + }, + { + "epoch": 0.8048799597067547, + "grad_norm": 0.9618764284654682, + "learning_rate": 1.931363838764733e-06, + "loss": 0.8189, + "step": 8989 + }, + { + "epoch": 0.8049695002518328, + "grad_norm": 0.9992129156814863, + "learning_rate": 1.9296508681190416e-06, + "loss": 0.8257, + "step": 8990 + }, + { + "epoch": 0.8050590407969108, + "grad_norm": 1.023404451436432, + "learning_rate": 1.9279385763248214e-06, + "loss": 0.8043, + "step": 8991 + }, + { + "epoch": 0.805148581341989, + "grad_norm": 0.9402971998786305, + "learning_rate": 1.926226963526103e-06, + "loss": 0.793, + "step": 8992 + }, + { + "epoch": 0.805238121887067, + "grad_norm": 1.0251500827856768, + "learning_rate": 1.9245160298668632e-06, + "loss": 0.7668, + "step": 8993 + }, + { + "epoch": 0.805327662432145, + "grad_norm": 0.9440613142332002, + "learning_rate": 1.9228057754910177e-06, + "loss": 0.758, + "step": 8994 + }, + { + "epoch": 0.8054172029772231, + "grad_norm": 0.9957975700036773, + "learning_rate": 1.9210962005424305e-06, + "loss": 0.7904, + "step": 8995 + }, + { + "epoch": 0.8055067435223012, + "grad_norm": 1.0292565840136336, + "learning_rate": 1.9193873051649036e-06, + "loss": 0.7429, + "step": 8996 + }, + { + "epoch": 0.8055962840673793, + "grad_norm": 0.9651295273645711, + "learning_rate": 1.917679089502185e-06, + "loss": 0.7496, + "step": 8997 + }, + { + "epoch": 0.8056858246124573, + "grad_norm": 1.1209103157727258, + "learning_rate": 1.9159715536979628e-06, + "loss": 0.7708, + "step": 8998 + }, + { + "epoch": 0.8057753651575355, + "grad_norm": 0.9491936847010795, + "learning_rate": 1.91426469789587e-06, + "loss": 0.7895, + "step": 8999 + }, + { + "epoch": 0.8058649057026135, + "grad_norm": 0.9843853048397123, + "learning_rate": 1.9125585222394814e-06, + "loss": 0.8142, + "step": 9000 + }, + { + "epoch": 0.8059544462476915, + "grad_norm": 0.9248184534867555, + "learning_rate": 1.9108530268723167e-06, + "loss": 0.7868, + "step": 9001 + }, + { + "epoch": 0.8060439867927696, + "grad_norm": 2.4815782543065072, + "learning_rate": 1.9091482119378346e-06, + "loss": 0.7689, + "step": 9002 + }, + { + "epoch": 0.8061335273378477, + "grad_norm": 0.9641198330162245, + "learning_rate": 1.907444077579439e-06, + "loss": 0.805, + "step": 9003 + }, + { + "epoch": 0.8062230678829257, + "grad_norm": 0.9518216044462596, + "learning_rate": 1.9057406239404786e-06, + "loss": 0.7435, + "step": 9004 + }, + { + "epoch": 0.8063126084280038, + "grad_norm": 1.0207956289552649, + "learning_rate": 1.9040378511642355e-06, + "loss": 0.7873, + "step": 9005 + }, + { + "epoch": 0.8064021489730818, + "grad_norm": 0.9125418437638111, + "learning_rate": 1.9023357593939485e-06, + "loss": 0.7586, + "step": 9006 + }, + { + "epoch": 0.80649168951816, + "grad_norm": 0.898497349168295, + "learning_rate": 1.9006343487727896e-06, + "loss": 0.8054, + "step": 9007 + }, + { + "epoch": 0.806581230063238, + "grad_norm": 1.0471157932414012, + "learning_rate": 1.8989336194438756e-06, + "loss": 0.7878, + "step": 9008 + }, + { + "epoch": 0.806670770608316, + "grad_norm": 0.9772046484422434, + "learning_rate": 1.8972335715502687e-06, + "loss": 0.8302, + "step": 9009 + }, + { + "epoch": 0.8067603111533942, + "grad_norm": 0.8422422952886176, + "learning_rate": 1.895534205234968e-06, + "loss": 0.7769, + "step": 9010 + }, + { + "epoch": 0.8068498516984722, + "grad_norm": 0.9477424942326121, + "learning_rate": 1.8938355206409165e-06, + "loss": 0.8012, + "step": 9011 + }, + { + "epoch": 0.8069393922435503, + "grad_norm": 0.9926723351100647, + "learning_rate": 1.892137517911008e-06, + "loss": 0.8174, + "step": 9012 + }, + { + "epoch": 0.8070289327886283, + "grad_norm": 0.9384424732056108, + "learning_rate": 1.8904401971880703e-06, + "loss": 0.8092, + "step": 9013 + }, + { + "epoch": 0.8071184733337065, + "grad_norm": 1.1235009937124925, + "learning_rate": 1.8887435586148772e-06, + "loss": 0.8677, + "step": 9014 + }, + { + "epoch": 0.8072080138787845, + "grad_norm": 1.334879947944591, + "learning_rate": 1.8870476023341456e-06, + "loss": 0.7917, + "step": 9015 + }, + { + "epoch": 0.8072975544238625, + "grad_norm": 0.9836151490059016, + "learning_rate": 1.8853523284885289e-06, + "loss": 0.7931, + "step": 9016 + }, + { + "epoch": 0.8073870949689407, + "grad_norm": 1.1408229155960663, + "learning_rate": 1.88365773722063e-06, + "loss": 0.8078, + "step": 9017 + }, + { + "epoch": 0.8074766355140187, + "grad_norm": 0.9659798979190097, + "learning_rate": 1.8819638286729946e-06, + "loss": 0.8172, + "step": 9018 + }, + { + "epoch": 0.8075661760590968, + "grad_norm": 0.8996621295845219, + "learning_rate": 1.8802706029881091e-06, + "loss": 0.7165, + "step": 9019 + }, + { + "epoch": 0.8076557166041748, + "grad_norm": 0.8734692229072873, + "learning_rate": 1.8785780603084025e-06, + "loss": 0.7852, + "step": 9020 + }, + { + "epoch": 0.8077452571492529, + "grad_norm": 0.9943321898823613, + "learning_rate": 1.8768862007762412e-06, + "loss": 0.8056, + "step": 9021 + }, + { + "epoch": 0.807834797694331, + "grad_norm": 1.0360163371134286, + "learning_rate": 1.8751950245339423e-06, + "loss": 0.8224, + "step": 9022 + }, + { + "epoch": 0.807924338239409, + "grad_norm": 0.9718435555357828, + "learning_rate": 1.8735045317237587e-06, + "loss": 0.7754, + "step": 9023 + }, + { + "epoch": 0.808013878784487, + "grad_norm": 1.0950285025808022, + "learning_rate": 1.8718147224878957e-06, + "loss": 0.79, + "step": 9024 + }, + { + "epoch": 0.8081034193295652, + "grad_norm": 0.9394027106476904, + "learning_rate": 1.8701255969684894e-06, + "loss": 0.7703, + "step": 9025 + }, + { + "epoch": 0.8081929598746432, + "grad_norm": 0.9515404013027152, + "learning_rate": 1.8684371553076286e-06, + "loss": 0.8428, + "step": 9026 + }, + { + "epoch": 0.8082825004197213, + "grad_norm": 0.951663853325569, + "learning_rate": 1.8667493976473329e-06, + "loss": 0.798, + "step": 9027 + }, + { + "epoch": 0.8083720409647994, + "grad_norm": 0.9158310426768923, + "learning_rate": 1.8650623241295751e-06, + "loss": 0.7826, + "step": 9028 + }, + { + "epoch": 0.8084615815098775, + "grad_norm": 0.9809458921575934, + "learning_rate": 1.863375934896261e-06, + "loss": 0.8296, + "step": 9029 + }, + { + "epoch": 0.8085511220549555, + "grad_norm": 1.0488940449923219, + "learning_rate": 1.8616902300892525e-06, + "loss": 0.8786, + "step": 9030 + }, + { + "epoch": 0.8086406626000335, + "grad_norm": 0.9310478720524025, + "learning_rate": 1.8600052098503429e-06, + "loss": 0.7921, + "step": 9031 + }, + { + "epoch": 0.8087302031451117, + "grad_norm": 0.8923906876205239, + "learning_rate": 1.8583208743212667e-06, + "loss": 0.7494, + "step": 9032 + }, + { + "epoch": 0.8088197436901897, + "grad_norm": 1.0374518233457615, + "learning_rate": 1.856637223643708e-06, + "loss": 0.8167, + "step": 9033 + }, + { + "epoch": 0.8089092842352678, + "grad_norm": 0.9555493499064428, + "learning_rate": 1.8549542579592894e-06, + "loss": 0.7989, + "step": 9034 + }, + { + "epoch": 0.8089988247803459, + "grad_norm": 0.9618246492738148, + "learning_rate": 1.8532719774095754e-06, + "loss": 0.7885, + "step": 9035 + }, + { + "epoch": 0.8090883653254239, + "grad_norm": 1.0478558988006612, + "learning_rate": 1.8515903821360748e-06, + "loss": 0.7878, + "step": 9036 + }, + { + "epoch": 0.809177905870502, + "grad_norm": 1.00081799822429, + "learning_rate": 1.849909472280239e-06, + "loss": 0.8131, + "step": 9037 + }, + { + "epoch": 0.80926744641558, + "grad_norm": 0.9798296674399435, + "learning_rate": 1.8482292479834585e-06, + "loss": 0.7511, + "step": 9038 + }, + { + "epoch": 0.8093569869606582, + "grad_norm": 0.9522369483262472, + "learning_rate": 1.846549709387071e-06, + "loss": 0.8029, + "step": 9039 + }, + { + "epoch": 0.8094465275057362, + "grad_norm": 0.9777865284301476, + "learning_rate": 1.8448708566323504e-06, + "loss": 0.7802, + "step": 9040 + }, + { + "epoch": 0.8095360680508142, + "grad_norm": 1.0360109034449243, + "learning_rate": 1.84319268986052e-06, + "loss": 0.8556, + "step": 9041 + }, + { + "epoch": 0.8096256085958923, + "grad_norm": 0.9287199009580602, + "learning_rate": 1.8415152092127385e-06, + "loss": 0.8181, + "step": 9042 + }, + { + "epoch": 0.8097151491409704, + "grad_norm": 1.0905452087378134, + "learning_rate": 1.839838414830112e-06, + "loss": 0.7808, + "step": 9043 + }, + { + "epoch": 0.8098046896860485, + "grad_norm": 0.9269534373620009, + "learning_rate": 1.838162306853687e-06, + "loss": 0.7616, + "step": 9044 + }, + { + "epoch": 0.8098942302311265, + "grad_norm": 1.1089000055966205, + "learning_rate": 1.836486885424451e-06, + "loss": 0.8305, + "step": 9045 + }, + { + "epoch": 0.8099837707762046, + "grad_norm": 0.9528507633010177, + "learning_rate": 1.834812150683336e-06, + "loss": 0.7761, + "step": 9046 + }, + { + "epoch": 0.8100733113212827, + "grad_norm": 0.9565485973385509, + "learning_rate": 1.8331381027712148e-06, + "loss": 0.8461, + "step": 9047 + }, + { + "epoch": 0.8101628518663607, + "grad_norm": 1.0530314267042464, + "learning_rate": 1.8314647418289033e-06, + "loss": 0.8313, + "step": 9048 + }, + { + "epoch": 0.8102523924114388, + "grad_norm": 0.9849000516574142, + "learning_rate": 1.8297920679971593e-06, + "loss": 0.8424, + "step": 9049 + }, + { + "epoch": 0.8103419329565169, + "grad_norm": 0.8783724017762079, + "learning_rate": 1.8281200814166811e-06, + "loss": 0.7447, + "step": 9050 + }, + { + "epoch": 0.810431473501595, + "grad_norm": 0.9625116514655508, + "learning_rate": 1.8264487822281129e-06, + "loss": 0.8088, + "step": 9051 + }, + { + "epoch": 0.810521014046673, + "grad_norm": 0.8736516958671962, + "learning_rate": 1.8247781705720368e-06, + "loss": 0.7942, + "step": 9052 + }, + { + "epoch": 0.8106105545917511, + "grad_norm": 0.8781099315761819, + "learning_rate": 1.8231082465889816e-06, + "loss": 0.7582, + "step": 9053 + }, + { + "epoch": 0.8107000951368292, + "grad_norm": 0.9408665291923171, + "learning_rate": 1.8214390104194146e-06, + "loss": 0.776, + "step": 9054 + }, + { + "epoch": 0.8107896356819072, + "grad_norm": 1.0173987332719001, + "learning_rate": 1.819770462203746e-06, + "loss": 0.8246, + "step": 9055 + }, + { + "epoch": 0.8108791762269852, + "grad_norm": 0.8885261141706097, + "learning_rate": 1.818102602082329e-06, + "loss": 0.7424, + "step": 9056 + }, + { + "epoch": 0.8109687167720634, + "grad_norm": 0.9017281813579983, + "learning_rate": 1.816435430195459e-06, + "loss": 0.7791, + "step": 9057 + }, + { + "epoch": 0.8110582573171414, + "grad_norm": 0.9636264621245374, + "learning_rate": 1.8147689466833751e-06, + "loss": 0.8164, + "step": 9058 + }, + { + "epoch": 0.8111477978622195, + "grad_norm": 1.022273926864252, + "learning_rate": 1.8131031516862495e-06, + "loss": 0.8404, + "step": 9059 + }, + { + "epoch": 0.8112373384072975, + "grad_norm": 1.0339494915947232, + "learning_rate": 1.8114380453442104e-06, + "loss": 0.7785, + "step": 9060 + }, + { + "epoch": 0.8113268789523757, + "grad_norm": 1.0753261623958086, + "learning_rate": 1.8097736277973189e-06, + "loss": 0.7878, + "step": 9061 + }, + { + "epoch": 0.8114164194974537, + "grad_norm": 0.9721020292082916, + "learning_rate": 1.8081098991855806e-06, + "loss": 0.8314, + "step": 9062 + }, + { + "epoch": 0.8115059600425317, + "grad_norm": 1.0037477020254262, + "learning_rate": 1.8064468596489427e-06, + "loss": 0.8409, + "step": 9063 + }, + { + "epoch": 0.8115955005876099, + "grad_norm": 1.0850523193778836, + "learning_rate": 1.8047845093272964e-06, + "loss": 0.7395, + "step": 9064 + }, + { + "epoch": 0.8116850411326879, + "grad_norm": 0.9214504427182194, + "learning_rate": 1.8031228483604668e-06, + "loss": 0.7985, + "step": 9065 + }, + { + "epoch": 0.811774581677766, + "grad_norm": 0.9515984446943759, + "learning_rate": 1.8014618768882341e-06, + "loss": 0.8172, + "step": 9066 + }, + { + "epoch": 0.811864122222844, + "grad_norm": 0.9326935235062704, + "learning_rate": 1.7998015950503124e-06, + "loss": 0.7632, + "step": 9067 + }, + { + "epoch": 0.8119536627679221, + "grad_norm": 0.9241165834407706, + "learning_rate": 1.7981420029863583e-06, + "loss": 0.7857, + "step": 9068 + }, + { + "epoch": 0.8120432033130002, + "grad_norm": 1.0706026999787563, + "learning_rate": 1.796483100835974e-06, + "loss": 0.7949, + "step": 9069 + }, + { + "epoch": 0.8121327438580782, + "grad_norm": 1.009278519007451, + "learning_rate": 1.7948248887386953e-06, + "loss": 0.8273, + "step": 9070 + }, + { + "epoch": 0.8122222844031564, + "grad_norm": 0.9863841231043998, + "learning_rate": 1.7931673668340067e-06, + "loss": 0.8525, + "step": 9071 + }, + { + "epoch": 0.8123118249482344, + "grad_norm": 0.9207652243726682, + "learning_rate": 1.7915105352613382e-06, + "loss": 0.8076, + "step": 9072 + }, + { + "epoch": 0.8124013654933124, + "grad_norm": 1.039691479378543, + "learning_rate": 1.7898543941600545e-06, + "loss": 0.7804, + "step": 9073 + }, + { + "epoch": 0.8124909060383905, + "grad_norm": 1.023316502493222, + "learning_rate": 1.7881989436694647e-06, + "loss": 0.7553, + "step": 9074 + }, + { + "epoch": 0.8125804465834686, + "grad_norm": 1.0037677411105437, + "learning_rate": 1.7865441839288223e-06, + "loss": 0.8536, + "step": 9075 + }, + { + "epoch": 0.8126699871285467, + "grad_norm": 1.1567209641057226, + "learning_rate": 1.7848901150773158e-06, + "loss": 0.792, + "step": 9076 + }, + { + "epoch": 0.8127595276736247, + "grad_norm": 1.0149760458111703, + "learning_rate": 1.7832367372540782e-06, + "loss": 0.8372, + "step": 9077 + }, + { + "epoch": 0.8128490682187027, + "grad_norm": 1.018290762249544, + "learning_rate": 1.7815840505981941e-06, + "loss": 0.8011, + "step": 9078 + }, + { + "epoch": 0.8129386087637809, + "grad_norm": 0.9643589252719816, + "learning_rate": 1.7799320552486787e-06, + "loss": 0.7837, + "step": 9079 + }, + { + "epoch": 0.8130281493088589, + "grad_norm": 1.0683162125501195, + "learning_rate": 1.7782807513444933e-06, + "loss": 0.8417, + "step": 9080 + }, + { + "epoch": 0.813117689853937, + "grad_norm": 1.04389470365152, + "learning_rate": 1.7766301390245367e-06, + "loss": 0.8626, + "step": 9081 + }, + { + "epoch": 0.8132072303990151, + "grad_norm": 0.9898304079679849, + "learning_rate": 1.7749802184276565e-06, + "loss": 0.8385, + "step": 9082 + }, + { + "epoch": 0.8132967709440931, + "grad_norm": 1.1054341022626595, + "learning_rate": 1.7733309896926331e-06, + "loss": 0.8031, + "step": 9083 + }, + { + "epoch": 0.8133863114891712, + "grad_norm": 0.9326003788303517, + "learning_rate": 1.7716824529582022e-06, + "loss": 0.7452, + "step": 9084 + }, + { + "epoch": 0.8134758520342492, + "grad_norm": 0.9437263567551972, + "learning_rate": 1.7700346083630294e-06, + "loss": 0.8014, + "step": 9085 + }, + { + "epoch": 0.8135653925793274, + "grad_norm": 1.09413995171599, + "learning_rate": 1.7683874560457293e-06, + "loss": 0.6972, + "step": 9086 + }, + { + "epoch": 0.8136549331244054, + "grad_norm": 0.9299337256106801, + "learning_rate": 1.766740996144849e-06, + "loss": 0.8263, + "step": 9087 + }, + { + "epoch": 0.8137444736694834, + "grad_norm": 0.9965748048985237, + "learning_rate": 1.7650952287988864e-06, + "loss": 0.7311, + "step": 9088 + }, + { + "epoch": 0.8138340142145616, + "grad_norm": 1.0780259608646732, + "learning_rate": 1.763450154146279e-06, + "loss": 0.7629, + "step": 9089 + }, + { + "epoch": 0.8139235547596396, + "grad_norm": 1.0536936232897605, + "learning_rate": 1.7618057723254e-06, + "loss": 0.811, + "step": 9090 + }, + { + "epoch": 0.8140130953047177, + "grad_norm": 0.950342848517687, + "learning_rate": 1.7601620834745791e-06, + "loss": 0.785, + "step": 9091 + }, + { + "epoch": 0.8141026358497957, + "grad_norm": 0.9795322908673348, + "learning_rate": 1.7585190877320712e-06, + "loss": 0.8134, + "step": 9092 + }, + { + "epoch": 0.8141921763948738, + "grad_norm": 0.9764738213255899, + "learning_rate": 1.7568767852360802e-06, + "loss": 0.8177, + "step": 9093 + }, + { + "epoch": 0.8142817169399519, + "grad_norm": 0.9857086552388424, + "learning_rate": 1.7552351761247521e-06, + "loss": 0.8754, + "step": 9094 + }, + { + "epoch": 0.8143712574850299, + "grad_norm": 1.059198494810535, + "learning_rate": 1.7535942605361733e-06, + "loss": 0.8001, + "step": 9095 + }, + { + "epoch": 0.814460798030108, + "grad_norm": 1.0463127052209766, + "learning_rate": 1.751954038608371e-06, + "loss": 0.8165, + "step": 9096 + }, + { + "epoch": 0.8145503385751861, + "grad_norm": 1.0947461984123277, + "learning_rate": 1.7503145104793219e-06, + "loss": 0.7826, + "step": 9097 + }, + { + "epoch": 0.8146398791202641, + "grad_norm": 0.9464998720916529, + "learning_rate": 1.7486756762869294e-06, + "loss": 0.7874, + "step": 9098 + }, + { + "epoch": 0.8147294196653422, + "grad_norm": 1.0015918885181458, + "learning_rate": 1.7470375361690516e-06, + "loss": 0.7692, + "step": 9099 + }, + { + "epoch": 0.8148189602104203, + "grad_norm": 1.0306190451817843, + "learning_rate": 1.7454000902634827e-06, + "loss": 0.7904, + "step": 9100 + }, + { + "epoch": 0.8149085007554984, + "grad_norm": 0.9261621358196472, + "learning_rate": 1.7437633387079577e-06, + "loss": 0.7835, + "step": 9101 + }, + { + "epoch": 0.8149980413005764, + "grad_norm": 0.9538858836129114, + "learning_rate": 1.7421272816401557e-06, + "loss": 0.807, + "step": 9102 + }, + { + "epoch": 0.8150875818456544, + "grad_norm": 0.9270530209460515, + "learning_rate": 1.7404919191976976e-06, + "loss": 0.8181, + "step": 9103 + }, + { + "epoch": 0.8151771223907326, + "grad_norm": 1.117927887546288, + "learning_rate": 1.7388572515181445e-06, + "loss": 0.8074, + "step": 9104 + }, + { + "epoch": 0.8152666629358106, + "grad_norm": 1.0353780028344353, + "learning_rate": 1.7372232787389986e-06, + "loss": 0.8107, + "step": 9105 + }, + { + "epoch": 0.8153562034808887, + "grad_norm": 0.8845052714273995, + "learning_rate": 1.7355900009977033e-06, + "loss": 0.8136, + "step": 9106 + }, + { + "epoch": 0.8154457440259668, + "grad_norm": 0.9914004997255265, + "learning_rate": 1.7339574184316477e-06, + "loss": 0.7549, + "step": 9107 + }, + { + "epoch": 0.8155352845710448, + "grad_norm": 0.9340670857185971, + "learning_rate": 1.7323255311781561e-06, + "loss": 0.7961, + "step": 9108 + }, + { + "epoch": 0.8156248251161229, + "grad_norm": 1.0394660673709044, + "learning_rate": 1.730694339374499e-06, + "loss": 0.8025, + "step": 9109 + }, + { + "epoch": 0.8157143656612009, + "grad_norm": 1.0395710288181919, + "learning_rate": 1.7290638431578877e-06, + "loss": 0.7955, + "step": 9110 + }, + { + "epoch": 0.8158039062062791, + "grad_norm": 0.9526695488679436, + "learning_rate": 1.7274340426654723e-06, + "loss": 0.7381, + "step": 9111 + }, + { + "epoch": 0.8158934467513571, + "grad_norm": 1.0950757537838844, + "learning_rate": 1.7258049380343478e-06, + "loss": 0.789, + "step": 9112 + }, + { + "epoch": 0.8159829872964351, + "grad_norm": 0.9263183840058052, + "learning_rate": 1.724176529401549e-06, + "loss": 0.8154, + "step": 9113 + }, + { + "epoch": 0.8160725278415132, + "grad_norm": 0.9414962992120856, + "learning_rate": 1.7225488169040517e-06, + "loss": 0.8146, + "step": 9114 + }, + { + "epoch": 0.8161620683865913, + "grad_norm": 1.1476430170162337, + "learning_rate": 1.7209218006787743e-06, + "loss": 0.8504, + "step": 9115 + }, + { + "epoch": 0.8162516089316694, + "grad_norm": 0.9565402618708234, + "learning_rate": 1.7192954808625761e-06, + "loss": 0.8439, + "step": 9116 + }, + { + "epoch": 0.8163411494767474, + "grad_norm": 0.9676346829665454, + "learning_rate": 1.7176698575922578e-06, + "loss": 0.8177, + "step": 9117 + }, + { + "epoch": 0.8164306900218256, + "grad_norm": 1.056012494171971, + "learning_rate": 1.7160449310045647e-06, + "loss": 0.8021, + "step": 9118 + }, + { + "epoch": 0.8165202305669036, + "grad_norm": 0.8938925752786546, + "learning_rate": 1.7144207012361702e-06, + "loss": 0.7927, + "step": 9119 + }, + { + "epoch": 0.8166097711119816, + "grad_norm": 1.0012587382378806, + "learning_rate": 1.7127971684237098e-06, + "loss": 0.769, + "step": 9120 + }, + { + "epoch": 0.8166993116570597, + "grad_norm": 0.9422885751322433, + "learning_rate": 1.7111743327037456e-06, + "loss": 0.7889, + "step": 9121 + }, + { + "epoch": 0.8167888522021378, + "grad_norm": 1.0644087579372201, + "learning_rate": 1.7095521942127858e-06, + "loss": 0.8156, + "step": 9122 + }, + { + "epoch": 0.8168783927472159, + "grad_norm": 1.037733722579703, + "learning_rate": 1.7079307530872802e-06, + "loss": 0.7964, + "step": 9123 + }, + { + "epoch": 0.8169679332922939, + "grad_norm": 1.3007389805184877, + "learning_rate": 1.7063100094636197e-06, + "loss": 0.7785, + "step": 9124 + }, + { + "epoch": 0.817057473837372, + "grad_norm": 1.0102029791112401, + "learning_rate": 1.7046899634781288e-06, + "loss": 0.841, + "step": 9125 + }, + { + "epoch": 0.8171470143824501, + "grad_norm": 0.9301832897170735, + "learning_rate": 1.7030706152670905e-06, + "loss": 0.8352, + "step": 9126 + }, + { + "epoch": 0.8172365549275281, + "grad_norm": 0.8942958971853152, + "learning_rate": 1.7014519649667138e-06, + "loss": 0.7373, + "step": 9127 + }, + { + "epoch": 0.8173260954726062, + "grad_norm": 0.9558940281828195, + "learning_rate": 1.699834012713155e-06, + "loss": 0.824, + "step": 9128 + }, + { + "epoch": 0.8174156360176843, + "grad_norm": 1.0510158365875901, + "learning_rate": 1.6982167586425146e-06, + "loss": 0.8194, + "step": 9129 + }, + { + "epoch": 0.8175051765627623, + "grad_norm": 0.98709440994425, + "learning_rate": 1.6966002028908246e-06, + "loss": 0.7975, + "step": 9130 + }, + { + "epoch": 0.8175947171078404, + "grad_norm": 1.0226995747486753, + "learning_rate": 1.694984345594065e-06, + "loss": 0.8143, + "step": 9131 + }, + { + "epoch": 0.8176842576529184, + "grad_norm": 0.9771757651457715, + "learning_rate": 1.6933691868881608e-06, + "loss": 0.8534, + "step": 9132 + }, + { + "epoch": 0.8177737981979966, + "grad_norm": 0.8734747723253398, + "learning_rate": 1.6917547269089717e-06, + "loss": 0.7403, + "step": 9133 + }, + { + "epoch": 0.8178633387430746, + "grad_norm": 1.0412913925180924, + "learning_rate": 1.6901409657923006e-06, + "loss": 0.7687, + "step": 9134 + }, + { + "epoch": 0.8179528792881526, + "grad_norm": 0.9167815390618094, + "learning_rate": 1.6885279036738944e-06, + "loss": 0.8025, + "step": 9135 + }, + { + "epoch": 0.8180424198332308, + "grad_norm": 1.0294977935043785, + "learning_rate": 1.6869155406894344e-06, + "loss": 0.784, + "step": 9136 + }, + { + "epoch": 0.8181319603783088, + "grad_norm": 1.1020025788532832, + "learning_rate": 1.6853038769745466e-06, + "loss": 0.8073, + "step": 9137 + }, + { + "epoch": 0.8182215009233869, + "grad_norm": 0.9707815393568654, + "learning_rate": 1.683692912664805e-06, + "loss": 0.7648, + "step": 9138 + }, + { + "epoch": 0.8183110414684649, + "grad_norm": 0.9603154102121777, + "learning_rate": 1.6820826478957143e-06, + "loss": 0.8094, + "step": 9139 + }, + { + "epoch": 0.818400582013543, + "grad_norm": 0.9114923130754732, + "learning_rate": 1.6804730828027272e-06, + "loss": 0.7777, + "step": 9140 + }, + { + "epoch": 0.8184901225586211, + "grad_norm": 1.0943239557510362, + "learning_rate": 1.6788642175212321e-06, + "loss": 0.7878, + "step": 9141 + }, + { + "epoch": 0.8185796631036991, + "grad_norm": 0.9574895839061504, + "learning_rate": 1.6772560521865633e-06, + "loss": 0.815, + "step": 9142 + }, + { + "epoch": 0.8186692036487773, + "grad_norm": 0.8948124875995853, + "learning_rate": 1.6756485869339933e-06, + "loss": 0.7436, + "step": 9143 + }, + { + "epoch": 0.8187587441938553, + "grad_norm": 0.9198239299965093, + "learning_rate": 1.6740418218987354e-06, + "loss": 0.8164, + "step": 9144 + }, + { + "epoch": 0.8188482847389333, + "grad_norm": 0.891341362014982, + "learning_rate": 1.67243575721595e-06, + "loss": 0.7542, + "step": 9145 + }, + { + "epoch": 0.8189378252840114, + "grad_norm": 0.9044440709544029, + "learning_rate": 1.6708303930207337e-06, + "loss": 0.812, + "step": 9146 + }, + { + "epoch": 0.8190273658290895, + "grad_norm": 0.9199080611609968, + "learning_rate": 1.6692257294481208e-06, + "loss": 0.8108, + "step": 9147 + }, + { + "epoch": 0.8191169063741676, + "grad_norm": 0.9429174098182886, + "learning_rate": 1.6676217666330907e-06, + "loss": 0.801, + "step": 9148 + }, + { + "epoch": 0.8192064469192456, + "grad_norm": 1.0290953756465717, + "learning_rate": 1.666018504710566e-06, + "loss": 0.8494, + "step": 9149 + }, + { + "epoch": 0.8192959874643236, + "grad_norm": 1.0138900284964079, + "learning_rate": 1.664415943815404e-06, + "loss": 0.8642, + "step": 9150 + }, + { + "epoch": 0.8193855280094018, + "grad_norm": 1.0057291841627611, + "learning_rate": 1.6628140840824147e-06, + "loss": 0.7483, + "step": 9151 + }, + { + "epoch": 0.8194750685544798, + "grad_norm": 0.9543478609799284, + "learning_rate": 1.6612129256463338e-06, + "loss": 0.8043, + "step": 9152 + }, + { + "epoch": 0.8195646090995579, + "grad_norm": 0.9841818418448113, + "learning_rate": 1.659612468641847e-06, + "loss": 0.817, + "step": 9153 + }, + { + "epoch": 0.819654149644636, + "grad_norm": 0.9571140494556872, + "learning_rate": 1.6580127132035817e-06, + "loss": 0.7799, + "step": 9154 + }, + { + "epoch": 0.819743690189714, + "grad_norm": 1.0088624085943356, + "learning_rate": 1.6564136594661017e-06, + "loss": 0.8152, + "step": 9155 + }, + { + "epoch": 0.8198332307347921, + "grad_norm": 0.9464452231263504, + "learning_rate": 1.654815307563914e-06, + "loss": 0.7438, + "step": 9156 + }, + { + "epoch": 0.8199227712798701, + "grad_norm": 1.0144955586733013, + "learning_rate": 1.653217657631473e-06, + "loss": 0.7847, + "step": 9157 + }, + { + "epoch": 0.8200123118249483, + "grad_norm": 0.9768462844772362, + "learning_rate": 1.65162070980316e-06, + "loss": 0.7693, + "step": 9158 + }, + { + "epoch": 0.8201018523700263, + "grad_norm": 1.0884047583704985, + "learning_rate": 1.6500244642133078e-06, + "loss": 0.7825, + "step": 9159 + }, + { + "epoch": 0.8201913929151043, + "grad_norm": 0.9339344409165125, + "learning_rate": 1.6484289209961879e-06, + "loss": 0.8146, + "step": 9160 + }, + { + "epoch": 0.8202809334601825, + "grad_norm": 0.9068256653221051, + "learning_rate": 1.6468340802860117e-06, + "loss": 0.7639, + "step": 9161 + }, + { + "epoch": 0.8203704740052605, + "grad_norm": 0.9222521094481316, + "learning_rate": 1.645239942216933e-06, + "loss": 0.7643, + "step": 9162 + }, + { + "epoch": 0.8204600145503386, + "grad_norm": 1.0492799877752386, + "learning_rate": 1.6436465069230433e-06, + "loss": 0.8327, + "step": 9163 + }, + { + "epoch": 0.8205495550954166, + "grad_norm": 1.1293354754093645, + "learning_rate": 1.6420537745383792e-06, + "loss": 0.7911, + "step": 9164 + }, + { + "epoch": 0.8206390956404948, + "grad_norm": 0.947684421848324, + "learning_rate": 1.6404617451969164e-06, + "loss": 0.8406, + "step": 9165 + }, + { + "epoch": 0.8207286361855728, + "grad_norm": 0.9300337340114597, + "learning_rate": 1.6388704190325689e-06, + "loss": 0.7727, + "step": 9166 + }, + { + "epoch": 0.8208181767306508, + "grad_norm": 1.0567045786637472, + "learning_rate": 1.6372797961791963e-06, + "loss": 0.7541, + "step": 9167 + }, + { + "epoch": 0.8209077172757289, + "grad_norm": 1.1165041998293563, + "learning_rate": 1.6356898767705954e-06, + "loss": 0.8368, + "step": 9168 + }, + { + "epoch": 0.820997257820807, + "grad_norm": 0.9232689996094305, + "learning_rate": 1.6341006609405052e-06, + "loss": 0.7968, + "step": 9169 + }, + { + "epoch": 0.821086798365885, + "grad_norm": 1.0159918299533541, + "learning_rate": 1.6325121488226048e-06, + "loss": 0.8167, + "step": 9170 + }, + { + "epoch": 0.8211763389109631, + "grad_norm": 0.9505530199345926, + "learning_rate": 1.630924340550516e-06, + "loss": 0.8125, + "step": 9171 + }, + { + "epoch": 0.8212658794560412, + "grad_norm": 1.0239086428024038, + "learning_rate": 1.6293372362577987e-06, + "loss": 0.744, + "step": 9172 + }, + { + "epoch": 0.8213554200011193, + "grad_norm": 0.9055839607828072, + "learning_rate": 1.627750836077956e-06, + "loss": 0.7712, + "step": 9173 + }, + { + "epoch": 0.8214449605461973, + "grad_norm": 0.9687670522957229, + "learning_rate": 1.62616514014443e-06, + "loss": 0.8063, + "step": 9174 + }, + { + "epoch": 0.8215345010912753, + "grad_norm": 0.960832720858117, + "learning_rate": 1.6245801485906054e-06, + "loss": 0.8012, + "step": 9175 + }, + { + "epoch": 0.8216240416363535, + "grad_norm": 0.9516673183138459, + "learning_rate": 1.6229958615498054e-06, + "loss": 0.7827, + "step": 9176 + }, + { + "epoch": 0.8217135821814315, + "grad_norm": 0.9873237747377506, + "learning_rate": 1.6214122791552944e-06, + "loss": 0.7949, + "step": 9177 + }, + { + "epoch": 0.8218031227265096, + "grad_norm": 0.9839296072803839, + "learning_rate": 1.6198294015402827e-06, + "loss": 0.793, + "step": 9178 + }, + { + "epoch": 0.8218926632715877, + "grad_norm": 1.0397672912973064, + "learning_rate": 1.618247228837908e-06, + "loss": 0.8768, + "step": 9179 + }, + { + "epoch": 0.8219822038166658, + "grad_norm": 0.9561157259825637, + "learning_rate": 1.6166657611812654e-06, + "loss": 0.8666, + "step": 9180 + }, + { + "epoch": 0.8220717443617438, + "grad_norm": 1.2394992987577216, + "learning_rate": 1.6150849987033802e-06, + "loss": 0.8312, + "step": 9181 + }, + { + "epoch": 0.8221612849068218, + "grad_norm": 1.0349530451013844, + "learning_rate": 1.6135049415372195e-06, + "loss": 0.7656, + "step": 9182 + }, + { + "epoch": 0.8222508254519, + "grad_norm": 1.0151965663059215, + "learning_rate": 1.611925589815696e-06, + "loss": 0.7905, + "step": 9183 + }, + { + "epoch": 0.822340365996978, + "grad_norm": 0.9846615685850826, + "learning_rate": 1.610346943671659e-06, + "loss": 0.766, + "step": 9184 + }, + { + "epoch": 0.822429906542056, + "grad_norm": 0.9091793031559229, + "learning_rate": 1.6087690032378933e-06, + "loss": 0.7719, + "step": 9185 + }, + { + "epoch": 0.8225194470871341, + "grad_norm": 1.0666489614879002, + "learning_rate": 1.6071917686471362e-06, + "loss": 0.8238, + "step": 9186 + }, + { + "epoch": 0.8226089876322122, + "grad_norm": 1.0723383842729917, + "learning_rate": 1.605615240032059e-06, + "loss": 0.7847, + "step": 9187 + }, + { + "epoch": 0.8226985281772903, + "grad_norm": 0.9485737636242153, + "learning_rate": 1.6040394175252716e-06, + "loss": 0.8309, + "step": 9188 + }, + { + "epoch": 0.8227880687223683, + "grad_norm": 1.0675102720548943, + "learning_rate": 1.6024643012593322e-06, + "loss": 0.7813, + "step": 9189 + }, + { + "epoch": 0.8228776092674465, + "grad_norm": 1.0372239350562886, + "learning_rate": 1.600889891366727e-06, + "loss": 0.7881, + "step": 9190 + }, + { + "epoch": 0.8229671498125245, + "grad_norm": 0.9858053192255403, + "learning_rate": 1.5993161879798946e-06, + "loss": 0.7443, + "step": 9191 + }, + { + "epoch": 0.8230566903576025, + "grad_norm": 0.9889827557822123, + "learning_rate": 1.597743191231207e-06, + "loss": 0.7353, + "step": 9192 + }, + { + "epoch": 0.8231462309026806, + "grad_norm": 1.0491242341336773, + "learning_rate": 1.5961709012529836e-06, + "loss": 0.8253, + "step": 9193 + }, + { + "epoch": 0.8232357714477587, + "grad_norm": 1.1062179401072145, + "learning_rate": 1.5945993181774788e-06, + "loss": 0.828, + "step": 9194 + }, + { + "epoch": 0.8233253119928368, + "grad_norm": 1.1394212359660891, + "learning_rate": 1.5930284421368914e-06, + "loss": 0.7919, + "step": 9195 + }, + { + "epoch": 0.8234148525379148, + "grad_norm": 0.9651201321965137, + "learning_rate": 1.5914582732633521e-06, + "loss": 0.8341, + "step": 9196 + }, + { + "epoch": 0.823504393082993, + "grad_norm": 1.0505817915242417, + "learning_rate": 1.5898888116889433e-06, + "loss": 0.8397, + "step": 9197 + }, + { + "epoch": 0.823593933628071, + "grad_norm": 0.9858376974959439, + "learning_rate": 1.588320057545678e-06, + "loss": 0.8039, + "step": 9198 + }, + { + "epoch": 0.823683474173149, + "grad_norm": 1.045461343998573, + "learning_rate": 1.586752010965521e-06, + "loss": 0.7997, + "step": 9199 + }, + { + "epoch": 0.8237730147182271, + "grad_norm": 0.890178143421997, + "learning_rate": 1.585184672080371e-06, + "loss": 0.8287, + "step": 9200 + }, + { + "epoch": 0.8238625552633052, + "grad_norm": 1.1799860808709588, + "learning_rate": 1.5836180410220625e-06, + "loss": 0.809, + "step": 9201 + }, + { + "epoch": 0.8239520958083832, + "grad_norm": 1.0470790376313244, + "learning_rate": 1.582052117922378e-06, + "loss": 0.7813, + "step": 9202 + }, + { + "epoch": 0.8240416363534613, + "grad_norm": 0.9427023414271469, + "learning_rate": 1.5804869029130376e-06, + "loss": 0.817, + "step": 9203 + }, + { + "epoch": 0.8241311768985393, + "grad_norm": 0.9368987079816568, + "learning_rate": 1.5789223961257005e-06, + "loss": 0.7696, + "step": 9204 + }, + { + "epoch": 0.8242207174436175, + "grad_norm": 1.005571873751868, + "learning_rate": 1.5773585976919715e-06, + "loss": 0.7678, + "step": 9205 + }, + { + "epoch": 0.8243102579886955, + "grad_norm": 1.249774771628386, + "learning_rate": 1.5757955077433929e-06, + "loss": 0.7995, + "step": 9206 + }, + { + "epoch": 0.8243997985337735, + "grad_norm": 0.9776102026288237, + "learning_rate": 1.5742331264114418e-06, + "loss": 0.7944, + "step": 9207 + }, + { + "epoch": 0.8244893390788517, + "grad_norm": 0.9775295456228488, + "learning_rate": 1.5726714538275422e-06, + "loss": 0.8154, + "step": 9208 + }, + { + "epoch": 0.8245788796239297, + "grad_norm": 0.9944785496211577, + "learning_rate": 1.5711104901230589e-06, + "loss": 0.8113, + "step": 9209 + }, + { + "epoch": 0.8246684201690078, + "grad_norm": 1.0221743521165492, + "learning_rate": 1.5695502354292913e-06, + "loss": 0.825, + "step": 9210 + }, + { + "epoch": 0.8247579607140858, + "grad_norm": 0.9390009504352447, + "learning_rate": 1.56799068987749e-06, + "loss": 0.7913, + "step": 9211 + }, + { + "epoch": 0.824847501259164, + "grad_norm": 1.06663363657489, + "learning_rate": 1.5664318535988322e-06, + "loss": 0.8245, + "step": 9212 + }, + { + "epoch": 0.824937041804242, + "grad_norm": 0.9765250631641107, + "learning_rate": 1.564873726724444e-06, + "loss": 0.7851, + "step": 9213 + }, + { + "epoch": 0.82502658234932, + "grad_norm": 1.1271073533720082, + "learning_rate": 1.563316309385391e-06, + "loss": 0.832, + "step": 9214 + }, + { + "epoch": 0.8251161228943982, + "grad_norm": 0.8825484903561781, + "learning_rate": 1.561759601712677e-06, + "loss": 0.775, + "step": 9215 + }, + { + "epoch": 0.8252056634394762, + "grad_norm": 0.9666564524882509, + "learning_rate": 1.5602036038372448e-06, + "loss": 0.7703, + "step": 9216 + }, + { + "epoch": 0.8252952039845542, + "grad_norm": 0.9592847466797919, + "learning_rate": 1.558648315889988e-06, + "loss": 0.7733, + "step": 9217 + }, + { + "epoch": 0.8253847445296323, + "grad_norm": 1.0453895211312276, + "learning_rate": 1.5570937380017248e-06, + "loss": 0.7985, + "step": 9218 + }, + { + "epoch": 0.8254742850747104, + "grad_norm": 1.0088715171851086, + "learning_rate": 1.5555398703032232e-06, + "loss": 0.8167, + "step": 9219 + }, + { + "epoch": 0.8255638256197885, + "grad_norm": 1.1091935613251864, + "learning_rate": 1.5539867129251895e-06, + "loss": 0.7815, + "step": 9220 + }, + { + "epoch": 0.8256533661648665, + "grad_norm": 0.9867309990735131, + "learning_rate": 1.5524342659982705e-06, + "loss": 0.8135, + "step": 9221 + }, + { + "epoch": 0.8257429067099445, + "grad_norm": 1.037690460207771, + "learning_rate": 1.5508825296530538e-06, + "loss": 0.8167, + "step": 9222 + }, + { + "epoch": 0.8258324472550227, + "grad_norm": 1.1443965799166527, + "learning_rate": 1.549331504020064e-06, + "loss": 0.7607, + "step": 9223 + }, + { + "epoch": 0.8259219878001007, + "grad_norm": 0.9857718855950449, + "learning_rate": 1.5477811892297711e-06, + "loss": 0.8073, + "step": 9224 + }, + { + "epoch": 0.8260115283451788, + "grad_norm": 0.8953967349383639, + "learning_rate": 1.5462315854125809e-06, + "loss": 0.7925, + "step": 9225 + }, + { + "epoch": 0.8261010688902569, + "grad_norm": 1.1471323468408094, + "learning_rate": 1.5446826926988413e-06, + "loss": 0.79, + "step": 9226 + }, + { + "epoch": 0.826190609435335, + "grad_norm": 0.9559289844372381, + "learning_rate": 1.54313451121884e-06, + "loss": 0.7574, + "step": 9227 + }, + { + "epoch": 0.826280149980413, + "grad_norm": 0.9314018233105323, + "learning_rate": 1.5415870411028055e-06, + "loss": 0.8101, + "step": 9228 + }, + { + "epoch": 0.826369690525491, + "grad_norm": 1.0730597275060598, + "learning_rate": 1.5400402824809058e-06, + "loss": 0.8546, + "step": 9229 + }, + { + "epoch": 0.8264592310705692, + "grad_norm": 1.0304056660382788, + "learning_rate": 1.538494235483249e-06, + "loss": 0.8124, + "step": 9230 + }, + { + "epoch": 0.8265487716156472, + "grad_norm": 1.0031773331721223, + "learning_rate": 1.536948900239883e-06, + "loss": 0.8088, + "step": 9231 + }, + { + "epoch": 0.8266383121607253, + "grad_norm": 2.237930828070287, + "learning_rate": 1.5354042768807976e-06, + "loss": 0.7928, + "step": 9232 + }, + { + "epoch": 0.8267278527058034, + "grad_norm": 1.012665118530479, + "learning_rate": 1.5338603655359196e-06, + "loss": 0.7512, + "step": 9233 + }, + { + "epoch": 0.8268173932508814, + "grad_norm": 1.0529608926019303, + "learning_rate": 1.53231716633512e-06, + "loss": 0.8361, + "step": 9234 + }, + { + "epoch": 0.8269069337959595, + "grad_norm": 0.9594525097366378, + "learning_rate": 1.5307746794082067e-06, + "loss": 0.7584, + "step": 9235 + }, + { + "epoch": 0.8269964743410375, + "grad_norm": 0.9729025477307098, + "learning_rate": 1.5292329048849286e-06, + "loss": 0.8067, + "step": 9236 + }, + { + "epoch": 0.8270860148861157, + "grad_norm": 0.9590582861006676, + "learning_rate": 1.527691842894975e-06, + "loss": 0.8043, + "step": 9237 + }, + { + "epoch": 0.8271755554311937, + "grad_norm": 0.9811386062725952, + "learning_rate": 1.5261514935679743e-06, + "loss": 0.8501, + "step": 9238 + }, + { + "epoch": 0.8272650959762717, + "grad_norm": 0.9329749402570326, + "learning_rate": 1.5246118570334967e-06, + "loss": 0.7679, + "step": 9239 + }, + { + "epoch": 0.8273546365213498, + "grad_norm": 1.2280015508950233, + "learning_rate": 1.5230729334210514e-06, + "loss": 0.8507, + "step": 9240 + }, + { + "epoch": 0.8274441770664279, + "grad_norm": 1.533775043861544, + "learning_rate": 1.5215347228600863e-06, + "loss": 0.8106, + "step": 9241 + }, + { + "epoch": 0.827533717611506, + "grad_norm": 1.0116777039512166, + "learning_rate": 1.5199972254799922e-06, + "loss": 0.8491, + "step": 9242 + }, + { + "epoch": 0.827623258156584, + "grad_norm": 0.8647606308651872, + "learning_rate": 1.5184604414100968e-06, + "loss": 0.7981, + "step": 9243 + }, + { + "epoch": 0.8277127987016621, + "grad_norm": 0.9719311309186743, + "learning_rate": 1.5169243707796732e-06, + "loss": 0.7701, + "step": 9244 + }, + { + "epoch": 0.8278023392467402, + "grad_norm": 0.9843673073988213, + "learning_rate": 1.515389013717925e-06, + "loss": 0.842, + "step": 9245 + }, + { + "epoch": 0.8278918797918182, + "grad_norm": 1.0501890422294864, + "learning_rate": 1.513854370354002e-06, + "loss": 0.7878, + "step": 9246 + }, + { + "epoch": 0.8279814203368963, + "grad_norm": 0.9890706852779633, + "learning_rate": 1.5123204408169977e-06, + "loss": 0.844, + "step": 9247 + }, + { + "epoch": 0.8280709608819744, + "grad_norm": 1.0141820878578718, + "learning_rate": 1.510787225235939e-06, + "loss": 0.8258, + "step": 9248 + }, + { + "epoch": 0.8281605014270524, + "grad_norm": 0.9799480830212686, + "learning_rate": 1.509254723739797e-06, + "loss": 0.7823, + "step": 9249 + }, + { + "epoch": 0.8282500419721305, + "grad_norm": 1.024470028594685, + "learning_rate": 1.5077229364574774e-06, + "loss": 0.8335, + "step": 9250 + }, + { + "epoch": 0.8283395825172086, + "grad_norm": 0.974423238209472, + "learning_rate": 1.5061918635178307e-06, + "loss": 0.743, + "step": 9251 + }, + { + "epoch": 0.8284291230622867, + "grad_norm": 1.2024733000253067, + "learning_rate": 1.5046615050496427e-06, + "loss": 0.8302, + "step": 9252 + }, + { + "epoch": 0.8285186636073647, + "grad_norm": 0.9296230197348008, + "learning_rate": 1.503131861181647e-06, + "loss": 0.7308, + "step": 9253 + }, + { + "epoch": 0.8286082041524427, + "grad_norm": 1.0468800928722324, + "learning_rate": 1.501602932042512e-06, + "loss": 0.8, + "step": 9254 + }, + { + "epoch": 0.8286977446975209, + "grad_norm": 1.0140774743385133, + "learning_rate": 1.5000747177608454e-06, + "loss": 0.8336, + "step": 9255 + }, + { + "epoch": 0.8287872852425989, + "grad_norm": 1.0817005554862047, + "learning_rate": 1.4985472184651927e-06, + "loss": 0.7979, + "step": 9256 + }, + { + "epoch": 0.828876825787677, + "grad_norm": 0.9296353754479479, + "learning_rate": 1.4970204342840445e-06, + "loss": 0.7689, + "step": 9257 + }, + { + "epoch": 0.828966366332755, + "grad_norm": 1.0514594903982553, + "learning_rate": 1.4954943653458265e-06, + "loss": 0.8541, + "step": 9258 + }, + { + "epoch": 0.8290559068778331, + "grad_norm": 1.0047022855627736, + "learning_rate": 1.4939690117789107e-06, + "loss": 0.8241, + "step": 9259 + }, + { + "epoch": 0.8291454474229112, + "grad_norm": 0.9546997951028352, + "learning_rate": 1.4924443737116057e-06, + "loss": 0.7803, + "step": 9260 + }, + { + "epoch": 0.8292349879679892, + "grad_norm": 1.0025659437999093, + "learning_rate": 1.4909204512721542e-06, + "loss": 0.7863, + "step": 9261 + }, + { + "epoch": 0.8293245285130674, + "grad_norm": 1.021572472609321, + "learning_rate": 1.4893972445887451e-06, + "loss": 0.8062, + "step": 9262 + }, + { + "epoch": 0.8294140690581454, + "grad_norm": 0.995831239039463, + "learning_rate": 1.4878747537895067e-06, + "loss": 0.822, + "step": 9263 + }, + { + "epoch": 0.8295036096032234, + "grad_norm": 1.00713756948133, + "learning_rate": 1.4863529790025033e-06, + "loss": 0.7974, + "step": 9264 + }, + { + "epoch": 0.8295931501483015, + "grad_norm": 0.9769879958124396, + "learning_rate": 1.484831920355746e-06, + "loss": 0.7848, + "step": 9265 + }, + { + "epoch": 0.8296826906933796, + "grad_norm": 1.0131127152634398, + "learning_rate": 1.4833115779771813e-06, + "loss": 0.8145, + "step": 9266 + }, + { + "epoch": 0.8297722312384577, + "grad_norm": 1.0208204266027203, + "learning_rate": 1.4817919519946922e-06, + "loss": 0.8004, + "step": 9267 + }, + { + "epoch": 0.8298617717835357, + "grad_norm": 1.0645144060282736, + "learning_rate": 1.4802730425361044e-06, + "loss": 0.8782, + "step": 9268 + }, + { + "epoch": 0.8299513123286139, + "grad_norm": 0.9571386361415842, + "learning_rate": 1.4787548497291848e-06, + "loss": 0.7679, + "step": 9269 + }, + { + "epoch": 0.8300408528736919, + "grad_norm": 1.0541557617426582, + "learning_rate": 1.4772373737016376e-06, + "loss": 0.7635, + "step": 9270 + }, + { + "epoch": 0.8301303934187699, + "grad_norm": 0.9478972451152083, + "learning_rate": 1.4757206145811143e-06, + "loss": 0.821, + "step": 9271 + }, + { + "epoch": 0.830219933963848, + "grad_norm": 0.905756682549673, + "learning_rate": 1.4742045724951914e-06, + "loss": 0.7899, + "step": 9272 + }, + { + "epoch": 0.8303094745089261, + "grad_norm": 0.9036745208599757, + "learning_rate": 1.4726892475713972e-06, + "loss": 0.7094, + "step": 9273 + }, + { + "epoch": 0.8303990150540042, + "grad_norm": 0.9283629046460248, + "learning_rate": 1.4711746399371952e-06, + "loss": 0.8262, + "step": 9274 + }, + { + "epoch": 0.8304885555990822, + "grad_norm": 1.06349578407657, + "learning_rate": 1.46966074971999e-06, + "loss": 0.8181, + "step": 9275 + }, + { + "epoch": 0.8305780961441602, + "grad_norm": 1.0553265729155814, + "learning_rate": 1.4681475770471254e-06, + "loss": 0.8635, + "step": 9276 + }, + { + "epoch": 0.8306676366892384, + "grad_norm": 1.0515576618831197, + "learning_rate": 1.466635122045883e-06, + "loss": 0.7972, + "step": 9277 + }, + { + "epoch": 0.8307571772343164, + "grad_norm": 1.0474234154596638, + "learning_rate": 1.4651233848434865e-06, + "loss": 0.8418, + "step": 9278 + }, + { + "epoch": 0.8308467177793945, + "grad_norm": 1.0402734793578703, + "learning_rate": 1.4636123655670976e-06, + "loss": 0.8143, + "step": 9279 + }, + { + "epoch": 0.8309362583244726, + "grad_norm": 1.057697969715789, + "learning_rate": 1.46210206434382e-06, + "loss": 0.7857, + "step": 9280 + }, + { + "epoch": 0.8310257988695506, + "grad_norm": 1.0150548984305776, + "learning_rate": 1.4605924813006933e-06, + "loss": 0.8479, + "step": 9281 + }, + { + "epoch": 0.8311153394146287, + "grad_norm": 1.1847705855892516, + "learning_rate": 1.4590836165647003e-06, + "loss": 0.7807, + "step": 9282 + }, + { + "epoch": 0.8312048799597067, + "grad_norm": 0.9834288682085118, + "learning_rate": 1.457575470262762e-06, + "loss": 0.8285, + "step": 9283 + }, + { + "epoch": 0.8312944205047849, + "grad_norm": 0.932081910083776, + "learning_rate": 1.4560680425217365e-06, + "loss": 0.7469, + "step": 9284 + }, + { + "epoch": 0.8313839610498629, + "grad_norm": 1.0037831945446654, + "learning_rate": 1.4545613334684262e-06, + "loss": 0.7566, + "step": 9285 + }, + { + "epoch": 0.8314735015949409, + "grad_norm": 0.9652530058535604, + "learning_rate": 1.453055343229568e-06, + "loss": 0.8238, + "step": 9286 + }, + { + "epoch": 0.8315630421400191, + "grad_norm": 1.0231788973172407, + "learning_rate": 1.4515500719318432e-06, + "loss": 0.7806, + "step": 9287 + }, + { + "epoch": 0.8316525826850971, + "grad_norm": 1.0123969257649366, + "learning_rate": 1.4500455197018703e-06, + "loss": 0.7895, + "step": 9288 + }, + { + "epoch": 0.8317421232301752, + "grad_norm": 0.9670798000656414, + "learning_rate": 1.448541686666205e-06, + "loss": 0.8152, + "step": 9289 + }, + { + "epoch": 0.8318316637752532, + "grad_norm": 1.0400110586077793, + "learning_rate": 1.447038572951347e-06, + "loss": 0.8141, + "step": 9290 + }, + { + "epoch": 0.8319212043203313, + "grad_norm": 1.0225821726761233, + "learning_rate": 1.445536178683733e-06, + "loss": 0.8163, + "step": 9291 + }, + { + "epoch": 0.8320107448654094, + "grad_norm": 1.0627421404061446, + "learning_rate": 1.4440345039897398e-06, + "loss": 0.8295, + "step": 9292 + }, + { + "epoch": 0.8321002854104874, + "grad_norm": 0.9494389265736692, + "learning_rate": 1.4425335489956816e-06, + "loss": 0.7581, + "step": 9293 + }, + { + "epoch": 0.8321898259555655, + "grad_norm": 0.9597468636537545, + "learning_rate": 1.4410333138278153e-06, + "loss": 0.8062, + "step": 9294 + }, + { + "epoch": 0.8322793665006436, + "grad_norm": 1.4483754003333227, + "learning_rate": 1.4395337986123349e-06, + "loss": 0.8566, + "step": 9295 + }, + { + "epoch": 0.8323689070457216, + "grad_norm": 0.9990419177062249, + "learning_rate": 1.4380350034753766e-06, + "loss": 0.8201, + "step": 9296 + }, + { + "epoch": 0.8324584475907997, + "grad_norm": 0.99089138471879, + "learning_rate": 1.436536928543012e-06, + "loss": 0.8225, + "step": 9297 + }, + { + "epoch": 0.8325479881358778, + "grad_norm": 0.9454435431021928, + "learning_rate": 1.435039573941256e-06, + "loss": 0.8183, + "step": 9298 + }, + { + "epoch": 0.8326375286809559, + "grad_norm": 0.9321080031700404, + "learning_rate": 1.433542939796062e-06, + "loss": 0.7969, + "step": 9299 + }, + { + "epoch": 0.8327270692260339, + "grad_norm": 1.0628322003806028, + "learning_rate": 1.4320470262333154e-06, + "loss": 0.7814, + "step": 9300 + }, + { + "epoch": 0.8328166097711119, + "grad_norm": 0.9396604359453226, + "learning_rate": 1.430551833378856e-06, + "loss": 0.764, + "step": 9301 + }, + { + "epoch": 0.8329061503161901, + "grad_norm": 1.0256126135806607, + "learning_rate": 1.4290573613584502e-06, + "loss": 0.7862, + "step": 9302 + }, + { + "epoch": 0.8329956908612681, + "grad_norm": 0.9503959428146012, + "learning_rate": 1.4275636102978086e-06, + "loss": 0.863, + "step": 9303 + }, + { + "epoch": 0.8330852314063462, + "grad_norm": 1.0330595563695593, + "learning_rate": 1.4260705803225838e-06, + "loss": 0.8502, + "step": 9304 + }, + { + "epoch": 0.8331747719514243, + "grad_norm": 0.9235747800319499, + "learning_rate": 1.42457827155836e-06, + "loss": 0.7862, + "step": 9305 + }, + { + "epoch": 0.8332643124965023, + "grad_norm": 1.031778751467731, + "learning_rate": 1.4230866841306645e-06, + "loss": 0.8428, + "step": 9306 + }, + { + "epoch": 0.8333538530415804, + "grad_norm": 0.942230496291779, + "learning_rate": 1.4215958181649702e-06, + "loss": 0.8061, + "step": 9307 + }, + { + "epoch": 0.8334433935866584, + "grad_norm": 1.1862723260445964, + "learning_rate": 1.4201056737866813e-06, + "loss": 0.8087, + "step": 9308 + }, + { + "epoch": 0.8335329341317366, + "grad_norm": 0.9128967073761088, + "learning_rate": 1.4186162511211454e-06, + "loss": 0.7819, + "step": 9309 + }, + { + "epoch": 0.8336224746768146, + "grad_norm": 1.1165664576287428, + "learning_rate": 1.4171275502936445e-06, + "loss": 0.845, + "step": 9310 + }, + { + "epoch": 0.8337120152218926, + "grad_norm": 1.2055046566607368, + "learning_rate": 1.4156395714294048e-06, + "loss": 0.8091, + "step": 9311 + }, + { + "epoch": 0.8338015557669707, + "grad_norm": 0.9953980491177246, + "learning_rate": 1.4141523146535886e-06, + "loss": 0.7361, + "step": 9312 + }, + { + "epoch": 0.8338910963120488, + "grad_norm": 1.0263834808837446, + "learning_rate": 1.4126657800913023e-06, + "loss": 0.7348, + "step": 9313 + }, + { + "epoch": 0.8339806368571269, + "grad_norm": 0.8972194798939946, + "learning_rate": 1.4111799678675875e-06, + "loss": 0.8014, + "step": 9314 + }, + { + "epoch": 0.8340701774022049, + "grad_norm": 0.9795184640822597, + "learning_rate": 1.4096948781074282e-06, + "loss": 0.8355, + "step": 9315 + }, + { + "epoch": 0.834159717947283, + "grad_norm": 0.9818780129950107, + "learning_rate": 1.4082105109357403e-06, + "loss": 0.7737, + "step": 9316 + }, + { + "epoch": 0.8342492584923611, + "grad_norm": 1.047338751982747, + "learning_rate": 1.4067268664773849e-06, + "loss": 0.7772, + "step": 9317 + }, + { + "epoch": 0.8343387990374391, + "grad_norm": 0.9508092693964137, + "learning_rate": 1.4052439448571608e-06, + "loss": 0.7661, + "step": 9318 + }, + { + "epoch": 0.8344283395825172, + "grad_norm": 0.9844442963406824, + "learning_rate": 1.403761746199811e-06, + "loss": 0.7726, + "step": 9319 + }, + { + "epoch": 0.8345178801275953, + "grad_norm": 0.9420578197626516, + "learning_rate": 1.402280270630013e-06, + "loss": 0.7966, + "step": 9320 + }, + { + "epoch": 0.8346074206726734, + "grad_norm": 0.9826005784325806, + "learning_rate": 1.4007995182723778e-06, + "loss": 0.7962, + "step": 9321 + }, + { + "epoch": 0.8346969612177514, + "grad_norm": 1.1032863816983074, + "learning_rate": 1.399319489251466e-06, + "loss": 0.8509, + "step": 9322 + }, + { + "epoch": 0.8347865017628295, + "grad_norm": 1.0446112990473353, + "learning_rate": 1.397840183691771e-06, + "loss": 0.789, + "step": 9323 + }, + { + "epoch": 0.8348760423079076, + "grad_norm": 1.332732400053229, + "learning_rate": 1.3963616017177262e-06, + "loss": 0.8648, + "step": 9324 + }, + { + "epoch": 0.8349655828529856, + "grad_norm": 1.0416975658695535, + "learning_rate": 1.3948837434537087e-06, + "loss": 0.7559, + "step": 9325 + }, + { + "epoch": 0.8350551233980636, + "grad_norm": 1.0853684461501492, + "learning_rate": 1.3934066090240306e-06, + "loss": 0.8591, + "step": 9326 + }, + { + "epoch": 0.8351446639431418, + "grad_norm": 1.063084288549793, + "learning_rate": 1.391930198552941e-06, + "loss": 0.827, + "step": 9327 + }, + { + "epoch": 0.8352342044882198, + "grad_norm": 1.0863449712139108, + "learning_rate": 1.3904545121646319e-06, + "loss": 0.7476, + "step": 9328 + }, + { + "epoch": 0.8353237450332979, + "grad_norm": 1.1092637286053433, + "learning_rate": 1.3889795499832327e-06, + "loss": 0.7889, + "step": 9329 + }, + { + "epoch": 0.8354132855783759, + "grad_norm": 0.920590489969962, + "learning_rate": 1.3875053121328142e-06, + "loss": 0.7789, + "step": 9330 + }, + { + "epoch": 0.8355028261234541, + "grad_norm": 1.257558246405282, + "learning_rate": 1.3860317987373817e-06, + "loss": 0.8177, + "step": 9331 + }, + { + "epoch": 0.8355923666685321, + "grad_norm": 0.9926872985998035, + "learning_rate": 1.384559009920885e-06, + "loss": 0.8713, + "step": 9332 + }, + { + "epoch": 0.8356819072136101, + "grad_norm": 0.9619027877371132, + "learning_rate": 1.3830869458072083e-06, + "loss": 0.7901, + "step": 9333 + }, + { + "epoch": 0.8357714477586883, + "grad_norm": 1.006640321906385, + "learning_rate": 1.3816156065201791e-06, + "loss": 0.8241, + "step": 9334 + }, + { + "epoch": 0.8358609883037663, + "grad_norm": 1.0515813212075948, + "learning_rate": 1.3801449921835585e-06, + "loss": 0.7816, + "step": 9335 + }, + { + "epoch": 0.8359505288488444, + "grad_norm": 1.1303103018572864, + "learning_rate": 1.3786751029210532e-06, + "loss": 0.7634, + "step": 9336 + }, + { + "epoch": 0.8360400693939224, + "grad_norm": 0.9616497506280306, + "learning_rate": 1.377205938856303e-06, + "loss": 0.775, + "step": 9337 + }, + { + "epoch": 0.8361296099390005, + "grad_norm": 0.9979300401969639, + "learning_rate": 1.3757375001128903e-06, + "loss": 0.7357, + "step": 9338 + }, + { + "epoch": 0.8362191504840786, + "grad_norm": 1.0464891806927004, + "learning_rate": 1.3742697868143362e-06, + "loss": 0.8075, + "step": 9339 + }, + { + "epoch": 0.8363086910291566, + "grad_norm": 0.9893442732004429, + "learning_rate": 1.3728027990840976e-06, + "loss": 0.779, + "step": 9340 + }, + { + "epoch": 0.8363982315742348, + "grad_norm": 0.9805203776882536, + "learning_rate": 1.3713365370455744e-06, + "loss": 0.8177, + "step": 9341 + }, + { + "epoch": 0.8364877721193128, + "grad_norm": 0.9634067576564073, + "learning_rate": 1.369871000822104e-06, + "loss": 0.8197, + "step": 9342 + }, + { + "epoch": 0.8365773126643908, + "grad_norm": 1.0091130284816987, + "learning_rate": 1.3684061905369606e-06, + "loss": 0.8026, + "step": 9343 + }, + { + "epoch": 0.8366668532094689, + "grad_norm": 0.9888378950541664, + "learning_rate": 1.3669421063133626e-06, + "loss": 0.8234, + "step": 9344 + }, + { + "epoch": 0.836756393754547, + "grad_norm": 1.0693551686954252, + "learning_rate": 1.3654787482744601e-06, + "loss": 0.8529, + "step": 9345 + }, + { + "epoch": 0.8368459342996251, + "grad_norm": 1.115279424313577, + "learning_rate": 1.3640161165433496e-06, + "loss": 0.7989, + "step": 9346 + }, + { + "epoch": 0.8369354748447031, + "grad_norm": 0.962231855705234, + "learning_rate": 1.36255421124306e-06, + "loss": 0.8294, + "step": 9347 + }, + { + "epoch": 0.8370250153897811, + "grad_norm": 1.0958877398234657, + "learning_rate": 1.3610930324965643e-06, + "loss": 0.8553, + "step": 9348 + }, + { + "epoch": 0.8371145559348593, + "grad_norm": 1.0083307553447438, + "learning_rate": 1.3596325804267696e-06, + "loss": 0.8021, + "step": 9349 + }, + { + "epoch": 0.8372040964799373, + "grad_norm": 1.0260208232843464, + "learning_rate": 1.3581728551565275e-06, + "loss": 0.8414, + "step": 9350 + }, + { + "epoch": 0.8372936370250154, + "grad_norm": 1.0181013358918505, + "learning_rate": 1.3567138568086225e-06, + "loss": 0.8092, + "step": 9351 + }, + { + "epoch": 0.8373831775700935, + "grad_norm": 0.979063610338897, + "learning_rate": 1.3552555855057825e-06, + "loss": 0.8085, + "step": 9352 + }, + { + "epoch": 0.8374727181151715, + "grad_norm": 0.9732686826197213, + "learning_rate": 1.3537980413706742e-06, + "loss": 0.7682, + "step": 9353 + }, + { + "epoch": 0.8375622586602496, + "grad_norm": 1.0298868342013812, + "learning_rate": 1.3523412245258948e-06, + "loss": 0.8597, + "step": 9354 + }, + { + "epoch": 0.8376517992053276, + "grad_norm": 1.0210219595458543, + "learning_rate": 1.3508851350939934e-06, + "loss": 0.8428, + "step": 9355 + }, + { + "epoch": 0.8377413397504058, + "grad_norm": 0.9491656805823092, + "learning_rate": 1.3494297731974494e-06, + "loss": 0.7323, + "step": 9356 + }, + { + "epoch": 0.8378308802954838, + "grad_norm": 1.020970130401167, + "learning_rate": 1.3479751389586836e-06, + "loss": 0.8393, + "step": 9357 + }, + { + "epoch": 0.8379204208405618, + "grad_norm": 1.1289678333450825, + "learning_rate": 1.3465212325000543e-06, + "loss": 0.8579, + "step": 9358 + }, + { + "epoch": 0.83800996138564, + "grad_norm": 0.9965978905279886, + "learning_rate": 1.345068053943863e-06, + "loss": 0.8405, + "step": 9359 + }, + { + "epoch": 0.838099501930718, + "grad_norm": 1.1431984683165126, + "learning_rate": 1.3436156034123383e-06, + "loss": 0.7505, + "step": 9360 + }, + { + "epoch": 0.8381890424757961, + "grad_norm": 0.9878026435496984, + "learning_rate": 1.3421638810276615e-06, + "loss": 0.8349, + "step": 9361 + }, + { + "epoch": 0.8382785830208741, + "grad_norm": 0.9758222306741415, + "learning_rate": 1.3407128869119469e-06, + "loss": 0.8536, + "step": 9362 + }, + { + "epoch": 0.8383681235659523, + "grad_norm": 0.9576380617256895, + "learning_rate": 1.3392626211872462e-06, + "loss": 0.763, + "step": 9363 + }, + { + "epoch": 0.8384576641110303, + "grad_norm": 1.191263813692219, + "learning_rate": 1.3378130839755533e-06, + "loss": 0.8132, + "step": 9364 + }, + { + "epoch": 0.8385472046561083, + "grad_norm": 0.9698702345466614, + "learning_rate": 1.3363642753987938e-06, + "loss": 0.8074, + "step": 9365 + }, + { + "epoch": 0.8386367452011864, + "grad_norm": 1.3110961185862187, + "learning_rate": 1.334916195578837e-06, + "loss": 0.7987, + "step": 9366 + }, + { + "epoch": 0.8387262857462645, + "grad_norm": 0.907938899406801, + "learning_rate": 1.3334688446374944e-06, + "loss": 0.808, + "step": 9367 + }, + { + "epoch": 0.8388158262913425, + "grad_norm": 0.9478701278421511, + "learning_rate": 1.3320222226965119e-06, + "loss": 0.759, + "step": 9368 + }, + { + "epoch": 0.8389053668364206, + "grad_norm": 1.0981178770515205, + "learning_rate": 1.3305763298775732e-06, + "loss": 0.8437, + "step": 9369 + }, + { + "epoch": 0.8389949073814987, + "grad_norm": 0.9380162544959776, + "learning_rate": 1.3291311663023055e-06, + "loss": 0.809, + "step": 9370 + }, + { + "epoch": 0.8390844479265768, + "grad_norm": 0.9163900798218562, + "learning_rate": 1.327686732092265e-06, + "loss": 0.8224, + "step": 9371 + }, + { + "epoch": 0.8391739884716548, + "grad_norm": 1.0593361852416765, + "learning_rate": 1.3262430273689542e-06, + "loss": 0.8304, + "step": 9372 + }, + { + "epoch": 0.8392635290167328, + "grad_norm": 1.065417561373481, + "learning_rate": 1.3248000522538174e-06, + "loss": 0.8049, + "step": 9373 + }, + { + "epoch": 0.839353069561811, + "grad_norm": 1.0355679906606496, + "learning_rate": 1.3233578068682295e-06, + "loss": 0.8436, + "step": 9374 + }, + { + "epoch": 0.839442610106889, + "grad_norm": 0.9814774237493498, + "learning_rate": 1.3219162913335115e-06, + "loss": 0.7769, + "step": 9375 + }, + { + "epoch": 0.8395321506519671, + "grad_norm": 1.0055103996469403, + "learning_rate": 1.320475505770913e-06, + "loss": 0.7948, + "step": 9376 + }, + { + "epoch": 0.8396216911970452, + "grad_norm": 0.9898926534419442, + "learning_rate": 1.3190354503016312e-06, + "loss": 0.8329, + "step": 9377 + }, + { + "epoch": 0.8397112317421233, + "grad_norm": 1.3350544758262883, + "learning_rate": 1.3175961250467962e-06, + "loss": 0.7893, + "step": 9378 + }, + { + "epoch": 0.8398007722872013, + "grad_norm": 1.0981814832288939, + "learning_rate": 1.3161575301274832e-06, + "loss": 0.8341, + "step": 9379 + }, + { + "epoch": 0.8398903128322793, + "grad_norm": 0.9564197075065075, + "learning_rate": 1.3147196656647044e-06, + "loss": 0.8154, + "step": 9380 + }, + { + "epoch": 0.8399798533773575, + "grad_norm": 0.9200920513060068, + "learning_rate": 1.3132825317794019e-06, + "loss": 0.8035, + "step": 9381 + }, + { + "epoch": 0.8400693939224355, + "grad_norm": 1.0014036790061887, + "learning_rate": 1.3118461285924643e-06, + "loss": 0.8191, + "step": 9382 + }, + { + "epoch": 0.8401589344675136, + "grad_norm": 0.9189910846009759, + "learning_rate": 1.31041045622472e-06, + "loss": 0.7865, + "step": 9383 + }, + { + "epoch": 0.8402484750125916, + "grad_norm": 0.9199667695563013, + "learning_rate": 1.3089755147969297e-06, + "loss": 0.7727, + "step": 9384 + }, + { + "epoch": 0.8403380155576697, + "grad_norm": 0.9918103194931872, + "learning_rate": 1.3075413044297969e-06, + "loss": 0.793, + "step": 9385 + }, + { + "epoch": 0.8404275561027478, + "grad_norm": 1.107784823147746, + "learning_rate": 1.3061078252439662e-06, + "loss": 0.8187, + "step": 9386 + }, + { + "epoch": 0.8405170966478258, + "grad_norm": 1.0663026137216804, + "learning_rate": 1.3046750773600137e-06, + "loss": 0.8763, + "step": 9387 + }, + { + "epoch": 0.840606637192904, + "grad_norm": 1.1036165674997183, + "learning_rate": 1.303243060898457e-06, + "loss": 0.8243, + "step": 9388 + }, + { + "epoch": 0.840696177737982, + "grad_norm": 1.0625703808868427, + "learning_rate": 1.3018117759797543e-06, + "loss": 0.7785, + "step": 9389 + }, + { + "epoch": 0.84078571828306, + "grad_norm": 0.9465974307320747, + "learning_rate": 1.3003812227243008e-06, + "loss": 0.8323, + "step": 9390 + }, + { + "epoch": 0.8408752588281381, + "grad_norm": 0.9440261369084691, + "learning_rate": 1.2989514012524285e-06, + "loss": 0.8345, + "step": 9391 + }, + { + "epoch": 0.8409647993732162, + "grad_norm": 1.2503007591932942, + "learning_rate": 1.2975223116844115e-06, + "loss": 0.7603, + "step": 9392 + }, + { + "epoch": 0.8410543399182943, + "grad_norm": 1.0417051341188797, + "learning_rate": 1.2960939541404572e-06, + "loss": 0.8147, + "step": 9393 + }, + { + "epoch": 0.8411438804633723, + "grad_norm": 0.9618166110649607, + "learning_rate": 1.2946663287407169e-06, + "loss": 0.7755, + "step": 9394 + }, + { + "epoch": 0.8412334210084504, + "grad_norm": 0.9972289893865883, + "learning_rate": 1.2932394356052768e-06, + "loss": 0.8042, + "step": 9395 + }, + { + "epoch": 0.8413229615535285, + "grad_norm": 0.9231087083050765, + "learning_rate": 1.2918132748541624e-06, + "loss": 0.8008, + "step": 9396 + }, + { + "epoch": 0.8414125020986065, + "grad_norm": 0.9449350453612199, + "learning_rate": 1.2903878466073382e-06, + "loss": 0.8029, + "step": 9397 + }, + { + "epoch": 0.8415020426436846, + "grad_norm": 0.9424755848644499, + "learning_rate": 1.2889631509847067e-06, + "loss": 0.824, + "step": 9398 + }, + { + "epoch": 0.8415915831887627, + "grad_norm": 1.0619739390075245, + "learning_rate": 1.2875391881061072e-06, + "loss": 0.8486, + "step": 9399 + }, + { + "epoch": 0.8416811237338407, + "grad_norm": 1.0490472726070956, + "learning_rate": 1.2861159580913207e-06, + "loss": 0.8207, + "step": 9400 + }, + { + "epoch": 0.8417706642789188, + "grad_norm": 0.9426405641807752, + "learning_rate": 1.2846934610600636e-06, + "loss": 0.8086, + "step": 9401 + }, + { + "epoch": 0.8418602048239968, + "grad_norm": 0.9954250590077064, + "learning_rate": 1.2832716971319914e-06, + "loss": 0.7845, + "step": 9402 + }, + { + "epoch": 0.841949745369075, + "grad_norm": 1.245168462987065, + "learning_rate": 1.2818506664266993e-06, + "loss": 0.8017, + "step": 9403 + }, + { + "epoch": 0.842039285914153, + "grad_norm": 1.095330937115553, + "learning_rate": 1.28043036906372e-06, + "loss": 0.8345, + "step": 9404 + }, + { + "epoch": 0.842128826459231, + "grad_norm": 1.272543221548517, + "learning_rate": 1.2790108051625228e-06, + "loss": 0.7979, + "step": 9405 + }, + { + "epoch": 0.8422183670043092, + "grad_norm": 0.8837808468662629, + "learning_rate": 1.277591974842517e-06, + "loss": 0.8204, + "step": 9406 + }, + { + "epoch": 0.8423079075493872, + "grad_norm": 0.9493494481412919, + "learning_rate": 1.2761738782230516e-06, + "loss": 0.796, + "step": 9407 + }, + { + "epoch": 0.8423974480944653, + "grad_norm": 0.8743774614321845, + "learning_rate": 1.274756515423411e-06, + "loss": 0.7685, + "step": 9408 + }, + { + "epoch": 0.8424869886395433, + "grad_norm": 0.982702787315466, + "learning_rate": 1.2733398865628189e-06, + "loss": 0.8363, + "step": 9409 + }, + { + "epoch": 0.8425765291846214, + "grad_norm": 0.9253358754093878, + "learning_rate": 1.2719239917604375e-06, + "loss": 0.8104, + "step": 9410 + }, + { + "epoch": 0.8426660697296995, + "grad_norm": 1.0292574948712812, + "learning_rate": 1.2705088311353687e-06, + "loss": 0.8227, + "step": 9411 + }, + { + "epoch": 0.8427556102747775, + "grad_norm": 0.9871819714266331, + "learning_rate": 1.26909440480665e-06, + "loss": 0.8187, + "step": 9412 + }, + { + "epoch": 0.8428451508198557, + "grad_norm": 0.9567690800315941, + "learning_rate": 1.26768071289326e-06, + "loss": 0.8322, + "step": 9413 + }, + { + "epoch": 0.8429346913649337, + "grad_norm": 0.9415354074840518, + "learning_rate": 1.266267755514109e-06, + "loss": 0.8691, + "step": 9414 + }, + { + "epoch": 0.8430242319100117, + "grad_norm": 0.9682124829935164, + "learning_rate": 1.264855532788055e-06, + "loss": 0.8335, + "step": 9415 + }, + { + "epoch": 0.8431137724550898, + "grad_norm": 1.0098555381199852, + "learning_rate": 1.263444044833889e-06, + "loss": 0.7765, + "step": 9416 + }, + { + "epoch": 0.8432033130001679, + "grad_norm": 0.9590123214488422, + "learning_rate": 1.2620332917703404e-06, + "loss": 0.7641, + "step": 9417 + }, + { + "epoch": 0.843292853545246, + "grad_norm": 1.0822258328180616, + "learning_rate": 1.2606232737160762e-06, + "loss": 0.8152, + "step": 9418 + }, + { + "epoch": 0.843382394090324, + "grad_norm": 1.019164939675285, + "learning_rate": 1.259213990789705e-06, + "loss": 0.7858, + "step": 9419 + }, + { + "epoch": 0.843471934635402, + "grad_norm": 0.8942582572575131, + "learning_rate": 1.2578054431097664e-06, + "loss": 0.7348, + "step": 9420 + }, + { + "epoch": 0.8435614751804802, + "grad_norm": 0.9997575570124957, + "learning_rate": 1.2563976307947467e-06, + "loss": 0.8008, + "step": 9421 + }, + { + "epoch": 0.8436510157255582, + "grad_norm": 1.1527811447071072, + "learning_rate": 1.2549905539630659e-06, + "loss": 0.8068, + "step": 9422 + }, + { + "epoch": 0.8437405562706363, + "grad_norm": 0.9740551403720202, + "learning_rate": 1.253584212733081e-06, + "loss": 0.8084, + "step": 9423 + }, + { + "epoch": 0.8438300968157144, + "grad_norm": 1.1486142228829237, + "learning_rate": 1.2521786072230935e-06, + "loss": 0.8221, + "step": 9424 + }, + { + "epoch": 0.8439196373607925, + "grad_norm": 0.9196442799200877, + "learning_rate": 1.250773737551333e-06, + "loss": 0.7709, + "step": 9425 + }, + { + "epoch": 0.8440091779058705, + "grad_norm": 1.238847067470714, + "learning_rate": 1.2493696038359726e-06, + "loss": 0.7771, + "step": 9426 + }, + { + "epoch": 0.8440987184509485, + "grad_norm": 1.0484319442145777, + "learning_rate": 1.247966206195127e-06, + "loss": 0.826, + "step": 9427 + }, + { + "epoch": 0.8441882589960267, + "grad_norm": 0.974343115951212, + "learning_rate": 1.2465635447468437e-06, + "loss": 0.8022, + "step": 9428 + }, + { + "epoch": 0.8442777995411047, + "grad_norm": 1.002867652709638, + "learning_rate": 1.2451616196091109e-06, + "loss": 0.7698, + "step": 9429 + }, + { + "epoch": 0.8443673400861827, + "grad_norm": 0.9509962367359098, + "learning_rate": 1.243760430899854e-06, + "loss": 0.8201, + "step": 9430 + }, + { + "epoch": 0.8444568806312609, + "grad_norm": 0.9946709587412615, + "learning_rate": 1.2423599787369344e-06, + "loss": 0.8055, + "step": 9431 + }, + { + "epoch": 0.8445464211763389, + "grad_norm": 0.9465193414641924, + "learning_rate": 1.2409602632381535e-06, + "loss": 0.7314, + "step": 9432 + }, + { + "epoch": 0.844635961721417, + "grad_norm": 0.9932042436517587, + "learning_rate": 1.2395612845212534e-06, + "loss": 0.7766, + "step": 9433 + }, + { + "epoch": 0.844725502266495, + "grad_norm": 0.9025696476038836, + "learning_rate": 1.2381630427039105e-06, + "loss": 0.8107, + "step": 9434 + }, + { + "epoch": 0.8448150428115732, + "grad_norm": 1.044463165232071, + "learning_rate": 1.2367655379037424e-06, + "loss": 0.8489, + "step": 9435 + }, + { + "epoch": 0.8449045833566512, + "grad_norm": 0.9208071850649792, + "learning_rate": 1.2353687702382978e-06, + "loss": 0.7652, + "step": 9436 + }, + { + "epoch": 0.8449941239017292, + "grad_norm": 0.9524663946012304, + "learning_rate": 1.2339727398250711e-06, + "loss": 0.7738, + "step": 9437 + }, + { + "epoch": 0.8450836644468073, + "grad_norm": 1.0531635333020888, + "learning_rate": 1.232577446781492e-06, + "loss": 0.8289, + "step": 9438 + }, + { + "epoch": 0.8451732049918854, + "grad_norm": 0.9994901936326652, + "learning_rate": 1.2311828912249258e-06, + "loss": 0.8259, + "step": 9439 + }, + { + "epoch": 0.8452627455369635, + "grad_norm": 0.939832901007213, + "learning_rate": 1.2297890732726814e-06, + "loss": 0.7599, + "step": 9440 + }, + { + "epoch": 0.8453522860820415, + "grad_norm": 1.1473839878539012, + "learning_rate": 1.228395993042003e-06, + "loss": 0.802, + "step": 9441 + }, + { + "epoch": 0.8454418266271196, + "grad_norm": 0.9741412892641501, + "learning_rate": 1.227003650650067e-06, + "loss": 0.7797, + "step": 9442 + }, + { + "epoch": 0.8455313671721977, + "grad_norm": 0.9893199232585013, + "learning_rate": 1.2256120462139963e-06, + "loss": 0.8683, + "step": 9443 + }, + { + "epoch": 0.8456209077172757, + "grad_norm": 0.9008887564516423, + "learning_rate": 1.2242211798508464e-06, + "loss": 0.8504, + "step": 9444 + }, + { + "epoch": 0.8457104482623538, + "grad_norm": 1.003194637913834, + "learning_rate": 1.222831051677611e-06, + "loss": 0.8603, + "step": 9445 + }, + { + "epoch": 0.8457999888074319, + "grad_norm": 0.9742825520050253, + "learning_rate": 1.2214416618112302e-06, + "loss": 0.8413, + "step": 9446 + }, + { + "epoch": 0.8458895293525099, + "grad_norm": 1.051911440744658, + "learning_rate": 1.220053010368567e-06, + "loss": 0.7739, + "step": 9447 + }, + { + "epoch": 0.845979069897588, + "grad_norm": 1.1145617458488868, + "learning_rate": 1.2186650974664337e-06, + "loss": 0.7834, + "step": 9448 + }, + { + "epoch": 0.8460686104426661, + "grad_norm": 1.1002011082265823, + "learning_rate": 1.217277923221577e-06, + "loss": 0.7859, + "step": 9449 + }, + { + "epoch": 0.8461581509877442, + "grad_norm": 0.9507004583417564, + "learning_rate": 1.215891487750681e-06, + "loss": 0.8104, + "step": 9450 + }, + { + "epoch": 0.8462476915328222, + "grad_norm": 1.0007878599485773, + "learning_rate": 1.2145057911703683e-06, + "loss": 0.8073, + "step": 9451 + }, + { + "epoch": 0.8463372320779002, + "grad_norm": 0.9323226864633257, + "learning_rate": 1.2131208335971988e-06, + "loss": 0.7493, + "step": 9452 + }, + { + "epoch": 0.8464267726229784, + "grad_norm": 1.0474800338546226, + "learning_rate": 1.2117366151476716e-06, + "loss": 0.8419, + "step": 9453 + }, + { + "epoch": 0.8465163131680564, + "grad_norm": 1.0939916402224295, + "learning_rate": 1.2103531359382214e-06, + "loss": 0.7377, + "step": 9454 + }, + { + "epoch": 0.8466058537131345, + "grad_norm": 1.082476535830715, + "learning_rate": 1.208970396085223e-06, + "loss": 0.8173, + "step": 9455 + }, + { + "epoch": 0.8466953942582125, + "grad_norm": 0.9079978422558551, + "learning_rate": 1.2075883957049862e-06, + "loss": 0.7941, + "step": 9456 + }, + { + "epoch": 0.8467849348032906, + "grad_norm": 1.0027050784110783, + "learning_rate": 1.2062071349137627e-06, + "loss": 0.8038, + "step": 9457 + }, + { + "epoch": 0.8468744753483687, + "grad_norm": 1.0017879626356014, + "learning_rate": 1.2048266138277388e-06, + "loss": 0.7775, + "step": 9458 + }, + { + "epoch": 0.8469640158934467, + "grad_norm": 0.9639095623977575, + "learning_rate": 1.203446832563039e-06, + "loss": 0.8161, + "step": 9459 + }, + { + "epoch": 0.8470535564385249, + "grad_norm": 1.148007910766874, + "learning_rate": 1.202067791235726e-06, + "loss": 0.8203, + "step": 9460 + }, + { + "epoch": 0.8471430969836029, + "grad_norm": 0.9264145345238843, + "learning_rate": 1.2006894899618016e-06, + "loss": 0.7906, + "step": 9461 + }, + { + "epoch": 0.8472326375286809, + "grad_norm": 0.9712203921305085, + "learning_rate": 1.199311928857202e-06, + "loss": 0.8463, + "step": 9462 + }, + { + "epoch": 0.847322178073759, + "grad_norm": 1.1841286242305693, + "learning_rate": 1.1979351080378042e-06, + "loss": 0.8327, + "step": 9463 + }, + { + "epoch": 0.8474117186188371, + "grad_norm": 1.0864736445283076, + "learning_rate": 1.1965590276194217e-06, + "loss": 0.8094, + "step": 9464 + }, + { + "epoch": 0.8475012591639152, + "grad_norm": 1.0196336839641365, + "learning_rate": 1.1951836877178069e-06, + "loss": 0.7741, + "step": 9465 + }, + { + "epoch": 0.8475907997089932, + "grad_norm": 0.9720058616682495, + "learning_rate": 1.1938090884486476e-06, + "loss": 0.8134, + "step": 9466 + }, + { + "epoch": 0.8476803402540714, + "grad_norm": 1.1150781787598198, + "learning_rate": 1.19243522992757e-06, + "loss": 0.8021, + "step": 9467 + }, + { + "epoch": 0.8477698807991494, + "grad_norm": 0.9832396470614113, + "learning_rate": 1.1910621122701405e-06, + "loss": 0.7275, + "step": 9468 + }, + { + "epoch": 0.8478594213442274, + "grad_norm": 1.0226878159083508, + "learning_rate": 1.1896897355918602e-06, + "loss": 0.8098, + "step": 9469 + }, + { + "epoch": 0.8479489618893055, + "grad_norm": 0.9990860856360991, + "learning_rate": 1.188318100008169e-06, + "loss": 0.7484, + "step": 9470 + }, + { + "epoch": 0.8480385024343836, + "grad_norm": 0.9634318291989801, + "learning_rate": 1.1869472056344455e-06, + "loss": 0.8267, + "step": 9471 + }, + { + "epoch": 0.8481280429794616, + "grad_norm": 0.9654549232795181, + "learning_rate": 1.1855770525860033e-06, + "loss": 0.7816, + "step": 9472 + }, + { + "epoch": 0.8482175835245397, + "grad_norm": 0.9800099967037483, + "learning_rate": 1.1842076409780977e-06, + "loss": 0.8137, + "step": 9473 + }, + { + "epoch": 0.8483071240696177, + "grad_norm": 1.1763036579790658, + "learning_rate": 1.1828389709259125e-06, + "loss": 0.7718, + "step": 9474 + }, + { + "epoch": 0.8483966646146959, + "grad_norm": 1.0435418595979582, + "learning_rate": 1.1814710425445842e-06, + "loss": 0.7594, + "step": 9475 + }, + { + "epoch": 0.8484862051597739, + "grad_norm": 1.0307086210870409, + "learning_rate": 1.180103855949174e-06, + "loss": 0.8252, + "step": 9476 + }, + { + "epoch": 0.848575745704852, + "grad_norm": 0.9537632326015479, + "learning_rate": 1.1787374112546856e-06, + "loss": 0.7966, + "step": 9477 + }, + { + "epoch": 0.8486652862499301, + "grad_norm": 0.9158085342558261, + "learning_rate": 1.1773717085760606e-06, + "loss": 0.7885, + "step": 9478 + }, + { + "epoch": 0.8487548267950081, + "grad_norm": 1.0227837995190376, + "learning_rate": 1.1760067480281801e-06, + "loss": 0.8439, + "step": 9479 + }, + { + "epoch": 0.8488443673400862, + "grad_norm": 1.0152985357472795, + "learning_rate": 1.1746425297258513e-06, + "loss": 0.7914, + "step": 9480 + }, + { + "epoch": 0.8489339078851642, + "grad_norm": 1.1448130848156446, + "learning_rate": 1.1732790537838369e-06, + "loss": 0.8052, + "step": 9481 + }, + { + "epoch": 0.8490234484302424, + "grad_norm": 1.035450225749339, + "learning_rate": 1.171916320316825e-06, + "loss": 0.8109, + "step": 9482 + }, + { + "epoch": 0.8491129889753204, + "grad_norm": 1.0379151041972199, + "learning_rate": 1.170554329439444e-06, + "loss": 0.7849, + "step": 9483 + }, + { + "epoch": 0.8492025295203984, + "grad_norm": 1.1615330236744337, + "learning_rate": 1.1691930812662622e-06, + "loss": 0.837, + "step": 9484 + }, + { + "epoch": 0.8492920700654766, + "grad_norm": 1.1092377424311615, + "learning_rate": 1.1678325759117782e-06, + "loss": 0.7911, + "step": 9485 + }, + { + "epoch": 0.8493816106105546, + "grad_norm": 1.1254574497463448, + "learning_rate": 1.1664728134904358e-06, + "loss": 0.8349, + "step": 9486 + }, + { + "epoch": 0.8494711511556327, + "grad_norm": 1.0225274445599308, + "learning_rate": 1.1651137941166169e-06, + "loss": 0.7369, + "step": 9487 + }, + { + "epoch": 0.8495606917007107, + "grad_norm": 0.9453485120651803, + "learning_rate": 1.1637555179046344e-06, + "loss": 0.8088, + "step": 9488 + }, + { + "epoch": 0.8496502322457888, + "grad_norm": 1.0195367076397395, + "learning_rate": 1.1623979849687429e-06, + "loss": 0.8143, + "step": 9489 + }, + { + "epoch": 0.8497397727908669, + "grad_norm": 0.9988113740426068, + "learning_rate": 1.161041195423136e-06, + "loss": 0.8291, + "step": 9490 + }, + { + "epoch": 0.8498293133359449, + "grad_norm": 1.0734114295013308, + "learning_rate": 1.1596851493819383e-06, + "loss": 0.783, + "step": 9491 + }, + { + "epoch": 0.849918853881023, + "grad_norm": 0.9091074497815385, + "learning_rate": 1.1583298469592185e-06, + "loss": 0.8156, + "step": 9492 + }, + { + "epoch": 0.8500083944261011, + "grad_norm": 0.9809529874139203, + "learning_rate": 1.1569752882689766e-06, + "loss": 0.775, + "step": 9493 + }, + { + "epoch": 0.8500979349711791, + "grad_norm": 0.9963326851454292, + "learning_rate": 1.1556214734251592e-06, + "loss": 0.7643, + "step": 9494 + }, + { + "epoch": 0.8501874755162572, + "grad_norm": 1.1062157967736226, + "learning_rate": 1.154268402541644e-06, + "loss": 0.7528, + "step": 9495 + }, + { + "epoch": 0.8502770160613353, + "grad_norm": 1.260644312273016, + "learning_rate": 1.1529160757322432e-06, + "loss": 0.7993, + "step": 9496 + }, + { + "epoch": 0.8503665566064134, + "grad_norm": 0.9599525588341968, + "learning_rate": 1.1515644931107129e-06, + "loss": 0.8222, + "step": 9497 + }, + { + "epoch": 0.8504560971514914, + "grad_norm": 0.962076443847939, + "learning_rate": 1.1502136547907417e-06, + "loss": 0.746, + "step": 9498 + }, + { + "epoch": 0.8505456376965694, + "grad_norm": 1.0153818162669237, + "learning_rate": 1.1488635608859578e-06, + "loss": 0.758, + "step": 9499 + }, + { + "epoch": 0.8506351782416476, + "grad_norm": 0.9075039173324784, + "learning_rate": 1.147514211509929e-06, + "loss": 0.7841, + "step": 9500 + }, + { + "epoch": 0.8507247187867256, + "grad_norm": 0.9724410596319404, + "learning_rate": 1.1461656067761605e-06, + "loss": 0.7745, + "step": 9501 + }, + { + "epoch": 0.8508142593318037, + "grad_norm": 1.073459678086075, + "learning_rate": 1.144817746798086e-06, + "loss": 0.7831, + "step": 9502 + }, + { + "epoch": 0.8509037998768818, + "grad_norm": 0.9569767801514034, + "learning_rate": 1.1434706316890865e-06, + "loss": 0.7383, + "step": 9503 + }, + { + "epoch": 0.8509933404219598, + "grad_norm": 0.9286263866754826, + "learning_rate": 1.1421242615624772e-06, + "loss": 0.7479, + "step": 9504 + }, + { + "epoch": 0.8510828809670379, + "grad_norm": 0.9538416711408632, + "learning_rate": 1.1407786365315076e-06, + "loss": 0.8277, + "step": 9505 + }, + { + "epoch": 0.8511724215121159, + "grad_norm": 1.1806466862913678, + "learning_rate": 1.1394337567093728e-06, + "loss": 0.7816, + "step": 9506 + }, + { + "epoch": 0.8512619620571941, + "grad_norm": 0.9716931585252794, + "learning_rate": 1.1380896222091953e-06, + "loss": 0.7992, + "step": 9507 + }, + { + "epoch": 0.8513515026022721, + "grad_norm": 0.9679859806528697, + "learning_rate": 1.1367462331440404e-06, + "loss": 0.8258, + "step": 9508 + }, + { + "epoch": 0.8514410431473501, + "grad_norm": 1.1031217507479882, + "learning_rate": 1.135403589626909e-06, + "loss": 0.814, + "step": 9509 + }, + { + "epoch": 0.8515305836924282, + "grad_norm": 0.898820820986938, + "learning_rate": 1.1340616917707415e-06, + "loss": 0.7793, + "step": 9510 + }, + { + "epoch": 0.8516201242375063, + "grad_norm": 1.0543523510164359, + "learning_rate": 1.1327205396884123e-06, + "loss": 0.8266, + "step": 9511 + }, + { + "epoch": 0.8517096647825844, + "grad_norm": 0.9046389463712229, + "learning_rate": 1.1313801334927355e-06, + "loss": 0.8173, + "step": 9512 + }, + { + "epoch": 0.8517992053276624, + "grad_norm": 1.3168328610196058, + "learning_rate": 1.1300404732964621e-06, + "loss": 0.789, + "step": 9513 + }, + { + "epoch": 0.8518887458727405, + "grad_norm": 0.8792623060339958, + "learning_rate": 1.1287015592122785e-06, + "loss": 0.8108, + "step": 9514 + }, + { + "epoch": 0.8519782864178186, + "grad_norm": 1.207497985153025, + "learning_rate": 1.1273633913528115e-06, + "loss": 0.769, + "step": 9515 + }, + { + "epoch": 0.8520678269628966, + "grad_norm": 0.9927586457286008, + "learning_rate": 1.1260259698306231e-06, + "loss": 0.766, + "step": 9516 + }, + { + "epoch": 0.8521573675079747, + "grad_norm": 0.9380127407786942, + "learning_rate": 1.1246892947582121e-06, + "loss": 0.8027, + "step": 9517 + }, + { + "epoch": 0.8522469080530528, + "grad_norm": 0.9574665086858727, + "learning_rate": 1.1233533662480156e-06, + "loss": 0.767, + "step": 9518 + }, + { + "epoch": 0.8523364485981308, + "grad_norm": 1.094419084597495, + "learning_rate": 1.1220181844124078e-06, + "loss": 0.8252, + "step": 9519 + }, + { + "epoch": 0.8524259891432089, + "grad_norm": 1.0033028569413718, + "learning_rate": 1.1206837493636992e-06, + "loss": 0.8347, + "step": 9520 + }, + { + "epoch": 0.852515529688287, + "grad_norm": 1.0517820300863763, + "learning_rate": 1.1193500612141384e-06, + "loss": 0.7481, + "step": 9521 + }, + { + "epoch": 0.8526050702333651, + "grad_norm": 0.9510987503277331, + "learning_rate": 1.1180171200759115e-06, + "loss": 0.8137, + "step": 9522 + }, + { + "epoch": 0.8526946107784431, + "grad_norm": 1.0004156751218516, + "learning_rate": 1.11668492606114e-06, + "loss": 0.8213, + "step": 9523 + }, + { + "epoch": 0.8527841513235211, + "grad_norm": 1.095855759420275, + "learning_rate": 1.1153534792818854e-06, + "loss": 0.7361, + "step": 9524 + }, + { + "epoch": 0.8528736918685993, + "grad_norm": 1.073705877262268, + "learning_rate": 1.1140227798501435e-06, + "loss": 0.7933, + "step": 9525 + }, + { + "epoch": 0.8529632324136773, + "grad_norm": 1.0938905108679595, + "learning_rate": 1.112692827877848e-06, + "loss": 0.8222, + "step": 9526 + }, + { + "epoch": 0.8530527729587554, + "grad_norm": 0.9016545239267576, + "learning_rate": 1.111363623476871e-06, + "loss": 0.7955, + "step": 9527 + }, + { + "epoch": 0.8531423135038334, + "grad_norm": 0.9915350967422595, + "learning_rate": 1.1100351667590203e-06, + "loss": 0.8146, + "step": 9528 + }, + { + "epoch": 0.8532318540489116, + "grad_norm": 0.9706926854106749, + "learning_rate": 1.1087074578360424e-06, + "loss": 0.7714, + "step": 9529 + }, + { + "epoch": 0.8533213945939896, + "grad_norm": 0.9480052924543311, + "learning_rate": 1.1073804968196189e-06, + "loss": 0.8199, + "step": 9530 + }, + { + "epoch": 0.8534109351390676, + "grad_norm": 1.040471103733673, + "learning_rate": 1.1060542838213695e-06, + "loss": 0.8255, + "step": 9531 + }, + { + "epoch": 0.8535004756841458, + "grad_norm": 1.0316185773437594, + "learning_rate": 1.1047288189528504e-06, + "loss": 0.7649, + "step": 9532 + }, + { + "epoch": 0.8535900162292238, + "grad_norm": 0.9320963252575724, + "learning_rate": 1.1034041023255581e-06, + "loss": 0.8029, + "step": 9533 + }, + { + "epoch": 0.8536795567743019, + "grad_norm": 1.0485771996100557, + "learning_rate": 1.102080134050918e-06, + "loss": 0.8598, + "step": 9534 + }, + { + "epoch": 0.8537690973193799, + "grad_norm": 1.3059548940731849, + "learning_rate": 1.100756914240303e-06, + "loss": 0.8331, + "step": 9535 + }, + { + "epoch": 0.853858637864458, + "grad_norm": 0.9983426477509885, + "learning_rate": 1.0994344430050163e-06, + "loss": 0.7919, + "step": 9536 + }, + { + "epoch": 0.8539481784095361, + "grad_norm": 1.0386778339035228, + "learning_rate": 1.0981127204563001e-06, + "loss": 0.7822, + "step": 9537 + }, + { + "epoch": 0.8540377189546141, + "grad_norm": 1.2650346217168582, + "learning_rate": 1.0967917467053336e-06, + "loss": 0.7924, + "step": 9538 + }, + { + "epoch": 0.8541272594996923, + "grad_norm": 1.0252441163245603, + "learning_rate": 1.095471521863234e-06, + "loss": 0.7736, + "step": 9539 + }, + { + "epoch": 0.8542168000447703, + "grad_norm": 0.9862055767900356, + "learning_rate": 1.0941520460410482e-06, + "loss": 0.8657, + "step": 9540 + }, + { + "epoch": 0.8543063405898483, + "grad_norm": 0.9664315080025508, + "learning_rate": 1.0928333193497731e-06, + "loss": 0.8062, + "step": 9541 + }, + { + "epoch": 0.8543958811349264, + "grad_norm": 1.136712935526052, + "learning_rate": 1.0915153419003343e-06, + "loss": 0.7886, + "step": 9542 + }, + { + "epoch": 0.8544854216800045, + "grad_norm": 0.9385308992038491, + "learning_rate": 1.0901981138035933e-06, + "loss": 0.8041, + "step": 9543 + }, + { + "epoch": 0.8545749622250826, + "grad_norm": 0.9889571661520725, + "learning_rate": 1.0888816351703557e-06, + "loss": 0.7596, + "step": 9544 + }, + { + "epoch": 0.8546645027701606, + "grad_norm": 0.9887101625764154, + "learning_rate": 1.087565906111354e-06, + "loss": 0.7376, + "step": 9545 + }, + { + "epoch": 0.8547540433152386, + "grad_norm": 1.0800904903172717, + "learning_rate": 1.0862509267372657e-06, + "loss": 0.7742, + "step": 9546 + }, + { + "epoch": 0.8548435838603168, + "grad_norm": 0.9587519000193999, + "learning_rate": 1.0849366971586995e-06, + "loss": 0.849, + "step": 9547 + }, + { + "epoch": 0.8549331244053948, + "grad_norm": 0.9649091094034121, + "learning_rate": 1.0836232174862083e-06, + "loss": 0.8163, + "step": 9548 + }, + { + "epoch": 0.8550226649504729, + "grad_norm": 1.0298647027366474, + "learning_rate": 1.082310487830277e-06, + "loss": 0.7788, + "step": 9549 + }, + { + "epoch": 0.855112205495551, + "grad_norm": 0.9256010130599501, + "learning_rate": 1.0809985083013296e-06, + "loss": 0.7757, + "step": 9550 + }, + { + "epoch": 0.855201746040629, + "grad_norm": 1.0097264214768489, + "learning_rate": 1.0796872790097213e-06, + "loss": 0.8805, + "step": 9551 + }, + { + "epoch": 0.8552912865857071, + "grad_norm": 1.0212327979221512, + "learning_rate": 1.078376800065749e-06, + "loss": 0.8069, + "step": 9552 + }, + { + "epoch": 0.8553808271307851, + "grad_norm": 1.097505244562918, + "learning_rate": 1.0770670715796472e-06, + "loss": 0.8045, + "step": 9553 + }, + { + "epoch": 0.8554703676758633, + "grad_norm": 0.931354645599154, + "learning_rate": 1.0757580936615874e-06, + "loss": 0.8153, + "step": 9554 + }, + { + "epoch": 0.8555599082209413, + "grad_norm": 1.0227330487480157, + "learning_rate": 1.0744498664216774e-06, + "loss": 0.7704, + "step": 9555 + }, + { + "epoch": 0.8556494487660193, + "grad_norm": 0.9051430392192664, + "learning_rate": 1.0731423899699568e-06, + "loss": 0.7721, + "step": 9556 + }, + { + "epoch": 0.8557389893110975, + "grad_norm": 1.013037974239861, + "learning_rate": 1.0718356644164074e-06, + "loss": 0.8074, + "step": 9557 + }, + { + "epoch": 0.8558285298561755, + "grad_norm": 0.9854900190122775, + "learning_rate": 1.0705296898709493e-06, + "loss": 0.7728, + "step": 9558 + }, + { + "epoch": 0.8559180704012536, + "grad_norm": 1.1038421401784437, + "learning_rate": 1.0692244664434326e-06, + "loss": 0.8356, + "step": 9559 + }, + { + "epoch": 0.8560076109463316, + "grad_norm": 1.0371183556966863, + "learning_rate": 1.0679199942436525e-06, + "loss": 0.7895, + "step": 9560 + }, + { + "epoch": 0.8560971514914097, + "grad_norm": 1.0460183665115081, + "learning_rate": 1.066616273381338e-06, + "loss": 0.7496, + "step": 9561 + }, + { + "epoch": 0.8561866920364878, + "grad_norm": 0.9838422391759553, + "learning_rate": 1.065313303966149e-06, + "loss": 0.7957, + "step": 9562 + }, + { + "epoch": 0.8562762325815658, + "grad_norm": 0.9666060392154043, + "learning_rate": 1.0640110861076902e-06, + "loss": 0.7607, + "step": 9563 + }, + { + "epoch": 0.8563657731266439, + "grad_norm": 1.0046538942601368, + "learning_rate": 1.0627096199154985e-06, + "loss": 0.7853, + "step": 9564 + }, + { + "epoch": 0.856455313671722, + "grad_norm": 0.8593984814100597, + "learning_rate": 1.0614089054990474e-06, + "loss": 0.7642, + "step": 9565 + }, + { + "epoch": 0.8565448542168, + "grad_norm": 0.9333816836430744, + "learning_rate": 1.0601089429677547e-06, + "loss": 0.78, + "step": 9566 + }, + { + "epoch": 0.8566343947618781, + "grad_norm": 0.9562053988629583, + "learning_rate": 1.0588097324309643e-06, + "loss": 0.7886, + "step": 9567 + }, + { + "epoch": 0.8567239353069562, + "grad_norm": 0.9292858053625015, + "learning_rate": 1.057511273997962e-06, + "loss": 0.7325, + "step": 9568 + }, + { + "epoch": 0.8568134758520343, + "grad_norm": 1.070072831312537, + "learning_rate": 1.0562135677779694e-06, + "loss": 0.7966, + "step": 9569 + }, + { + "epoch": 0.8569030163971123, + "grad_norm": 0.9931404720942684, + "learning_rate": 1.0549166138801482e-06, + "loss": 0.7941, + "step": 9570 + }, + { + "epoch": 0.8569925569421903, + "grad_norm": 0.9170716929023089, + "learning_rate": 1.0536204124135885e-06, + "loss": 0.7842, + "step": 9571 + }, + { + "epoch": 0.8570820974872685, + "grad_norm": 0.942424492974866, + "learning_rate": 1.0523249634873312e-06, + "loss": 0.7738, + "step": 9572 + }, + { + "epoch": 0.8571716380323465, + "grad_norm": 0.9496521084047362, + "learning_rate": 1.051030267210338e-06, + "loss": 0.8209, + "step": 9573 + }, + { + "epoch": 0.8572611785774246, + "grad_norm": 1.0325117838445033, + "learning_rate": 1.0497363236915158e-06, + "loss": 0.7838, + "step": 9574 + }, + { + "epoch": 0.8573507191225027, + "grad_norm": 0.9354377269349455, + "learning_rate": 1.0484431330397083e-06, + "loss": 0.7551, + "step": 9575 + }, + { + "epoch": 0.8574402596675808, + "grad_norm": 0.9574097071653969, + "learning_rate": 1.0471506953636944e-06, + "loss": 0.7002, + "step": 9576 + }, + { + "epoch": 0.8575298002126588, + "grad_norm": 0.9398283824855922, + "learning_rate": 1.0458590107721889e-06, + "loss": 0.776, + "step": 9577 + }, + { + "epoch": 0.8576193407577368, + "grad_norm": 1.0496664290807773, + "learning_rate": 1.0445680793738444e-06, + "loss": 0.8196, + "step": 9578 + }, + { + "epoch": 0.857708881302815, + "grad_norm": 0.9010200824606396, + "learning_rate": 1.0432779012772498e-06, + "loss": 0.7723, + "step": 9579 + }, + { + "epoch": 0.857798421847893, + "grad_norm": 1.0881859468403354, + "learning_rate": 1.0419884765909315e-06, + "loss": 0.8137, + "step": 9580 + }, + { + "epoch": 0.857887962392971, + "grad_norm": 0.9352122452571657, + "learning_rate": 1.0406998054233507e-06, + "loss": 0.7587, + "step": 9581 + }, + { + "epoch": 0.8579775029380491, + "grad_norm": 0.9866732237796213, + "learning_rate": 1.0394118878829063e-06, + "loss": 0.8577, + "step": 9582 + }, + { + "epoch": 0.8580670434831272, + "grad_norm": 0.9775160907078001, + "learning_rate": 1.0381247240779346e-06, + "loss": 0.8001, + "step": 9583 + }, + { + "epoch": 0.8581565840282053, + "grad_norm": 0.9103113700857707, + "learning_rate": 1.036838314116706e-06, + "loss": 0.8213, + "step": 9584 + }, + { + "epoch": 0.8582461245732833, + "grad_norm": 0.9479596697638377, + "learning_rate": 1.0355526581074316e-06, + "loss": 0.7652, + "step": 9585 + }, + { + "epoch": 0.8583356651183615, + "grad_norm": 1.0986459290781252, + "learning_rate": 1.0342677561582536e-06, + "loss": 0.8159, + "step": 9586 + }, + { + "epoch": 0.8584252056634395, + "grad_norm": 0.9790392434003694, + "learning_rate": 1.032983608377256e-06, + "loss": 0.8185, + "step": 9587 + }, + { + "epoch": 0.8585147462085175, + "grad_norm": 0.9559111704954044, + "learning_rate": 1.0317002148724564e-06, + "loss": 0.8229, + "step": 9588 + }, + { + "epoch": 0.8586042867535956, + "grad_norm": 1.0042402745486412, + "learning_rate": 1.0304175757518097e-06, + "loss": 0.7894, + "step": 9589 + }, + { + "epoch": 0.8586938272986737, + "grad_norm": 0.9779955369643236, + "learning_rate": 1.0291356911232075e-06, + "loss": 0.7651, + "step": 9590 + }, + { + "epoch": 0.8587833678437518, + "grad_norm": 0.9577369298652622, + "learning_rate": 1.0278545610944778e-06, + "loss": 0.786, + "step": 9591 + }, + { + "epoch": 0.8588729083888298, + "grad_norm": 0.9522307660730169, + "learning_rate": 1.0265741857733846e-06, + "loss": 0.7475, + "step": 9592 + }, + { + "epoch": 0.8589624489339079, + "grad_norm": 0.9623770285700268, + "learning_rate": 1.0252945652676305e-06, + "loss": 0.7936, + "step": 9593 + }, + { + "epoch": 0.859051989478986, + "grad_norm": 1.0364636348843959, + "learning_rate": 1.0240156996848483e-06, + "loss": 0.8294, + "step": 9594 + }, + { + "epoch": 0.859141530024064, + "grad_norm": 1.0200836930309878, + "learning_rate": 1.0227375891326175e-06, + "loss": 0.8226, + "step": 9595 + }, + { + "epoch": 0.859231070569142, + "grad_norm": 0.9032347816067988, + "learning_rate": 1.0214602337184465e-06, + "loss": 0.7785, + "step": 9596 + }, + { + "epoch": 0.8593206111142202, + "grad_norm": 1.1752470031322075, + "learning_rate": 1.0201836335497816e-06, + "loss": 0.8055, + "step": 9597 + }, + { + "epoch": 0.8594101516592982, + "grad_norm": 0.9165920602098242, + "learning_rate": 1.0189077887340072e-06, + "loss": 0.7775, + "step": 9598 + }, + { + "epoch": 0.8594996922043763, + "grad_norm": 0.9845016126791963, + "learning_rate": 1.0176326993784447e-06, + "loss": 0.7846, + "step": 9599 + }, + { + "epoch": 0.8595892327494543, + "grad_norm": 0.9971936330820526, + "learning_rate": 1.0163583655903464e-06, + "loss": 0.8439, + "step": 9600 + }, + { + "epoch": 0.8596787732945325, + "grad_norm": 0.9516604741793241, + "learning_rate": 1.0150847874769065e-06, + "loss": 0.7734, + "step": 9601 + }, + { + "epoch": 0.8597683138396105, + "grad_norm": 0.9378683326908789, + "learning_rate": 1.013811965145256e-06, + "loss": 0.8166, + "step": 9602 + }, + { + "epoch": 0.8598578543846885, + "grad_norm": 0.9640512891341534, + "learning_rate": 1.0125398987024605e-06, + "loss": 0.7766, + "step": 9603 + }, + { + "epoch": 0.8599473949297667, + "grad_norm": 0.9562342692896773, + "learning_rate": 1.0112685882555229e-06, + "loss": 0.7839, + "step": 9604 + }, + { + "epoch": 0.8600369354748447, + "grad_norm": 0.9354697769660194, + "learning_rate": 1.009998033911378e-06, + "loss": 0.7919, + "step": 9605 + }, + { + "epoch": 0.8601264760199228, + "grad_norm": 1.0597545611253751, + "learning_rate": 1.0087282357769024e-06, + "loss": 0.8591, + "step": 9606 + }, + { + "epoch": 0.8602160165650008, + "grad_norm": 0.9879164144454476, + "learning_rate": 1.0074591939589063e-06, + "loss": 0.8286, + "step": 9607 + }, + { + "epoch": 0.8603055571100789, + "grad_norm": 0.9181539111383245, + "learning_rate": 1.0061909085641397e-06, + "loss": 0.7955, + "step": 9608 + }, + { + "epoch": 0.860395097655157, + "grad_norm": 0.9095216392409001, + "learning_rate": 1.0049233796992874e-06, + "loss": 0.8216, + "step": 9609 + }, + { + "epoch": 0.860484638200235, + "grad_norm": 0.9453638623526938, + "learning_rate": 1.0036566074709686e-06, + "loss": 0.7508, + "step": 9610 + }, + { + "epoch": 0.8605741787453132, + "grad_norm": 0.9383002865255036, + "learning_rate": 1.002390591985738e-06, + "loss": 0.8029, + "step": 9611 + }, + { + "epoch": 0.8606637192903912, + "grad_norm": 1.0401824576994183, + "learning_rate": 1.0011253333500903e-06, + "loss": 0.7303, + "step": 9612 + }, + { + "epoch": 0.8607532598354692, + "grad_norm": 0.993142229029005, + "learning_rate": 9.99860831670454e-07, + "loss": 0.8285, + "step": 9613 + }, + { + "epoch": 0.8608428003805473, + "grad_norm": 1.0858151847039264, + "learning_rate": 9.985970870531968e-07, + "loss": 0.7993, + "step": 9614 + }, + { + "epoch": 0.8609323409256254, + "grad_norm": 0.9707399542360674, + "learning_rate": 9.973340996046211e-07, + "loss": 0.7869, + "step": 9615 + }, + { + "epoch": 0.8610218814707035, + "grad_norm": 0.9637358422273686, + "learning_rate": 9.960718694309623e-07, + "loss": 0.8391, + "step": 9616 + }, + { + "epoch": 0.8611114220157815, + "grad_norm": 0.9506965384047706, + "learning_rate": 9.94810396638397e-07, + "loss": 0.7457, + "step": 9617 + }, + { + "epoch": 0.8612009625608595, + "grad_norm": 1.0064334990522585, + "learning_rate": 9.935496813330358e-07, + "loss": 0.8612, + "step": 9618 + }, + { + "epoch": 0.8612905031059377, + "grad_norm": 1.04671898858899, + "learning_rate": 9.92289723620924e-07, + "loss": 0.7953, + "step": 9619 + }, + { + "epoch": 0.8613800436510157, + "grad_norm": 0.966471857702878, + "learning_rate": 9.910305236080498e-07, + "loss": 0.7758, + "step": 9620 + }, + { + "epoch": 0.8614695841960938, + "grad_norm": 0.9169349444127871, + "learning_rate": 9.89772081400332e-07, + "loss": 0.7814, + "step": 9621 + }, + { + "epoch": 0.8615591247411719, + "grad_norm": 0.9684515908038033, + "learning_rate": 9.885143971036226e-07, + "loss": 0.8274, + "step": 9622 + }, + { + "epoch": 0.86164866528625, + "grad_norm": 1.0023198485233595, + "learning_rate": 9.87257470823717e-07, + "loss": 0.8158, + "step": 9623 + }, + { + "epoch": 0.861738205831328, + "grad_norm": 1.0060778787485087, + "learning_rate": 9.860013026663428e-07, + "loss": 0.7653, + "step": 9624 + }, + { + "epoch": 0.861827746376406, + "grad_norm": 0.9039885261115476, + "learning_rate": 9.847458927371623e-07, + "loss": 0.7618, + "step": 9625 + }, + { + "epoch": 0.8619172869214842, + "grad_norm": 1.0048151482667587, + "learning_rate": 9.83491241141784e-07, + "loss": 0.787, + "step": 9626 + }, + { + "epoch": 0.8620068274665622, + "grad_norm": 0.913490046675313, + "learning_rate": 9.822373479857383e-07, + "loss": 0.8387, + "step": 9627 + }, + { + "epoch": 0.8620963680116402, + "grad_norm": 0.9323123974510575, + "learning_rate": 9.809842133745006e-07, + "loss": 0.8247, + "step": 9628 + }, + { + "epoch": 0.8621859085567184, + "grad_norm": 0.8961867270554208, + "learning_rate": 9.797318374134811e-07, + "loss": 0.7931, + "step": 9629 + }, + { + "epoch": 0.8622754491017964, + "grad_norm": 1.0336249865529368, + "learning_rate": 9.784802202080246e-07, + "loss": 0.7809, + "step": 9630 + }, + { + "epoch": 0.8623649896468745, + "grad_norm": 0.9762678791967343, + "learning_rate": 9.772293618634131e-07, + "loss": 0.8322, + "step": 9631 + }, + { + "epoch": 0.8624545301919525, + "grad_norm": 1.0127184917535343, + "learning_rate": 9.759792624848662e-07, + "loss": 0.7968, + "step": 9632 + }, + { + "epoch": 0.8625440707370307, + "grad_norm": 1.0072060920571084, + "learning_rate": 9.747299221775363e-07, + "loss": 0.8243, + "step": 9633 + }, + { + "epoch": 0.8626336112821087, + "grad_norm": 0.97938694648066, + "learning_rate": 9.734813410465149e-07, + "loss": 0.7839, + "step": 9634 + }, + { + "epoch": 0.8627231518271867, + "grad_norm": 1.0633339897191998, + "learning_rate": 9.72233519196828e-07, + "loss": 0.8267, + "step": 9635 + }, + { + "epoch": 0.8628126923722648, + "grad_norm": 0.9832441241606009, + "learning_rate": 9.709864567334394e-07, + "loss": 0.8166, + "step": 9636 + }, + { + "epoch": 0.8629022329173429, + "grad_norm": 0.9087356822438557, + "learning_rate": 9.697401537612472e-07, + "loss": 0.8019, + "step": 9637 + }, + { + "epoch": 0.862991773462421, + "grad_norm": 1.0948780341908522, + "learning_rate": 9.684946103850856e-07, + "loss": 0.7553, + "step": 9638 + }, + { + "epoch": 0.863081314007499, + "grad_norm": 0.9516049107709965, + "learning_rate": 9.672498267097263e-07, + "loss": 0.7899, + "step": 9639 + }, + { + "epoch": 0.8631708545525771, + "grad_norm": 1.0802748806367994, + "learning_rate": 9.660058028398766e-07, + "loss": 0.8156, + "step": 9640 + }, + { + "epoch": 0.8632603950976552, + "grad_norm": 1.5291317730117053, + "learning_rate": 9.647625388801806e-07, + "loss": 0.7498, + "step": 9641 + }, + { + "epoch": 0.8633499356427332, + "grad_norm": 1.042043481654263, + "learning_rate": 9.635200349352159e-07, + "loss": 0.8149, + "step": 9642 + }, + { + "epoch": 0.8634394761878113, + "grad_norm": 1.0495975206915507, + "learning_rate": 9.622782911094985e-07, + "loss": 0.8296, + "step": 9643 + }, + { + "epoch": 0.8635290167328894, + "grad_norm": 0.9364997658852079, + "learning_rate": 9.610373075074808e-07, + "loss": 0.7393, + "step": 9644 + }, + { + "epoch": 0.8636185572779674, + "grad_norm": 1.03187591297213, + "learning_rate": 9.59797084233548e-07, + "loss": 0.7791, + "step": 9645 + }, + { + "epoch": 0.8637080978230455, + "grad_norm": 0.8710400080566761, + "learning_rate": 9.585576213920267e-07, + "loss": 0.777, + "step": 9646 + }, + { + "epoch": 0.8637976383681236, + "grad_norm": 0.8767545858490539, + "learning_rate": 9.573189190871735e-07, + "loss": 0.7297, + "step": 9647 + }, + { + "epoch": 0.8638871789132017, + "grad_norm": 0.9918131614146409, + "learning_rate": 9.560809774231872e-07, + "loss": 0.8091, + "step": 9648 + }, + { + "epoch": 0.8639767194582797, + "grad_norm": 0.9586679312276287, + "learning_rate": 9.548437965041957e-07, + "loss": 0.8301, + "step": 9649 + }, + { + "epoch": 0.8640662600033577, + "grad_norm": 1.2369426522401579, + "learning_rate": 9.536073764342701e-07, + "loss": 0.7837, + "step": 9650 + }, + { + "epoch": 0.8641558005484359, + "grad_norm": 0.9589246993903835, + "learning_rate": 9.523717173174118e-07, + "loss": 0.7958, + "step": 9651 + }, + { + "epoch": 0.8642453410935139, + "grad_norm": 0.9134175670755973, + "learning_rate": 9.511368192575609e-07, + "loss": 0.828, + "step": 9652 + }, + { + "epoch": 0.864334881638592, + "grad_norm": 0.9424394933401217, + "learning_rate": 9.499026823585955e-07, + "loss": 0.8123, + "step": 9653 + }, + { + "epoch": 0.86442442218367, + "grad_norm": 1.0897698967553955, + "learning_rate": 9.486693067243225e-07, + "loss": 0.7554, + "step": 9654 + }, + { + "epoch": 0.8645139627287481, + "grad_norm": 0.9251022065648881, + "learning_rate": 9.474366924584899e-07, + "loss": 0.7939, + "step": 9655 + }, + { + "epoch": 0.8646035032738262, + "grad_norm": 0.9426288892078449, + "learning_rate": 9.46204839664786e-07, + "loss": 0.8026, + "step": 9656 + }, + { + "epoch": 0.8646930438189042, + "grad_norm": 0.9831841895862496, + "learning_rate": 9.449737484468258e-07, + "loss": 0.8024, + "step": 9657 + }, + { + "epoch": 0.8647825843639824, + "grad_norm": 0.9674842315793059, + "learning_rate": 9.437434189081674e-07, + "loss": 0.8371, + "step": 9658 + }, + { + "epoch": 0.8648721249090604, + "grad_norm": 1.0366789998960846, + "learning_rate": 9.425138511523024e-07, + "loss": 0.7827, + "step": 9659 + }, + { + "epoch": 0.8649616654541384, + "grad_norm": 0.9181265540012836, + "learning_rate": 9.41285045282655e-07, + "loss": 0.7807, + "step": 9660 + }, + { + "epoch": 0.8650512059992165, + "grad_norm": 1.0117389879512924, + "learning_rate": 9.400570014025879e-07, + "loss": 0.8397, + "step": 9661 + }, + { + "epoch": 0.8651407465442946, + "grad_norm": 0.9929570364874514, + "learning_rate": 9.388297196154039e-07, + "loss": 0.7283, + "step": 9662 + }, + { + "epoch": 0.8652302870893727, + "grad_norm": 1.114845567276967, + "learning_rate": 9.376032000243362e-07, + "loss": 0.7708, + "step": 9663 + }, + { + "epoch": 0.8653198276344507, + "grad_norm": 2.2909094024800214, + "learning_rate": 9.363774427325578e-07, + "loss": 0.8074, + "step": 9664 + }, + { + "epoch": 0.8654093681795287, + "grad_norm": 0.9759099478725024, + "learning_rate": 9.351524478431717e-07, + "loss": 0.822, + "step": 9665 + }, + { + "epoch": 0.8654989087246069, + "grad_norm": 1.015316668681043, + "learning_rate": 9.339282154592211e-07, + "loss": 0.826, + "step": 9666 + }, + { + "epoch": 0.8655884492696849, + "grad_norm": 0.8693365140495327, + "learning_rate": 9.327047456836835e-07, + "loss": 0.7325, + "step": 9667 + }, + { + "epoch": 0.865677989814763, + "grad_norm": 0.9521801876254858, + "learning_rate": 9.314820386194778e-07, + "loss": 0.8801, + "step": 9668 + }, + { + "epoch": 0.8657675303598411, + "grad_norm": 1.078156932076896, + "learning_rate": 9.302600943694507e-07, + "loss": 0.7804, + "step": 9669 + }, + { + "epoch": 0.8658570709049191, + "grad_norm": 0.949543342533609, + "learning_rate": 9.290389130363908e-07, + "loss": 0.7521, + "step": 9670 + }, + { + "epoch": 0.8659466114499972, + "grad_norm": 0.9925034754511334, + "learning_rate": 9.278184947230162e-07, + "loss": 0.8337, + "step": 9671 + }, + { + "epoch": 0.8660361519950752, + "grad_norm": 0.9818205812626446, + "learning_rate": 9.26598839531987e-07, + "loss": 0.8091, + "step": 9672 + }, + { + "epoch": 0.8661256925401534, + "grad_norm": 0.8863572868773191, + "learning_rate": 9.253799475658931e-07, + "loss": 0.8338, + "step": 9673 + }, + { + "epoch": 0.8662152330852314, + "grad_norm": 0.9274481257642485, + "learning_rate": 9.241618189272683e-07, + "loss": 0.7757, + "step": 9674 + }, + { + "epoch": 0.8663047736303094, + "grad_norm": 1.097303224698927, + "learning_rate": 9.229444537185784e-07, + "loss": 0.7591, + "step": 9675 + }, + { + "epoch": 0.8663943141753876, + "grad_norm": 0.953171076171005, + "learning_rate": 9.217278520422202e-07, + "loss": 0.8434, + "step": 9676 + }, + { + "epoch": 0.8664838547204656, + "grad_norm": 1.0202255044836142, + "learning_rate": 9.205120140005309e-07, + "loss": 0.7461, + "step": 9677 + }, + { + "epoch": 0.8665733952655437, + "grad_norm": 0.9564295151387561, + "learning_rate": 9.19296939695783e-07, + "loss": 0.8209, + "step": 9678 + }, + { + "epoch": 0.8666629358106217, + "grad_norm": 0.9536856667457038, + "learning_rate": 9.180826292301837e-07, + "loss": 0.8111, + "step": 9679 + }, + { + "epoch": 0.8667524763556999, + "grad_norm": 1.0240962964789941, + "learning_rate": 9.168690827058813e-07, + "loss": 0.8263, + "step": 9680 + }, + { + "epoch": 0.8668420169007779, + "grad_norm": 1.0158430463736017, + "learning_rate": 9.15656300224953e-07, + "loss": 0.7447, + "step": 9681 + }, + { + "epoch": 0.8669315574458559, + "grad_norm": 0.9103247559027354, + "learning_rate": 9.144442818894117e-07, + "loss": 0.8271, + "step": 9682 + }, + { + "epoch": 0.867021097990934, + "grad_norm": 0.9513142310063918, + "learning_rate": 9.132330278012114e-07, + "loss": 0.8023, + "step": 9683 + }, + { + "epoch": 0.8671106385360121, + "grad_norm": 0.9495255104532422, + "learning_rate": 9.120225380622372e-07, + "loss": 0.8098, + "step": 9684 + }, + { + "epoch": 0.8672001790810902, + "grad_norm": 1.550329171346597, + "learning_rate": 9.10812812774311e-07, + "loss": 0.8796, + "step": 9685 + }, + { + "epoch": 0.8672897196261682, + "grad_norm": 1.0227010042693285, + "learning_rate": 9.096038520391936e-07, + "loss": 0.8072, + "step": 9686 + }, + { + "epoch": 0.8673792601712463, + "grad_norm": 1.0316099731365584, + "learning_rate": 9.08395655958576e-07, + "loss": 0.7486, + "step": 9687 + }, + { + "epoch": 0.8674688007163244, + "grad_norm": 1.0024889513637125, + "learning_rate": 9.071882246340902e-07, + "loss": 0.7708, + "step": 9688 + }, + { + "epoch": 0.8675583412614024, + "grad_norm": 1.0198861443608758, + "learning_rate": 9.059815581672993e-07, + "loss": 0.8035, + "step": 9689 + }, + { + "epoch": 0.8676478818064804, + "grad_norm": 1.0078690570358035, + "learning_rate": 9.047756566597055e-07, + "loss": 0.8069, + "step": 9690 + }, + { + "epoch": 0.8677374223515586, + "grad_norm": 0.9510465944103557, + "learning_rate": 9.035705202127443e-07, + "loss": 0.7994, + "step": 9691 + }, + { + "epoch": 0.8678269628966366, + "grad_norm": 1.0284646894086966, + "learning_rate": 9.02366148927789e-07, + "loss": 0.8354, + "step": 9692 + }, + { + "epoch": 0.8679165034417147, + "grad_norm": 1.0977158614859097, + "learning_rate": 9.011625429061455e-07, + "loss": 0.7892, + "step": 9693 + }, + { + "epoch": 0.8680060439867928, + "grad_norm": 0.9744013668506387, + "learning_rate": 8.999597022490603e-07, + "loss": 0.8258, + "step": 9694 + }, + { + "epoch": 0.8680955845318709, + "grad_norm": 1.2154247075048843, + "learning_rate": 8.987576270577092e-07, + "loss": 0.7983, + "step": 9695 + }, + { + "epoch": 0.8681851250769489, + "grad_norm": 1.0794590426208217, + "learning_rate": 8.975563174332091e-07, + "loss": 0.8397, + "step": 9696 + }, + { + "epoch": 0.8682746656220269, + "grad_norm": 0.9593467168555687, + "learning_rate": 8.963557734766082e-07, + "loss": 0.8063, + "step": 9697 + }, + { + "epoch": 0.8683642061671051, + "grad_norm": 1.0347340641383724, + "learning_rate": 8.951559952888944e-07, + "loss": 0.7489, + "step": 9698 + }, + { + "epoch": 0.8684537467121831, + "grad_norm": 0.9038258764355297, + "learning_rate": 8.939569829709882e-07, + "loss": 0.7857, + "step": 9699 + }, + { + "epoch": 0.8685432872572612, + "grad_norm": 1.000410913283481, + "learning_rate": 8.927587366237467e-07, + "loss": 0.788, + "step": 9700 + }, + { + "epoch": 0.8686328278023392, + "grad_norm": 0.9804602115083662, + "learning_rate": 8.915612563479625e-07, + "loss": 0.7161, + "step": 9701 + }, + { + "epoch": 0.8687223683474173, + "grad_norm": 1.066161848935821, + "learning_rate": 8.903645422443641e-07, + "loss": 0.7849, + "step": 9702 + }, + { + "epoch": 0.8688119088924954, + "grad_norm": 1.0428819049132827, + "learning_rate": 8.891685944136141e-07, + "loss": 0.798, + "step": 9703 + }, + { + "epoch": 0.8689014494375734, + "grad_norm": 0.9442231980705521, + "learning_rate": 8.879734129563133e-07, + "loss": 0.8337, + "step": 9704 + }, + { + "epoch": 0.8689909899826516, + "grad_norm": 1.0241257729361417, + "learning_rate": 8.867789979729947e-07, + "loss": 0.7594, + "step": 9705 + }, + { + "epoch": 0.8690805305277296, + "grad_norm": 0.8485619026589344, + "learning_rate": 8.855853495641309e-07, + "loss": 0.732, + "step": 9706 + }, + { + "epoch": 0.8691700710728076, + "grad_norm": 0.9972226368388587, + "learning_rate": 8.843924678301253e-07, + "loss": 0.8112, + "step": 9707 + }, + { + "epoch": 0.8692596116178857, + "grad_norm": 1.196430818881917, + "learning_rate": 8.832003528713218e-07, + "loss": 0.7397, + "step": 9708 + }, + { + "epoch": 0.8693491521629638, + "grad_norm": 1.064788671067656, + "learning_rate": 8.820090047879926e-07, + "loss": 0.8284, + "step": 9709 + }, + { + "epoch": 0.8694386927080419, + "grad_norm": 1.0057104727753952, + "learning_rate": 8.80818423680354e-07, + "loss": 0.8017, + "step": 9710 + }, + { + "epoch": 0.8695282332531199, + "grad_norm": 0.9981387630261437, + "learning_rate": 8.79628609648554e-07, + "loss": 0.7768, + "step": 9711 + }, + { + "epoch": 0.869617773798198, + "grad_norm": 0.9220572838316972, + "learning_rate": 8.784395627926734e-07, + "loss": 0.7741, + "step": 9712 + }, + { + "epoch": 0.8697073143432761, + "grad_norm": 1.1155381554749546, + "learning_rate": 8.772512832127355e-07, + "loss": 0.8101, + "step": 9713 + }, + { + "epoch": 0.8697968548883541, + "grad_norm": 1.2985708180177682, + "learning_rate": 8.760637710086884e-07, + "loss": 0.8478, + "step": 9714 + }, + { + "epoch": 0.8698863954334322, + "grad_norm": 0.9726915265661399, + "learning_rate": 8.74877026280424e-07, + "loss": 0.824, + "step": 9715 + }, + { + "epoch": 0.8699759359785103, + "grad_norm": 0.9993378812328921, + "learning_rate": 8.736910491277694e-07, + "loss": 0.8225, + "step": 9716 + }, + { + "epoch": 0.8700654765235883, + "grad_norm": 0.922964843439431, + "learning_rate": 8.725058396504837e-07, + "loss": 0.7618, + "step": 9717 + }, + { + "epoch": 0.8701550170686664, + "grad_norm": 0.8623185804931164, + "learning_rate": 8.713213979482626e-07, + "loss": 0.7768, + "step": 9718 + }, + { + "epoch": 0.8702445576137444, + "grad_norm": 0.9977991938017136, + "learning_rate": 8.701377241207409e-07, + "loss": 0.7786, + "step": 9719 + }, + { + "epoch": 0.8703340981588226, + "grad_norm": 1.0002034440085878, + "learning_rate": 8.68954818267479e-07, + "loss": 0.8229, + "step": 9720 + }, + { + "epoch": 0.8704236387039006, + "grad_norm": 0.90750303976621, + "learning_rate": 8.677726804879816e-07, + "loss": 0.7458, + "step": 9721 + }, + { + "epoch": 0.8705131792489786, + "grad_norm": 1.3617394982505355, + "learning_rate": 8.665913108816882e-07, + "loss": 0.8176, + "step": 9722 + }, + { + "epoch": 0.8706027197940568, + "grad_norm": 0.961764787627757, + "learning_rate": 8.654107095479713e-07, + "loss": 0.8158, + "step": 9723 + }, + { + "epoch": 0.8706922603391348, + "grad_norm": 0.9783296713225507, + "learning_rate": 8.642308765861407e-07, + "loss": 0.7965, + "step": 9724 + }, + { + "epoch": 0.8707818008842129, + "grad_norm": 0.9744647398972225, + "learning_rate": 8.630518120954357e-07, + "loss": 0.7608, + "step": 9725 + }, + { + "epoch": 0.8708713414292909, + "grad_norm": 1.0460643325578858, + "learning_rate": 8.618735161750369e-07, + "loss": 0.8148, + "step": 9726 + }, + { + "epoch": 0.870960881974369, + "grad_norm": 1.2722133471352022, + "learning_rate": 8.606959889240584e-07, + "loss": 0.8515, + "step": 9727 + }, + { + "epoch": 0.8710504225194471, + "grad_norm": 1.2595857308109049, + "learning_rate": 8.595192304415534e-07, + "loss": 0.8041, + "step": 9728 + }, + { + "epoch": 0.8711399630645251, + "grad_norm": 1.0636581024202847, + "learning_rate": 8.583432408265036e-07, + "loss": 0.8384, + "step": 9729 + }, + { + "epoch": 0.8712295036096033, + "grad_norm": 1.0691356028166792, + "learning_rate": 8.571680201778321e-07, + "loss": 0.7986, + "step": 9730 + }, + { + "epoch": 0.8713190441546813, + "grad_norm": 1.136833385893806, + "learning_rate": 8.559935685943921e-07, + "loss": 0.8618, + "step": 9731 + }, + { + "epoch": 0.8714085846997593, + "grad_norm": 1.0968095491316403, + "learning_rate": 8.548198861749757e-07, + "loss": 0.7985, + "step": 9732 + }, + { + "epoch": 0.8714981252448374, + "grad_norm": 0.9193782074151037, + "learning_rate": 8.536469730183061e-07, + "loss": 0.8303, + "step": 9733 + }, + { + "epoch": 0.8715876657899155, + "grad_norm": 1.031783788471677, + "learning_rate": 8.5247482922305e-07, + "loss": 0.7978, + "step": 9734 + }, + { + "epoch": 0.8716772063349936, + "grad_norm": 0.9726529757745428, + "learning_rate": 8.513034548878041e-07, + "loss": 0.7301, + "step": 9735 + }, + { + "epoch": 0.8717667468800716, + "grad_norm": 0.9697544033645193, + "learning_rate": 8.501328501110972e-07, + "loss": 0.823, + "step": 9736 + }, + { + "epoch": 0.8718562874251496, + "grad_norm": 0.9303911750766886, + "learning_rate": 8.489630149913985e-07, + "loss": 0.7734, + "step": 9737 + }, + { + "epoch": 0.8719458279702278, + "grad_norm": 1.0173442582118148, + "learning_rate": 8.477939496271092e-07, + "loss": 0.7582, + "step": 9738 + }, + { + "epoch": 0.8720353685153058, + "grad_norm": 0.9876091508872713, + "learning_rate": 8.466256541165696e-07, + "loss": 0.8469, + "step": 9739 + }, + { + "epoch": 0.8721249090603839, + "grad_norm": 0.9311107004376196, + "learning_rate": 8.454581285580499e-07, + "loss": 0.8082, + "step": 9740 + }, + { + "epoch": 0.872214449605462, + "grad_norm": 1.0229410973244177, + "learning_rate": 8.442913730497638e-07, + "loss": 0.85, + "step": 9741 + }, + { + "epoch": 0.87230399015054, + "grad_norm": 1.0575898092150893, + "learning_rate": 8.431253876898504e-07, + "loss": 0.8008, + "step": 9742 + }, + { + "epoch": 0.8723935306956181, + "grad_norm": 0.9003071081156029, + "learning_rate": 8.419601725763893e-07, + "loss": 0.7734, + "step": 9743 + }, + { + "epoch": 0.8724830712406961, + "grad_norm": 0.9588727888795702, + "learning_rate": 8.407957278073952e-07, + "loss": 0.7364, + "step": 9744 + }, + { + "epoch": 0.8725726117857743, + "grad_norm": 1.0986648690827348, + "learning_rate": 8.396320534808178e-07, + "loss": 0.8344, + "step": 9745 + }, + { + "epoch": 0.8726621523308523, + "grad_norm": 0.9095840509931644, + "learning_rate": 8.384691496945408e-07, + "loss": 0.8103, + "step": 9746 + }, + { + "epoch": 0.8727516928759304, + "grad_norm": 1.0882825966551244, + "learning_rate": 8.373070165463837e-07, + "loss": 0.8066, + "step": 9747 + }, + { + "epoch": 0.8728412334210085, + "grad_norm": 0.96475108066984, + "learning_rate": 8.361456541341028e-07, + "loss": 0.7983, + "step": 9748 + }, + { + "epoch": 0.8729307739660865, + "grad_norm": 0.9007587428518711, + "learning_rate": 8.349850625553868e-07, + "loss": 0.8187, + "step": 9749 + }, + { + "epoch": 0.8730203145111646, + "grad_norm": 0.9335155387730634, + "learning_rate": 8.338252419078608e-07, + "loss": 0.7526, + "step": 9750 + }, + { + "epoch": 0.8731098550562426, + "grad_norm": 1.0438817038966874, + "learning_rate": 8.326661922890855e-07, + "loss": 0.7631, + "step": 9751 + }, + { + "epoch": 0.8731993956013208, + "grad_norm": 0.9964501776378016, + "learning_rate": 8.315079137965576e-07, + "loss": 0.7937, + "step": 9752 + }, + { + "epoch": 0.8732889361463988, + "grad_norm": 0.944569110424118, + "learning_rate": 8.303504065277057e-07, + "loss": 0.7671, + "step": 9753 + }, + { + "epoch": 0.8733784766914768, + "grad_norm": 1.0045386260209057, + "learning_rate": 8.291936705798964e-07, + "loss": 0.7597, + "step": 9754 + }, + { + "epoch": 0.8734680172365549, + "grad_norm": 0.9819509726408752, + "learning_rate": 8.280377060504308e-07, + "loss": 0.817, + "step": 9755 + }, + { + "epoch": 0.873557557781633, + "grad_norm": 1.124808700625049, + "learning_rate": 8.268825130365454e-07, + "loss": 0.8299, + "step": 9756 + }, + { + "epoch": 0.8736470983267111, + "grad_norm": 0.9346114983164763, + "learning_rate": 8.257280916354093e-07, + "loss": 0.835, + "step": 9757 + }, + { + "epoch": 0.8737366388717891, + "grad_norm": 0.9537586993383416, + "learning_rate": 8.245744419441304e-07, + "loss": 0.8182, + "step": 9758 + }, + { + "epoch": 0.8738261794168672, + "grad_norm": 1.2773304723099699, + "learning_rate": 8.234215640597498e-07, + "loss": 0.7948, + "step": 9759 + }, + { + "epoch": 0.8739157199619453, + "grad_norm": 1.0250542574123196, + "learning_rate": 8.222694580792434e-07, + "loss": 0.8192, + "step": 9760 + }, + { + "epoch": 0.8740052605070233, + "grad_norm": 0.9220182331191347, + "learning_rate": 8.211181240995225e-07, + "loss": 0.7724, + "step": 9761 + }, + { + "epoch": 0.8740948010521014, + "grad_norm": 0.9358149522953858, + "learning_rate": 8.199675622174342e-07, + "loss": 0.837, + "step": 9762 + }, + { + "epoch": 0.8741843415971795, + "grad_norm": 0.9053557277607059, + "learning_rate": 8.188177725297585e-07, + "loss": 0.7939, + "step": 9763 + }, + { + "epoch": 0.8742738821422575, + "grad_norm": 0.972740016786196, + "learning_rate": 8.176687551332141e-07, + "loss": 0.8347, + "step": 9764 + }, + { + "epoch": 0.8743634226873356, + "grad_norm": 1.0162046063925805, + "learning_rate": 8.1652051012445e-07, + "loss": 0.847, + "step": 9765 + }, + { + "epoch": 0.8744529632324137, + "grad_norm": 0.9539888776710241, + "learning_rate": 8.153730376000557e-07, + "loss": 0.8359, + "step": 9766 + }, + { + "epoch": 0.8745425037774918, + "grad_norm": 0.9561572907391523, + "learning_rate": 8.142263376565518e-07, + "loss": 0.8139, + "step": 9767 + }, + { + "epoch": 0.8746320443225698, + "grad_norm": 1.0036655042734668, + "learning_rate": 8.130804103903956e-07, + "loss": 0.8099, + "step": 9768 + }, + { + "epoch": 0.8747215848676478, + "grad_norm": 0.9705083777095447, + "learning_rate": 8.119352558979742e-07, + "loss": 0.8211, + "step": 9769 + }, + { + "epoch": 0.874811125412726, + "grad_norm": 1.1687135551347951, + "learning_rate": 8.107908742756198e-07, + "loss": 0.742, + "step": 9770 + }, + { + "epoch": 0.874900665957804, + "grad_norm": 0.9558009318580759, + "learning_rate": 8.09647265619592e-07, + "loss": 0.7538, + "step": 9771 + }, + { + "epoch": 0.8749902065028821, + "grad_norm": 1.045613323224456, + "learning_rate": 8.08504430026088e-07, + "loss": 0.7566, + "step": 9772 + }, + { + "epoch": 0.8750797470479601, + "grad_norm": 0.946625502604746, + "learning_rate": 8.07362367591239e-07, + "loss": 0.7717, + "step": 9773 + }, + { + "epoch": 0.8751692875930382, + "grad_norm": 0.9702793710486658, + "learning_rate": 8.062210784111135e-07, + "loss": 0.8081, + "step": 9774 + }, + { + "epoch": 0.8752588281381163, + "grad_norm": 0.9995915891444216, + "learning_rate": 8.050805625817071e-07, + "loss": 0.8157, + "step": 9775 + }, + { + "epoch": 0.8753483686831943, + "grad_norm": 0.9062155125740023, + "learning_rate": 8.039408201989618e-07, + "loss": 0.8032, + "step": 9776 + }, + { + "epoch": 0.8754379092282725, + "grad_norm": 0.9573408905890085, + "learning_rate": 8.028018513587477e-07, + "loss": 0.8153, + "step": 9777 + }, + { + "epoch": 0.8755274497733505, + "grad_norm": 1.0417428335204069, + "learning_rate": 8.016636561568713e-07, + "loss": 0.8316, + "step": 9778 + }, + { + "epoch": 0.8756169903184285, + "grad_norm": 0.8639736584756212, + "learning_rate": 8.005262346890752e-07, + "loss": 0.7465, + "step": 9779 + }, + { + "epoch": 0.8757065308635066, + "grad_norm": 0.9593382063459616, + "learning_rate": 7.993895870510316e-07, + "loss": 0.8052, + "step": 9780 + }, + { + "epoch": 0.8757960714085847, + "grad_norm": 0.9853090804400931, + "learning_rate": 7.982537133383528e-07, + "loss": 0.84, + "step": 9781 + }, + { + "epoch": 0.8758856119536628, + "grad_norm": 0.9270240324666513, + "learning_rate": 7.97118613646587e-07, + "loss": 0.8244, + "step": 9782 + }, + { + "epoch": 0.8759751524987408, + "grad_norm": 0.934849005931734, + "learning_rate": 7.959842880712143e-07, + "loss": 0.7859, + "step": 9783 + }, + { + "epoch": 0.876064693043819, + "grad_norm": 1.0276032025232105, + "learning_rate": 7.948507367076519e-07, + "loss": 0.8031, + "step": 9784 + }, + { + "epoch": 0.876154233588897, + "grad_norm": 0.941833516126144, + "learning_rate": 7.937179596512467e-07, + "loss": 0.7807, + "step": 9785 + }, + { + "epoch": 0.876243774133975, + "grad_norm": 0.9086344039477847, + "learning_rate": 7.92585956997286e-07, + "loss": 0.7363, + "step": 9786 + }, + { + "epoch": 0.8763333146790531, + "grad_norm": 0.9464328887920288, + "learning_rate": 7.914547288409891e-07, + "loss": 0.7601, + "step": 9787 + }, + { + "epoch": 0.8764228552241312, + "grad_norm": 1.0067352267720557, + "learning_rate": 7.903242752775142e-07, + "loss": 0.8014, + "step": 9788 + }, + { + "epoch": 0.8765123957692093, + "grad_norm": 0.985419110955858, + "learning_rate": 7.891945964019488e-07, + "loss": 0.8225, + "step": 9789 + }, + { + "epoch": 0.8766019363142873, + "grad_norm": 1.0092430178200362, + "learning_rate": 7.880656923093211e-07, + "loss": 0.7776, + "step": 9790 + }, + { + "epoch": 0.8766914768593653, + "grad_norm": 0.9485356945957446, + "learning_rate": 7.869375630945875e-07, + "loss": 0.7672, + "step": 9791 + }, + { + "epoch": 0.8767810174044435, + "grad_norm": 0.996539467663567, + "learning_rate": 7.85810208852642e-07, + "loss": 0.7967, + "step": 9792 + }, + { + "epoch": 0.8768705579495215, + "grad_norm": 1.0334554465199335, + "learning_rate": 7.846836296783167e-07, + "loss": 0.8255, + "step": 9793 + }, + { + "epoch": 0.8769600984945995, + "grad_norm": 0.9088401012000215, + "learning_rate": 7.835578256663712e-07, + "loss": 0.8294, + "step": 9794 + }, + { + "epoch": 0.8770496390396777, + "grad_norm": 1.078680478430899, + "learning_rate": 7.824327969115119e-07, + "loss": 0.7569, + "step": 9795 + }, + { + "epoch": 0.8771391795847557, + "grad_norm": 1.028118944230959, + "learning_rate": 7.813085435083678e-07, + "loss": 0.8464, + "step": 9796 + }, + { + "epoch": 0.8772287201298338, + "grad_norm": 1.0679999767384944, + "learning_rate": 7.801850655515064e-07, + "loss": 0.8322, + "step": 9797 + }, + { + "epoch": 0.8773182606749118, + "grad_norm": 0.946355863168016, + "learning_rate": 7.790623631354333e-07, + "loss": 0.8051, + "step": 9798 + }, + { + "epoch": 0.87740780121999, + "grad_norm": 1.0215508333014118, + "learning_rate": 7.779404363545861e-07, + "loss": 0.7976, + "step": 9799 + }, + { + "epoch": 0.877497341765068, + "grad_norm": 1.0817862241527378, + "learning_rate": 7.768192853033352e-07, + "loss": 0.802, + "step": 9800 + }, + { + "epoch": 0.877586882310146, + "grad_norm": 1.08636407754348, + "learning_rate": 7.756989100759949e-07, + "loss": 0.7839, + "step": 9801 + }, + { + "epoch": 0.8776764228552242, + "grad_norm": 0.8711485410377877, + "learning_rate": 7.745793107667998e-07, + "loss": 0.7878, + "step": 9802 + }, + { + "epoch": 0.8777659634003022, + "grad_norm": 1.000664383474099, + "learning_rate": 7.734604874699315e-07, + "loss": 0.772, + "step": 9803 + }, + { + "epoch": 0.8778555039453803, + "grad_norm": 1.0185897915799873, + "learning_rate": 7.723424402794999e-07, + "loss": 0.8124, + "step": 9804 + }, + { + "epoch": 0.8779450444904583, + "grad_norm": 0.9892352812041512, + "learning_rate": 7.712251692895522e-07, + "loss": 0.7649, + "step": 9805 + }, + { + "epoch": 0.8780345850355364, + "grad_norm": 1.3611582057179115, + "learning_rate": 7.70108674594069e-07, + "loss": 0.7925, + "step": 9806 + }, + { + "epoch": 0.8781241255806145, + "grad_norm": 0.9953033088493918, + "learning_rate": 7.689929562869669e-07, + "loss": 0.8122, + "step": 9807 + }, + { + "epoch": 0.8782136661256925, + "grad_norm": 1.3580779417717428, + "learning_rate": 7.678780144620956e-07, + "loss": 0.842, + "step": 9808 + }, + { + "epoch": 0.8783032066707706, + "grad_norm": 0.9028211830247261, + "learning_rate": 7.667638492132423e-07, + "loss": 0.7879, + "step": 9809 + }, + { + "epoch": 0.8783927472158487, + "grad_norm": 1.0273831995755325, + "learning_rate": 7.656504606341242e-07, + "loss": 0.7853, + "step": 9810 + }, + { + "epoch": 0.8784822877609267, + "grad_norm": 0.9292371083901101, + "learning_rate": 7.645378488183986e-07, + "loss": 0.7805, + "step": 9811 + }, + { + "epoch": 0.8785718283060048, + "grad_norm": 0.9260584537783453, + "learning_rate": 7.634260138596528e-07, + "loss": 0.7869, + "step": 9812 + }, + { + "epoch": 0.8786613688510829, + "grad_norm": 1.1267648806819965, + "learning_rate": 7.623149558514109e-07, + "loss": 0.8349, + "step": 9813 + }, + { + "epoch": 0.878750909396161, + "grad_norm": 0.9557321799807886, + "learning_rate": 7.612046748871327e-07, + "loss": 0.7401, + "step": 9814 + }, + { + "epoch": 0.878840449941239, + "grad_norm": 1.0005819877209745, + "learning_rate": 7.600951710602111e-07, + "loss": 0.7781, + "step": 9815 + }, + { + "epoch": 0.878929990486317, + "grad_norm": 1.0509734204573693, + "learning_rate": 7.589864444639727e-07, + "loss": 0.7949, + "step": 9816 + }, + { + "epoch": 0.8790195310313952, + "grad_norm": 0.9409700263899377, + "learning_rate": 7.578784951916818e-07, + "loss": 0.8425, + "step": 9817 + }, + { + "epoch": 0.8791090715764732, + "grad_norm": 1.1381749428005803, + "learning_rate": 7.567713233365337e-07, + "loss": 0.859, + "step": 9818 + }, + { + "epoch": 0.8791986121215513, + "grad_norm": 0.9905079487291544, + "learning_rate": 7.556649289916618e-07, + "loss": 0.8465, + "step": 9819 + }, + { + "epoch": 0.8792881526666294, + "grad_norm": 1.1592414290959263, + "learning_rate": 7.545593122501305e-07, + "loss": 0.7977, + "step": 9820 + }, + { + "epoch": 0.8793776932117074, + "grad_norm": 0.943338095280278, + "learning_rate": 7.534544732049431e-07, + "loss": 0.7853, + "step": 9821 + }, + { + "epoch": 0.8794672337567855, + "grad_norm": 1.038089148182455, + "learning_rate": 7.523504119490321e-07, + "loss": 0.6971, + "step": 9822 + }, + { + "epoch": 0.8795567743018635, + "grad_norm": 0.9668546617246336, + "learning_rate": 7.512471285752698e-07, + "loss": 0.7952, + "step": 9823 + }, + { + "epoch": 0.8796463148469417, + "grad_norm": 1.0377805610079907, + "learning_rate": 7.501446231764609e-07, + "loss": 0.7672, + "step": 9824 + }, + { + "epoch": 0.8797358553920197, + "grad_norm": 0.9550606872011534, + "learning_rate": 7.490428958453422e-07, + "loss": 0.8041, + "step": 9825 + }, + { + "epoch": 0.8798253959370977, + "grad_norm": 0.9850703320592671, + "learning_rate": 7.479419466745908e-07, + "loss": 0.7886, + "step": 9826 + }, + { + "epoch": 0.8799149364821758, + "grad_norm": 0.8629978378926485, + "learning_rate": 7.468417757568114e-07, + "loss": 0.7687, + "step": 9827 + }, + { + "epoch": 0.8800044770272539, + "grad_norm": 1.076171519992695, + "learning_rate": 7.457423831845511e-07, + "loss": 0.761, + "step": 9828 + }, + { + "epoch": 0.880094017572332, + "grad_norm": 0.9526392617395856, + "learning_rate": 7.446437690502806e-07, + "loss": 0.7808, + "step": 9829 + }, + { + "epoch": 0.88018355811741, + "grad_norm": 0.9181673950704209, + "learning_rate": 7.435459334464179e-07, + "loss": 0.852, + "step": 9830 + }, + { + "epoch": 0.8802730986624882, + "grad_norm": 0.9397464708923388, + "learning_rate": 7.424488764653082e-07, + "loss": 0.8225, + "step": 9831 + }, + { + "epoch": 0.8803626392075662, + "grad_norm": 0.9388564347080101, + "learning_rate": 7.413525981992298e-07, + "loss": 0.7665, + "step": 9832 + }, + { + "epoch": 0.8804521797526442, + "grad_norm": 0.9771259216936814, + "learning_rate": 7.402570987404001e-07, + "loss": 0.8221, + "step": 9833 + }, + { + "epoch": 0.8805417202977223, + "grad_norm": 1.0184685156760551, + "learning_rate": 7.391623781809709e-07, + "loss": 0.829, + "step": 9834 + }, + { + "epoch": 0.8806312608428004, + "grad_norm": 1.073933743661023, + "learning_rate": 7.380684366130197e-07, + "loss": 0.753, + "step": 9835 + }, + { + "epoch": 0.8807208013878784, + "grad_norm": 1.1403977625911974, + "learning_rate": 7.369752741285729e-07, + "loss": 0.744, + "step": 9836 + }, + { + "epoch": 0.8808103419329565, + "grad_norm": 1.2751822216343298, + "learning_rate": 7.358828908195792e-07, + "loss": 0.7813, + "step": 9837 + }, + { + "epoch": 0.8808998824780346, + "grad_norm": 0.9586220881159375, + "learning_rate": 7.347912867779283e-07, + "loss": 0.8013, + "step": 9838 + }, + { + "epoch": 0.8809894230231127, + "grad_norm": 1.04948302898256, + "learning_rate": 7.337004620954435e-07, + "loss": 0.7847, + "step": 9839 + }, + { + "epoch": 0.8810789635681907, + "grad_norm": 0.9670661870410249, + "learning_rate": 7.32610416863877e-07, + "loss": 0.7888, + "step": 9840 + }, + { + "epoch": 0.8811685041132687, + "grad_norm": 1.0298972520242087, + "learning_rate": 7.315211511749242e-07, + "loss": 0.8, + "step": 9841 + }, + { + "epoch": 0.8812580446583469, + "grad_norm": 1.0175773605713476, + "learning_rate": 7.304326651202065e-07, + "loss": 0.8362, + "step": 9842 + }, + { + "epoch": 0.8813475852034249, + "grad_norm": 0.9189549171001492, + "learning_rate": 7.29344958791287e-07, + "loss": 0.8128, + "step": 9843 + }, + { + "epoch": 0.881437125748503, + "grad_norm": 0.9960933827101033, + "learning_rate": 7.282580322796606e-07, + "loss": 0.874, + "step": 9844 + }, + { + "epoch": 0.881526666293581, + "grad_norm": 0.9732778571116106, + "learning_rate": 7.271718856767562e-07, + "loss": 0.8189, + "step": 9845 + }, + { + "epoch": 0.8816162068386592, + "grad_norm": 0.9858362820808764, + "learning_rate": 7.26086519073933e-07, + "loss": 0.7978, + "step": 9846 + }, + { + "epoch": 0.8817057473837372, + "grad_norm": 0.980870945883378, + "learning_rate": 7.250019325624912e-07, + "loss": 0.8054, + "step": 9847 + }, + { + "epoch": 0.8817952879288152, + "grad_norm": 0.9807060169239823, + "learning_rate": 7.239181262336604e-07, + "loss": 0.789, + "step": 9848 + }, + { + "epoch": 0.8818848284738934, + "grad_norm": 1.0194821064282118, + "learning_rate": 7.228351001786116e-07, + "loss": 0.789, + "step": 9849 + }, + { + "epoch": 0.8819743690189714, + "grad_norm": 0.9679439639230165, + "learning_rate": 7.217528544884433e-07, + "loss": 0.7678, + "step": 9850 + }, + { + "epoch": 0.8820639095640495, + "grad_norm": 1.0003269571387614, + "learning_rate": 7.206713892541884e-07, + "loss": 0.7844, + "step": 9851 + }, + { + "epoch": 0.8821534501091275, + "grad_norm": 0.9280736978949874, + "learning_rate": 7.195907045668171e-07, + "loss": 0.8084, + "step": 9852 + }, + { + "epoch": 0.8822429906542056, + "grad_norm": 0.9412840758958403, + "learning_rate": 7.185108005172347e-07, + "loss": 0.7822, + "step": 9853 + }, + { + "epoch": 0.8823325311992837, + "grad_norm": 1.0889754939069687, + "learning_rate": 7.174316771962752e-07, + "loss": 0.7411, + "step": 9854 + }, + { + "epoch": 0.8824220717443617, + "grad_norm": 1.0272199833259048, + "learning_rate": 7.163533346947183e-07, + "loss": 0.7876, + "step": 9855 + }, + { + "epoch": 0.8825116122894399, + "grad_norm": 1.0403525550361983, + "learning_rate": 7.152757731032645e-07, + "loss": 0.8132, + "step": 9856 + }, + { + "epoch": 0.8826011528345179, + "grad_norm": 1.0091771608241993, + "learning_rate": 7.141989925125559e-07, + "loss": 0.841, + "step": 9857 + }, + { + "epoch": 0.8826906933795959, + "grad_norm": 0.9734762855463261, + "learning_rate": 7.131229930131689e-07, + "loss": 0.7676, + "step": 9858 + }, + { + "epoch": 0.882780233924674, + "grad_norm": 1.2835988569437364, + "learning_rate": 7.120477746956123e-07, + "loss": 0.806, + "step": 9859 + }, + { + "epoch": 0.8828697744697521, + "grad_norm": 0.9684613488185034, + "learning_rate": 7.109733376503281e-07, + "loss": 0.816, + "step": 9860 + }, + { + "epoch": 0.8829593150148302, + "grad_norm": 1.214126291893131, + "learning_rate": 7.098996819677006e-07, + "loss": 0.7465, + "step": 9861 + }, + { + "epoch": 0.8830488555599082, + "grad_norm": 0.9933197081487194, + "learning_rate": 7.088268077380356e-07, + "loss": 0.8165, + "step": 9862 + }, + { + "epoch": 0.8831383961049862, + "grad_norm": 1.0433426419260803, + "learning_rate": 7.07754715051584e-07, + "loss": 0.8252, + "step": 9863 + }, + { + "epoch": 0.8832279366500644, + "grad_norm": 0.9588611716236244, + "learning_rate": 7.066834039985237e-07, + "loss": 0.7915, + "step": 9864 + }, + { + "epoch": 0.8833174771951424, + "grad_norm": 1.1333183014029315, + "learning_rate": 7.056128746689717e-07, + "loss": 0.8206, + "step": 9865 + }, + { + "epoch": 0.8834070177402205, + "grad_norm": 0.8894077619600714, + "learning_rate": 7.045431271529767e-07, + "loss": 0.7704, + "step": 9866 + }, + { + "epoch": 0.8834965582852986, + "grad_norm": 0.9732615935059117, + "learning_rate": 7.034741615405227e-07, + "loss": 0.8293, + "step": 9867 + }, + { + "epoch": 0.8835860988303766, + "grad_norm": 1.0604689430851104, + "learning_rate": 7.024059779215287e-07, + "loss": 0.7936, + "step": 9868 + }, + { + "epoch": 0.8836756393754547, + "grad_norm": 0.9990437921434144, + "learning_rate": 7.013385763858449e-07, + "loss": 0.7458, + "step": 9869 + }, + { + "epoch": 0.8837651799205327, + "grad_norm": 0.9223506198710638, + "learning_rate": 7.002719570232586e-07, + "loss": 0.7701, + "step": 9870 + }, + { + "epoch": 0.8838547204656109, + "grad_norm": 1.0233802711643287, + "learning_rate": 6.9920611992349e-07, + "loss": 0.8115, + "step": 9871 + }, + { + "epoch": 0.8839442610106889, + "grad_norm": 0.9439578122268587, + "learning_rate": 6.981410651761933e-07, + "loss": 0.763, + "step": 9872 + }, + { + "epoch": 0.8840338015557669, + "grad_norm": 0.9590002220547745, + "learning_rate": 6.970767928709599e-07, + "loss": 0.8136, + "step": 9873 + }, + { + "epoch": 0.8841233421008451, + "grad_norm": 0.9805836162859698, + "learning_rate": 6.960133030973104e-07, + "loss": 0.8214, + "step": 9874 + }, + { + "epoch": 0.8842128826459231, + "grad_norm": 0.9698652912697726, + "learning_rate": 6.949505959447023e-07, + "loss": 0.8057, + "step": 9875 + }, + { + "epoch": 0.8843024231910012, + "grad_norm": 1.005258093280118, + "learning_rate": 6.938886715025284e-07, + "loss": 0.7435, + "step": 9876 + }, + { + "epoch": 0.8843919637360792, + "grad_norm": 1.0260772790272097, + "learning_rate": 6.92827529860114e-07, + "loss": 0.7977, + "step": 9877 + }, + { + "epoch": 0.8844815042811573, + "grad_norm": 0.9510253123237471, + "learning_rate": 6.917671711067176e-07, + "loss": 0.7737, + "step": 9878 + }, + { + "epoch": 0.8845710448262354, + "grad_norm": 0.9687981500437558, + "learning_rate": 6.907075953315346e-07, + "loss": 0.7997, + "step": 9879 + }, + { + "epoch": 0.8846605853713134, + "grad_norm": 0.9422514901604037, + "learning_rate": 6.896488026236914e-07, + "loss": 0.7626, + "step": 9880 + }, + { + "epoch": 0.8847501259163915, + "grad_norm": 1.044599744388437, + "learning_rate": 6.885907930722525e-07, + "loss": 0.8226, + "step": 9881 + }, + { + "epoch": 0.8848396664614696, + "grad_norm": 1.0535834807569582, + "learning_rate": 6.87533566766212e-07, + "loss": 0.824, + "step": 9882 + }, + { + "epoch": 0.8849292070065476, + "grad_norm": 0.9547869762437075, + "learning_rate": 6.864771237945022e-07, + "loss": 0.8207, + "step": 9883 + }, + { + "epoch": 0.8850187475516257, + "grad_norm": 1.023538380131524, + "learning_rate": 6.854214642459855e-07, + "loss": 0.7923, + "step": 9884 + }, + { + "epoch": 0.8851082880967038, + "grad_norm": 1.0423316879756122, + "learning_rate": 6.84366588209463e-07, + "loss": 0.785, + "step": 9885 + }, + { + "epoch": 0.8851978286417819, + "grad_norm": 1.2147324676930111, + "learning_rate": 6.833124957736659e-07, + "loss": 0.8118, + "step": 9886 + }, + { + "epoch": 0.8852873691868599, + "grad_norm": 1.0001329990900338, + "learning_rate": 6.82259187027261e-07, + "loss": 0.806, + "step": 9887 + }, + { + "epoch": 0.8853769097319379, + "grad_norm": 0.9687319433743499, + "learning_rate": 6.81206662058852e-07, + "loss": 0.7569, + "step": 9888 + }, + { + "epoch": 0.8854664502770161, + "grad_norm": 1.5485829855799689, + "learning_rate": 6.801549209569669e-07, + "loss": 0.8073, + "step": 9889 + }, + { + "epoch": 0.8855559908220941, + "grad_norm": 0.9575800121372752, + "learning_rate": 6.791039638100816e-07, + "loss": 0.8475, + "step": 9890 + }, + { + "epoch": 0.8856455313671722, + "grad_norm": 1.009529690296095, + "learning_rate": 6.780537907065965e-07, + "loss": 0.8155, + "step": 9891 + }, + { + "epoch": 0.8857350719122503, + "grad_norm": 0.9721110469169533, + "learning_rate": 6.770044017348498e-07, + "loss": 0.8417, + "step": 9892 + }, + { + "epoch": 0.8858246124573284, + "grad_norm": 0.9481725185534631, + "learning_rate": 6.759557969831109e-07, + "loss": 0.826, + "step": 9893 + }, + { + "epoch": 0.8859141530024064, + "grad_norm": 1.0774780509105069, + "learning_rate": 6.749079765395883e-07, + "loss": 0.843, + "step": 9894 + }, + { + "epoch": 0.8860036935474844, + "grad_norm": 1.034737793132593, + "learning_rate": 6.738609404924168e-07, + "loss": 0.7561, + "step": 9895 + }, + { + "epoch": 0.8860932340925626, + "grad_norm": 1.0186796952311126, + "learning_rate": 6.728146889296716e-07, + "loss": 0.7348, + "step": 9896 + }, + { + "epoch": 0.8861827746376406, + "grad_norm": 1.0368944939513032, + "learning_rate": 6.717692219393601e-07, + "loss": 0.7841, + "step": 9897 + }, + { + "epoch": 0.8862723151827187, + "grad_norm": 0.9077689129683076, + "learning_rate": 6.707245396094253e-07, + "loss": 0.8046, + "step": 9898 + }, + { + "epoch": 0.8863618557277967, + "grad_norm": 0.9376919886076567, + "learning_rate": 6.696806420277413e-07, + "loss": 0.7791, + "step": 9899 + }, + { + "epoch": 0.8864513962728748, + "grad_norm": 0.8802664037859377, + "learning_rate": 6.686375292821157e-07, + "loss": 0.7456, + "step": 9900 + }, + { + "epoch": 0.8865409368179529, + "grad_norm": 1.1283498152495757, + "learning_rate": 6.675952014602937e-07, + "loss": 0.8131, + "step": 9901 + }, + { + "epoch": 0.8866304773630309, + "grad_norm": 0.9863867866210473, + "learning_rate": 6.665536586499488e-07, + "loss": 0.8071, + "step": 9902 + }, + { + "epoch": 0.8867200179081091, + "grad_norm": 0.9848282144043862, + "learning_rate": 6.655129009386974e-07, + "loss": 0.8451, + "step": 9903 + }, + { + "epoch": 0.8868095584531871, + "grad_norm": 1.0818080777758607, + "learning_rate": 6.644729284140828e-07, + "loss": 0.8561, + "step": 9904 + }, + { + "epoch": 0.8868990989982651, + "grad_norm": 0.8885447875057321, + "learning_rate": 6.634337411635849e-07, + "loss": 0.7736, + "step": 9905 + }, + { + "epoch": 0.8869886395433432, + "grad_norm": 1.0342204171878764, + "learning_rate": 6.623953392746152e-07, + "loss": 0.7816, + "step": 9906 + }, + { + "epoch": 0.8870781800884213, + "grad_norm": 1.0048154355805707, + "learning_rate": 6.613577228345202e-07, + "loss": 0.7731, + "step": 9907 + }, + { + "epoch": 0.8871677206334994, + "grad_norm": 0.8818723378372741, + "learning_rate": 6.603208919305792e-07, + "loss": 0.7783, + "step": 9908 + }, + { + "epoch": 0.8872572611785774, + "grad_norm": 0.9979421614145839, + "learning_rate": 6.592848466500123e-07, + "loss": 0.7797, + "step": 9909 + }, + { + "epoch": 0.8873468017236555, + "grad_norm": 0.9889813314459065, + "learning_rate": 6.582495870799666e-07, + "loss": 0.7636, + "step": 9910 + }, + { + "epoch": 0.8874363422687336, + "grad_norm": 1.2623720123065876, + "learning_rate": 6.572151133075222e-07, + "loss": 0.8132, + "step": 9911 + }, + { + "epoch": 0.8875258828138116, + "grad_norm": 1.079529749992829, + "learning_rate": 6.561814254196974e-07, + "loss": 0.8563, + "step": 9912 + }, + { + "epoch": 0.8876154233588897, + "grad_norm": 1.018669930889253, + "learning_rate": 6.551485235034416e-07, + "loss": 0.8079, + "step": 9913 + }, + { + "epoch": 0.8877049639039678, + "grad_norm": 0.9563525638873442, + "learning_rate": 6.541164076456385e-07, + "loss": 0.8266, + "step": 9914 + }, + { + "epoch": 0.8877945044490458, + "grad_norm": 1.1260987048704978, + "learning_rate": 6.530850779331099e-07, + "loss": 0.8233, + "step": 9915 + }, + { + "epoch": 0.8878840449941239, + "grad_norm": 1.2221780742977932, + "learning_rate": 6.520545344526063e-07, + "loss": 0.7777, + "step": 9916 + }, + { + "epoch": 0.8879735855392019, + "grad_norm": 1.0720258552291122, + "learning_rate": 6.51024777290813e-07, + "loss": 0.8265, + "step": 9917 + }, + { + "epoch": 0.8880631260842801, + "grad_norm": 1.0025242255099671, + "learning_rate": 6.499958065343492e-07, + "loss": 0.7149, + "step": 9918 + }, + { + "epoch": 0.8881526666293581, + "grad_norm": 0.9894722797972897, + "learning_rate": 6.489676222697683e-07, + "loss": 0.8018, + "step": 9919 + }, + { + "epoch": 0.8882422071744361, + "grad_norm": 0.9433127041715978, + "learning_rate": 6.479402245835587e-07, + "loss": 0.7857, + "step": 9920 + }, + { + "epoch": 0.8883317477195143, + "grad_norm": 0.9585168062099032, + "learning_rate": 6.469136135621434e-07, + "loss": 0.7875, + "step": 9921 + }, + { + "epoch": 0.8884212882645923, + "grad_norm": 1.0448981301626772, + "learning_rate": 6.458877892918758e-07, + "loss": 0.7709, + "step": 9922 + }, + { + "epoch": 0.8885108288096704, + "grad_norm": 0.9469908831668271, + "learning_rate": 6.448627518590444e-07, + "loss": 0.792, + "step": 9923 + }, + { + "epoch": 0.8886003693547484, + "grad_norm": 0.872736211836871, + "learning_rate": 6.438385013498727e-07, + "loss": 0.7806, + "step": 9924 + }, + { + "epoch": 0.8886899098998265, + "grad_norm": 1.0505593698527258, + "learning_rate": 6.428150378505171e-07, + "loss": 0.8295, + "step": 9925 + }, + { + "epoch": 0.8887794504449046, + "grad_norm": 0.9855662574745117, + "learning_rate": 6.417923614470689e-07, + "loss": 0.717, + "step": 9926 + }, + { + "epoch": 0.8888689909899826, + "grad_norm": 1.0226501088945537, + "learning_rate": 6.407704722255514e-07, + "loss": 0.8054, + "step": 9927 + }, + { + "epoch": 0.8889585315350608, + "grad_norm": 1.013583703887514, + "learning_rate": 6.397493702719226e-07, + "loss": 0.8594, + "step": 9928 + }, + { + "epoch": 0.8890480720801388, + "grad_norm": 0.9178398536134609, + "learning_rate": 6.387290556720749e-07, + "loss": 0.8154, + "step": 9929 + }, + { + "epoch": 0.8891376126252168, + "grad_norm": 0.9994942006875942, + "learning_rate": 6.377095285118329e-07, + "loss": 0.8298, + "step": 9930 + }, + { + "epoch": 0.8892271531702949, + "grad_norm": 0.9860537494489169, + "learning_rate": 6.366907888769569e-07, + "loss": 0.8098, + "step": 9931 + }, + { + "epoch": 0.889316693715373, + "grad_norm": 0.9321200968247388, + "learning_rate": 6.356728368531384e-07, + "loss": 0.8199, + "step": 9932 + }, + { + "epoch": 0.8894062342604511, + "grad_norm": 1.0091043074095212, + "learning_rate": 6.346556725260067e-07, + "loss": 0.817, + "step": 9933 + }, + { + "epoch": 0.8894957748055291, + "grad_norm": 1.0961654503467206, + "learning_rate": 6.336392959811199e-07, + "loss": 0.7693, + "step": 9934 + }, + { + "epoch": 0.8895853153506071, + "grad_norm": 0.9755442473176906, + "learning_rate": 6.326237073039743e-07, + "loss": 0.7426, + "step": 9935 + }, + { + "epoch": 0.8896748558956853, + "grad_norm": 1.1460587620962055, + "learning_rate": 6.316089065799958e-07, + "loss": 0.7813, + "step": 9936 + }, + { + "epoch": 0.8897643964407633, + "grad_norm": 1.0466513473659182, + "learning_rate": 6.305948938945483e-07, + "loss": 0.7729, + "step": 9937 + }, + { + "epoch": 0.8898539369858414, + "grad_norm": 1.1298520487309693, + "learning_rate": 6.29581669332926e-07, + "loss": 0.8028, + "step": 9938 + }, + { + "epoch": 0.8899434775309195, + "grad_norm": 0.9713403205632621, + "learning_rate": 6.285692329803572e-07, + "loss": 0.7501, + "step": 9939 + }, + { + "epoch": 0.8900330180759976, + "grad_norm": 1.124085686499429, + "learning_rate": 6.275575849220072e-07, + "loss": 0.7881, + "step": 9940 + }, + { + "epoch": 0.8901225586210756, + "grad_norm": 1.0860753523770987, + "learning_rate": 6.265467252429702e-07, + "loss": 0.8082, + "step": 9941 + }, + { + "epoch": 0.8902120991661536, + "grad_norm": 0.9899562494913732, + "learning_rate": 6.255366540282782e-07, + "loss": 0.8314, + "step": 9942 + }, + { + "epoch": 0.8903016397112318, + "grad_norm": 0.9524596789668761, + "learning_rate": 6.245273713628941e-07, + "loss": 0.74, + "step": 9943 + }, + { + "epoch": 0.8903911802563098, + "grad_norm": 0.9755006968342398, + "learning_rate": 6.235188773317146e-07, + "loss": 0.7585, + "step": 9944 + }, + { + "epoch": 0.8904807208013878, + "grad_norm": 1.0846689513127081, + "learning_rate": 6.225111720195731e-07, + "loss": 0.808, + "step": 9945 + }, + { + "epoch": 0.890570261346466, + "grad_norm": 1.0099944870087119, + "learning_rate": 6.215042555112327e-07, + "loss": 0.7426, + "step": 9946 + }, + { + "epoch": 0.890659801891544, + "grad_norm": 0.9521833797242738, + "learning_rate": 6.204981278913936e-07, + "loss": 0.8149, + "step": 9947 + }, + { + "epoch": 0.8907493424366221, + "grad_norm": 0.9774130601149447, + "learning_rate": 6.194927892446878e-07, + "loss": 0.7971, + "step": 9948 + }, + { + "epoch": 0.8908388829817001, + "grad_norm": 0.9646551441927631, + "learning_rate": 6.184882396556779e-07, + "loss": 0.8152, + "step": 9949 + }, + { + "epoch": 0.8909284235267783, + "grad_norm": 0.9062045091522603, + "learning_rate": 6.174844792088652e-07, + "loss": 0.7824, + "step": 9950 + }, + { + "epoch": 0.8910179640718563, + "grad_norm": 1.0978580092150452, + "learning_rate": 6.164815079886844e-07, + "loss": 0.8009, + "step": 9951 + }, + { + "epoch": 0.8911075046169343, + "grad_norm": 0.9793458529125768, + "learning_rate": 6.154793260795011e-07, + "loss": 0.795, + "step": 9952 + }, + { + "epoch": 0.8911970451620124, + "grad_norm": 1.0084524542284112, + "learning_rate": 6.144779335656159e-07, + "loss": 0.7663, + "step": 9953 + }, + { + "epoch": 0.8912865857070905, + "grad_norm": 1.0838937083673923, + "learning_rate": 6.134773305312636e-07, + "loss": 0.8439, + "step": 9954 + }, + { + "epoch": 0.8913761262521686, + "grad_norm": 1.0583795847350332, + "learning_rate": 6.12477517060609e-07, + "loss": 0.7878, + "step": 9955 + }, + { + "epoch": 0.8914656667972466, + "grad_norm": 0.9437666283381655, + "learning_rate": 6.114784932377526e-07, + "loss": 0.814, + "step": 9956 + }, + { + "epoch": 0.8915552073423247, + "grad_norm": 0.8876357868918994, + "learning_rate": 6.104802591467329e-07, + "loss": 0.785, + "step": 9957 + }, + { + "epoch": 0.8916447478874028, + "grad_norm": 0.9453750217581149, + "learning_rate": 6.09482814871516e-07, + "loss": 0.8062, + "step": 9958 + }, + { + "epoch": 0.8917342884324808, + "grad_norm": 1.0427685090786825, + "learning_rate": 6.084861604960047e-07, + "loss": 0.7681, + "step": 9959 + }, + { + "epoch": 0.8918238289775589, + "grad_norm": 0.930499158074984, + "learning_rate": 6.074902961040319e-07, + "loss": 0.76, + "step": 9960 + }, + { + "epoch": 0.891913369522637, + "grad_norm": 0.9588367291430306, + "learning_rate": 6.064952217793685e-07, + "loss": 0.8256, + "step": 9961 + }, + { + "epoch": 0.892002910067715, + "grad_norm": 0.9988894418366342, + "learning_rate": 6.055009376057152e-07, + "loss": 0.8183, + "step": 9962 + }, + { + "epoch": 0.8920924506127931, + "grad_norm": 1.0562786970788445, + "learning_rate": 6.045074436667108e-07, + "loss": 0.7772, + "step": 9963 + }, + { + "epoch": 0.8921819911578712, + "grad_norm": 1.1765680904902591, + "learning_rate": 6.035147400459218e-07, + "loss": 0.8826, + "step": 9964 + }, + { + "epoch": 0.8922715317029493, + "grad_norm": 1.027828479486301, + "learning_rate": 6.025228268268557e-07, + "loss": 0.8447, + "step": 9965 + }, + { + "epoch": 0.8923610722480273, + "grad_norm": 0.9697866937651108, + "learning_rate": 6.015317040929425e-07, + "loss": 0.7632, + "step": 9966 + }, + { + "epoch": 0.8924506127931053, + "grad_norm": 1.0517693589092671, + "learning_rate": 6.005413719275566e-07, + "loss": 0.7657, + "step": 9967 + }, + { + "epoch": 0.8925401533381835, + "grad_norm": 1.1655550570603423, + "learning_rate": 5.995518304139991e-07, + "loss": 0.7837, + "step": 9968 + }, + { + "epoch": 0.8926296938832615, + "grad_norm": 0.9466188600696482, + "learning_rate": 5.985630796355091e-07, + "loss": 0.7869, + "step": 9969 + }, + { + "epoch": 0.8927192344283396, + "grad_norm": 0.9335773209850894, + "learning_rate": 5.975751196752589e-07, + "loss": 0.8414, + "step": 9970 + }, + { + "epoch": 0.8928087749734176, + "grad_norm": 0.9782809613187378, + "learning_rate": 5.965879506163475e-07, + "loss": 0.7461, + "step": 9971 + }, + { + "epoch": 0.8928983155184957, + "grad_norm": 1.0069936035871836, + "learning_rate": 5.956015725418152e-07, + "loss": 0.8177, + "step": 9972 + }, + { + "epoch": 0.8929878560635738, + "grad_norm": 0.9305892452213185, + "learning_rate": 5.946159855346323e-07, + "loss": 0.7436, + "step": 9973 + }, + { + "epoch": 0.8930773966086518, + "grad_norm": 1.0075484139974755, + "learning_rate": 5.936311896777014e-07, + "loss": 0.8406, + "step": 9974 + }, + { + "epoch": 0.89316693715373, + "grad_norm": 0.9853121460991587, + "learning_rate": 5.92647185053864e-07, + "loss": 0.8117, + "step": 9975 + }, + { + "epoch": 0.893256477698808, + "grad_norm": 1.0441078609605476, + "learning_rate": 5.916639717458917e-07, + "loss": 0.8082, + "step": 9976 + }, + { + "epoch": 0.893346018243886, + "grad_norm": 1.181633530126853, + "learning_rate": 5.906815498364848e-07, + "loss": 0.8002, + "step": 9977 + }, + { + "epoch": 0.8934355587889641, + "grad_norm": 1.0580123822669165, + "learning_rate": 5.896999194082842e-07, + "loss": 0.8372, + "step": 9978 + }, + { + "epoch": 0.8935250993340422, + "grad_norm": 0.8959174586658117, + "learning_rate": 5.887190805438614e-07, + "loss": 0.7456, + "step": 9979 + }, + { + "epoch": 0.8936146398791203, + "grad_norm": 0.9565687323618474, + "learning_rate": 5.877390333257204e-07, + "loss": 0.8184, + "step": 9980 + }, + { + "epoch": 0.8937041804241983, + "grad_norm": 1.11615953951939, + "learning_rate": 5.86759777836301e-07, + "loss": 0.8719, + "step": 9981 + }, + { + "epoch": 0.8937937209692765, + "grad_norm": 0.9379327677049312, + "learning_rate": 5.857813141579726e-07, + "loss": 0.8166, + "step": 9982 + }, + { + "epoch": 0.8938832615143545, + "grad_norm": 0.9393516389690907, + "learning_rate": 5.84803642373043e-07, + "loss": 0.7903, + "step": 9983 + }, + { + "epoch": 0.8939728020594325, + "grad_norm": 1.22291923194786, + "learning_rate": 5.838267625637495e-07, + "loss": 0.8486, + "step": 9984 + }, + { + "epoch": 0.8940623426045106, + "grad_norm": 1.1976238436112334, + "learning_rate": 5.828506748122642e-07, + "loss": 0.7178, + "step": 9985 + }, + { + "epoch": 0.8941518831495887, + "grad_norm": 0.9812165181039328, + "learning_rate": 5.818753792006926e-07, + "loss": 0.8028, + "step": 9986 + }, + { + "epoch": 0.8942414236946667, + "grad_norm": 0.9854806076048201, + "learning_rate": 5.809008758110724e-07, + "loss": 0.782, + "step": 9987 + }, + { + "epoch": 0.8943309642397448, + "grad_norm": 1.0270250325290047, + "learning_rate": 5.799271647253768e-07, + "loss": 0.79, + "step": 9988 + }, + { + "epoch": 0.8944205047848228, + "grad_norm": 0.9379729769780246, + "learning_rate": 5.789542460255115e-07, + "loss": 0.753, + "step": 9989 + }, + { + "epoch": 0.894510045329901, + "grad_norm": 1.0063728667137473, + "learning_rate": 5.779821197933144e-07, + "loss": 0.8373, + "step": 9990 + }, + { + "epoch": 0.894599585874979, + "grad_norm": 0.9547802631041389, + "learning_rate": 5.770107861105578e-07, + "loss": 0.8641, + "step": 9991 + }, + { + "epoch": 0.894689126420057, + "grad_norm": 1.2546355839015437, + "learning_rate": 5.760402450589464e-07, + "loss": 0.786, + "step": 9992 + }, + { + "epoch": 0.8947786669651352, + "grad_norm": 0.9694806063263535, + "learning_rate": 5.750704967201204e-07, + "loss": 0.7878, + "step": 9993 + }, + { + "epoch": 0.8948682075102132, + "grad_norm": 0.9465183345372448, + "learning_rate": 5.741015411756513e-07, + "loss": 0.8305, + "step": 9994 + }, + { + "epoch": 0.8949577480552913, + "grad_norm": 0.8765383184654157, + "learning_rate": 5.731333785070437e-07, + "loss": 0.7951, + "step": 9995 + }, + { + "epoch": 0.8950472886003693, + "grad_norm": 1.156313780653024, + "learning_rate": 5.721660087957382e-07, + "loss": 0.7603, + "step": 9996 + }, + { + "epoch": 0.8951368291454475, + "grad_norm": 0.9460604138619739, + "learning_rate": 5.71199432123104e-07, + "loss": 0.7983, + "step": 9997 + }, + { + "epoch": 0.8952263696905255, + "grad_norm": 0.9873503895829151, + "learning_rate": 5.702336485704485e-07, + "loss": 0.7793, + "step": 9998 + }, + { + "epoch": 0.8953159102356035, + "grad_norm": 1.0067657581726523, + "learning_rate": 5.692686582190099e-07, + "loss": 0.81, + "step": 9999 + }, + { + "epoch": 0.8954054507806817, + "grad_norm": 1.0171821290039484, + "learning_rate": 5.6830446114996e-07, + "loss": 0.8167, + "step": 10000 + }, + { + "epoch": 0.8954949913257597, + "grad_norm": 1.1356278967575386, + "learning_rate": 5.673410574444027e-07, + "loss": 0.8391, + "step": 10001 + }, + { + "epoch": 0.8955845318708378, + "grad_norm": 1.0570739890030072, + "learning_rate": 5.663784471833777e-07, + "loss": 0.7987, + "step": 10002 + }, + { + "epoch": 0.8956740724159158, + "grad_norm": 0.9585881496514032, + "learning_rate": 5.654166304478581e-07, + "loss": 0.7719, + "step": 10003 + }, + { + "epoch": 0.8957636129609939, + "grad_norm": 0.9710179853590815, + "learning_rate": 5.644556073187446e-07, + "loss": 0.83, + "step": 10004 + }, + { + "epoch": 0.895853153506072, + "grad_norm": 0.9030289756216271, + "learning_rate": 5.634953778768793e-07, + "loss": 0.7851, + "step": 10005 + }, + { + "epoch": 0.89594269405115, + "grad_norm": 0.9163993010636187, + "learning_rate": 5.625359422030308e-07, + "loss": 0.8146, + "step": 10006 + }, + { + "epoch": 0.896032234596228, + "grad_norm": 0.9855617993120946, + "learning_rate": 5.615773003779057e-07, + "loss": 0.8588, + "step": 10007 + }, + { + "epoch": 0.8961217751413062, + "grad_norm": 0.9556209325252594, + "learning_rate": 5.606194524821429e-07, + "loss": 0.7774, + "step": 10008 + }, + { + "epoch": 0.8962113156863842, + "grad_norm": 0.9430905772706917, + "learning_rate": 5.596623985963101e-07, + "loss": 0.7826, + "step": 10009 + }, + { + "epoch": 0.8963008562314623, + "grad_norm": 1.1351390436002864, + "learning_rate": 5.587061388009107e-07, + "loss": 0.8333, + "step": 10010 + }, + { + "epoch": 0.8963903967765404, + "grad_norm": 0.9654083945280173, + "learning_rate": 5.577506731763871e-07, + "loss": 0.8238, + "step": 10011 + }, + { + "epoch": 0.8964799373216185, + "grad_norm": 0.8906166103605484, + "learning_rate": 5.56796001803106e-07, + "loss": 0.7749, + "step": 10012 + }, + { + "epoch": 0.8965694778666965, + "grad_norm": 0.9357488861191008, + "learning_rate": 5.558421247613732e-07, + "loss": 0.7675, + "step": 10013 + }, + { + "epoch": 0.8966590184117745, + "grad_norm": 1.092934498926836, + "learning_rate": 5.548890421314279e-07, + "loss": 0.791, + "step": 10014 + }, + { + "epoch": 0.8967485589568527, + "grad_norm": 1.0274872931425811, + "learning_rate": 5.539367539934348e-07, + "loss": 0.768, + "step": 10015 + }, + { + "epoch": 0.8968380995019307, + "grad_norm": 0.9666219707935592, + "learning_rate": 5.529852604274987e-07, + "loss": 0.7263, + "step": 10016 + }, + { + "epoch": 0.8969276400470088, + "grad_norm": 1.0058974570161976, + "learning_rate": 5.520345615136591e-07, + "loss": 0.7374, + "step": 10017 + }, + { + "epoch": 0.8970171805920869, + "grad_norm": 1.0380446827022656, + "learning_rate": 5.51084657331884e-07, + "loss": 0.8489, + "step": 10018 + }, + { + "epoch": 0.8971067211371649, + "grad_norm": 0.9199319773731917, + "learning_rate": 5.501355479620774e-07, + "loss": 0.7997, + "step": 10019 + }, + { + "epoch": 0.897196261682243, + "grad_norm": 0.9749102380171594, + "learning_rate": 5.491872334840731e-07, + "loss": 0.8171, + "step": 10020 + }, + { + "epoch": 0.897285802227321, + "grad_norm": 0.9896420546965614, + "learning_rate": 5.482397139776419e-07, + "loss": 0.7918, + "step": 10021 + }, + { + "epoch": 0.8973753427723992, + "grad_norm": 1.0291700929950498, + "learning_rate": 5.472929895224832e-07, + "loss": 0.8009, + "step": 10022 + }, + { + "epoch": 0.8974648833174772, + "grad_norm": 0.9003815295508676, + "learning_rate": 5.463470601982357e-07, + "loss": 0.797, + "step": 10023 + }, + { + "epoch": 0.8975544238625552, + "grad_norm": 0.9684958679330604, + "learning_rate": 5.454019260844678e-07, + "loss": 0.8074, + "step": 10024 + }, + { + "epoch": 0.8976439644076333, + "grad_norm": 1.0409909361803587, + "learning_rate": 5.444575872606816e-07, + "loss": 0.8185, + "step": 10025 + }, + { + "epoch": 0.8977335049527114, + "grad_norm": 1.3769915433772986, + "learning_rate": 5.43514043806308e-07, + "loss": 0.7734, + "step": 10026 + }, + { + "epoch": 0.8978230454977895, + "grad_norm": 0.9903127022847581, + "learning_rate": 5.425712958007179e-07, + "loss": 0.8282, + "step": 10027 + }, + { + "epoch": 0.8979125860428675, + "grad_norm": 0.9343133209674779, + "learning_rate": 5.4162934332321e-07, + "loss": 0.7948, + "step": 10028 + }, + { + "epoch": 0.8980021265879456, + "grad_norm": 0.944797588323456, + "learning_rate": 5.406881864530212e-07, + "loss": 0.7728, + "step": 10029 + }, + { + "epoch": 0.8980916671330237, + "grad_norm": 1.0412404995015119, + "learning_rate": 5.397478252693178e-07, + "loss": 0.8245, + "step": 10030 + }, + { + "epoch": 0.8981812076781017, + "grad_norm": 1.0598063934066146, + "learning_rate": 5.38808259851199e-07, + "loss": 0.8477, + "step": 10031 + }, + { + "epoch": 0.8982707482231798, + "grad_norm": 0.9716796782053765, + "learning_rate": 5.37869490277697e-07, + "loss": 0.7857, + "step": 10032 + }, + { + "epoch": 0.8983602887682579, + "grad_norm": 1.039570692534801, + "learning_rate": 5.3693151662778e-07, + "loss": 0.8099, + "step": 10033 + }, + { + "epoch": 0.898449829313336, + "grad_norm": 1.1566494930140174, + "learning_rate": 5.359943389803457e-07, + "loss": 0.8102, + "step": 10034 + }, + { + "epoch": 0.898539369858414, + "grad_norm": 0.961363097045426, + "learning_rate": 5.350579574142256e-07, + "loss": 0.8231, + "step": 10035 + }, + { + "epoch": 0.8986289104034921, + "grad_norm": 0.9896523149800057, + "learning_rate": 5.3412237200819e-07, + "loss": 0.8019, + "step": 10036 + }, + { + "epoch": 0.8987184509485702, + "grad_norm": 1.1049265003686415, + "learning_rate": 5.331875828409327e-07, + "loss": 0.7827, + "step": 10037 + }, + { + "epoch": 0.8988079914936482, + "grad_norm": 1.01670629572103, + "learning_rate": 5.322535899910863e-07, + "loss": 0.786, + "step": 10038 + }, + { + "epoch": 0.8988975320387262, + "grad_norm": 1.0511879150515668, + "learning_rate": 5.313203935372158e-07, + "loss": 0.7791, + "step": 10039 + }, + { + "epoch": 0.8989870725838044, + "grad_norm": 1.0393754871319771, + "learning_rate": 5.303879935578182e-07, + "loss": 0.7647, + "step": 10040 + }, + { + "epoch": 0.8990766131288824, + "grad_norm": 1.116070174573382, + "learning_rate": 5.294563901313232e-07, + "loss": 0.8441, + "step": 10041 + }, + { + "epoch": 0.8991661536739605, + "grad_norm": 1.1020580966620328, + "learning_rate": 5.285255833360947e-07, + "loss": 0.7845, + "step": 10042 + }, + { + "epoch": 0.8992556942190385, + "grad_norm": 1.0971457403664175, + "learning_rate": 5.275955732504301e-07, + "loss": 0.8115, + "step": 10043 + }, + { + "epoch": 0.8993452347641167, + "grad_norm": 0.9251690386558937, + "learning_rate": 5.266663599525579e-07, + "loss": 0.7981, + "step": 10044 + }, + { + "epoch": 0.8994347753091947, + "grad_norm": 0.9515745576765963, + "learning_rate": 5.257379435206411e-07, + "loss": 0.7693, + "step": 10045 + }, + { + "epoch": 0.8995243158542727, + "grad_norm": 0.9206058224340953, + "learning_rate": 5.248103240327739e-07, + "loss": 0.8, + "step": 10046 + }, + { + "epoch": 0.8996138563993509, + "grad_norm": 0.9695190083188647, + "learning_rate": 5.238835015669863e-07, + "loss": 0.809, + "step": 10047 + }, + { + "epoch": 0.8997033969444289, + "grad_norm": 1.0747155323889144, + "learning_rate": 5.229574762012379e-07, + "loss": 0.8441, + "step": 10048 + }, + { + "epoch": 0.899792937489507, + "grad_norm": 0.9480782021570312, + "learning_rate": 5.220322480134243e-07, + "loss": 0.8133, + "step": 10049 + }, + { + "epoch": 0.899882478034585, + "grad_norm": 1.0084423027138234, + "learning_rate": 5.21107817081371e-07, + "loss": 0.8253, + "step": 10050 + }, + { + "epoch": 0.8999720185796631, + "grad_norm": 1.1366616227214632, + "learning_rate": 5.201841834828402e-07, + "loss": 0.8468, + "step": 10051 + }, + { + "epoch": 0.9000615591247412, + "grad_norm": 0.95141204694734, + "learning_rate": 5.192613472955243e-07, + "loss": 0.7937, + "step": 10052 + }, + { + "epoch": 0.9001510996698192, + "grad_norm": 1.194573400406679, + "learning_rate": 5.183393085970478e-07, + "loss": 0.8464, + "step": 10053 + }, + { + "epoch": 0.9002406402148974, + "grad_norm": 1.025638331724656, + "learning_rate": 5.174180674649721e-07, + "loss": 0.8315, + "step": 10054 + }, + { + "epoch": 0.9003301807599754, + "grad_norm": 1.0656291840117451, + "learning_rate": 5.164976239767872e-07, + "loss": 0.7724, + "step": 10055 + }, + { + "epoch": 0.9004197213050534, + "grad_norm": 1.2677672814740164, + "learning_rate": 5.15577978209918e-07, + "loss": 0.8444, + "step": 10056 + }, + { + "epoch": 0.9005092618501315, + "grad_norm": 0.9602801985604429, + "learning_rate": 5.146591302417236e-07, + "loss": 0.7902, + "step": 10057 + }, + { + "epoch": 0.9005988023952096, + "grad_norm": 0.9237174185980306, + "learning_rate": 5.137410801494902e-07, + "loss": 0.851, + "step": 10058 + }, + { + "epoch": 0.9006883429402877, + "grad_norm": 0.9987198666443217, + "learning_rate": 5.128238280104458e-07, + "loss": 0.7455, + "step": 10059 + }, + { + "epoch": 0.9007778834853657, + "grad_norm": 0.972489091235027, + "learning_rate": 5.119073739017455e-07, + "loss": 0.7527, + "step": 10060 + }, + { + "epoch": 0.9008674240304437, + "grad_norm": 0.9771328558788107, + "learning_rate": 5.109917179004775e-07, + "loss": 0.8108, + "step": 10061 + }, + { + "epoch": 0.9009569645755219, + "grad_norm": 1.0808820207200132, + "learning_rate": 5.100768600836647e-07, + "loss": 0.797, + "step": 10062 + }, + { + "epoch": 0.9010465051205999, + "grad_norm": 1.2570395925133155, + "learning_rate": 5.091628005282634e-07, + "loss": 0.8235, + "step": 10063 + }, + { + "epoch": 0.901136045665678, + "grad_norm": 0.9532771180583974, + "learning_rate": 5.082495393111564e-07, + "loss": 0.8272, + "step": 10064 + }, + { + "epoch": 0.9012255862107561, + "grad_norm": 0.9492457797170617, + "learning_rate": 5.073370765091678e-07, + "loss": 0.8173, + "step": 10065 + }, + { + "epoch": 0.9013151267558341, + "grad_norm": 1.0395294566610298, + "learning_rate": 5.06425412199052e-07, + "loss": 0.7871, + "step": 10066 + }, + { + "epoch": 0.9014046673009122, + "grad_norm": 1.386683375318751, + "learning_rate": 5.055145464574929e-07, + "loss": 0.7876, + "step": 10067 + }, + { + "epoch": 0.9014942078459902, + "grad_norm": 0.9790797269435996, + "learning_rate": 5.046044793611126e-07, + "loss": 0.8369, + "step": 10068 + }, + { + "epoch": 0.9015837483910684, + "grad_norm": 1.056691953471654, + "learning_rate": 5.036952109864579e-07, + "loss": 0.7543, + "step": 10069 + }, + { + "epoch": 0.9016732889361464, + "grad_norm": 1.1379718579382234, + "learning_rate": 5.027867414100163e-07, + "loss": 0.8071, + "step": 10070 + }, + { + "epoch": 0.9017628294812244, + "grad_norm": 0.921164365577179, + "learning_rate": 5.018790707082066e-07, + "loss": 0.7555, + "step": 10071 + }, + { + "epoch": 0.9018523700263026, + "grad_norm": 0.9301831413461399, + "learning_rate": 5.009721989573779e-07, + "loss": 0.776, + "step": 10072 + }, + { + "epoch": 0.9019419105713806, + "grad_norm": 1.0118199467700413, + "learning_rate": 5.000661262338135e-07, + "loss": 0.7844, + "step": 10073 + }, + { + "epoch": 0.9020314511164587, + "grad_norm": 0.8888780205303195, + "learning_rate": 4.991608526137293e-07, + "loss": 0.7208, + "step": 10074 + }, + { + "epoch": 0.9021209916615367, + "grad_norm": 1.1829061196171597, + "learning_rate": 4.982563781732741e-07, + "loss": 0.7916, + "step": 10075 + }, + { + "epoch": 0.9022105322066148, + "grad_norm": 0.9640349294479128, + "learning_rate": 4.973527029885261e-07, + "loss": 0.7989, + "step": 10076 + }, + { + "epoch": 0.9023000727516929, + "grad_norm": 1.04957770290259, + "learning_rate": 4.964498271355044e-07, + "loss": 0.7915, + "step": 10077 + }, + { + "epoch": 0.9023896132967709, + "grad_norm": 0.9269261850396617, + "learning_rate": 4.95547750690154e-07, + "loss": 0.7832, + "step": 10078 + }, + { + "epoch": 0.902479153841849, + "grad_norm": 1.0523619531204833, + "learning_rate": 4.946464737283562e-07, + "loss": 0.7505, + "step": 10079 + }, + { + "epoch": 0.9025686943869271, + "grad_norm": 0.905655591157747, + "learning_rate": 4.937459963259206e-07, + "loss": 0.7648, + "step": 10080 + }, + { + "epoch": 0.9026582349320051, + "grad_norm": 1.142042422030418, + "learning_rate": 4.92846318558593e-07, + "loss": 0.7564, + "step": 10081 + }, + { + "epoch": 0.9027477754770832, + "grad_norm": 0.9556214693921594, + "learning_rate": 4.919474405020519e-07, + "loss": 0.8269, + "step": 10082 + }, + { + "epoch": 0.9028373160221613, + "grad_norm": 1.2390691981544155, + "learning_rate": 4.910493622319079e-07, + "loss": 0.789, + "step": 10083 + }, + { + "epoch": 0.9029268565672394, + "grad_norm": 0.9645356460804934, + "learning_rate": 4.901520838237062e-07, + "loss": 0.8099, + "step": 10084 + }, + { + "epoch": 0.9030163971123174, + "grad_norm": 0.9711658016216062, + "learning_rate": 4.892556053529218e-07, + "loss": 0.7426, + "step": 10085 + }, + { + "epoch": 0.9031059376573954, + "grad_norm": 0.9766055890572426, + "learning_rate": 4.883599268949624e-07, + "loss": 0.7409, + "step": 10086 + }, + { + "epoch": 0.9031954782024736, + "grad_norm": 0.9445889788747694, + "learning_rate": 4.874650485251697e-07, + "loss": 0.752, + "step": 10087 + }, + { + "epoch": 0.9032850187475516, + "grad_norm": 0.9919993056573089, + "learning_rate": 4.865709703188193e-07, + "loss": 0.8041, + "step": 10088 + }, + { + "epoch": 0.9033745592926297, + "grad_norm": 0.9849671556416439, + "learning_rate": 4.856776923511164e-07, + "loss": 0.8344, + "step": 10089 + }, + { + "epoch": 0.9034640998377078, + "grad_norm": 1.1437429843570166, + "learning_rate": 4.847852146972032e-07, + "loss": 0.8529, + "step": 10090 + }, + { + "epoch": 0.9035536403827858, + "grad_norm": 0.9991252872277344, + "learning_rate": 4.838935374321496e-07, + "loss": 0.7914, + "step": 10091 + }, + { + "epoch": 0.9036431809278639, + "grad_norm": 0.9551529646731034, + "learning_rate": 4.830026606309623e-07, + "loss": 0.8113, + "step": 10092 + }, + { + "epoch": 0.9037327214729419, + "grad_norm": 1.1020543772302855, + "learning_rate": 4.82112584368577e-07, + "loss": 0.7484, + "step": 10093 + }, + { + "epoch": 0.9038222620180201, + "grad_norm": 1.069545370514513, + "learning_rate": 4.812233087198659e-07, + "loss": 0.845, + "step": 10094 + }, + { + "epoch": 0.9039118025630981, + "grad_norm": 1.2093081507042924, + "learning_rate": 4.803348337596292e-07, + "loss": 0.7743, + "step": 10095 + }, + { + "epoch": 0.9040013431081761, + "grad_norm": 0.9619773413538854, + "learning_rate": 4.794471595626071e-07, + "loss": 0.7626, + "step": 10096 + }, + { + "epoch": 0.9040908836532542, + "grad_norm": 0.979422762207851, + "learning_rate": 4.785602862034644e-07, + "loss": 0.8242, + "step": 10097 + }, + { + "epoch": 0.9041804241983323, + "grad_norm": 1.072534225404781, + "learning_rate": 4.776742137568025e-07, + "loss": 0.7809, + "step": 10098 + }, + { + "epoch": 0.9042699647434104, + "grad_norm": 0.8997036291387532, + "learning_rate": 4.767889422971561e-07, + "loss": 0.7604, + "step": 10099 + }, + { + "epoch": 0.9043595052884884, + "grad_norm": 0.9221515491070817, + "learning_rate": 4.7590447189899025e-07, + "loss": 0.7794, + "step": 10100 + }, + { + "epoch": 0.9044490458335666, + "grad_norm": 1.0677456446305342, + "learning_rate": 4.7502080263670315e-07, + "loss": 0.7368, + "step": 10101 + }, + { + "epoch": 0.9045385863786446, + "grad_norm": 0.9372921038753773, + "learning_rate": 4.7413793458462755e-07, + "loss": 0.8296, + "step": 10102 + }, + { + "epoch": 0.9046281269237226, + "grad_norm": 0.9621980107243769, + "learning_rate": 4.7325586781702737e-07, + "loss": 0.7697, + "step": 10103 + }, + { + "epoch": 0.9047176674688007, + "grad_norm": 0.9941961937849999, + "learning_rate": 4.7237460240809884e-07, + "loss": 0.8402, + "step": 10104 + }, + { + "epoch": 0.9048072080138788, + "grad_norm": 0.9666086497788448, + "learning_rate": 4.7149413843197047e-07, + "loss": 0.7389, + "step": 10105 + }, + { + "epoch": 0.9048967485589569, + "grad_norm": 1.0544866015025116, + "learning_rate": 4.7061447596270407e-07, + "loss": 0.7683, + "step": 10106 + }, + { + "epoch": 0.9049862891040349, + "grad_norm": 1.1227543198350987, + "learning_rate": 4.69735615074296e-07, + "loss": 0.8433, + "step": 10107 + }, + { + "epoch": 0.905075829649113, + "grad_norm": 0.9333528756997943, + "learning_rate": 4.688575558406705e-07, + "loss": 0.7538, + "step": 10108 + }, + { + "epoch": 0.9051653701941911, + "grad_norm": 1.0740345105537787, + "learning_rate": 4.679802983356885e-07, + "loss": 0.8125, + "step": 10109 + }, + { + "epoch": 0.9052549107392691, + "grad_norm": 0.9514236392400367, + "learning_rate": 4.67103842633142e-07, + "loss": 0.83, + "step": 10110 + }, + { + "epoch": 0.9053444512843472, + "grad_norm": 1.0201465676417034, + "learning_rate": 4.662281888067555e-07, + "loss": 0.8018, + "step": 10111 + }, + { + "epoch": 0.9054339918294253, + "grad_norm": 1.0368656668849545, + "learning_rate": 4.653533369301855e-07, + "loss": 0.8218, + "step": 10112 + }, + { + "epoch": 0.9055235323745033, + "grad_norm": 0.9105575020161973, + "learning_rate": 4.644792870770221e-07, + "loss": 0.8092, + "step": 10113 + }, + { + "epoch": 0.9056130729195814, + "grad_norm": 1.0608751803786725, + "learning_rate": 4.636060393207886e-07, + "loss": 0.808, + "step": 10114 + }, + { + "epoch": 0.9057026134646594, + "grad_norm": 1.0439123481748924, + "learning_rate": 4.6273359373493753e-07, + "loss": 0.8156, + "step": 10115 + }, + { + "epoch": 0.9057921540097376, + "grad_norm": 0.9011035952167434, + "learning_rate": 4.61861950392859e-07, + "loss": 0.7735, + "step": 10116 + }, + { + "epoch": 0.9058816945548156, + "grad_norm": 1.0058359741762124, + "learning_rate": 4.6099110936786985e-07, + "loss": 0.8308, + "step": 10117 + }, + { + "epoch": 0.9059712350998936, + "grad_norm": 0.9815458544954996, + "learning_rate": 4.601210707332238e-07, + "loss": 0.8557, + "step": 10118 + }, + { + "epoch": 0.9060607756449718, + "grad_norm": 0.9465152881641007, + "learning_rate": 4.5925183456210665e-07, + "loss": 0.7849, + "step": 10119 + }, + { + "epoch": 0.9061503161900498, + "grad_norm": 0.9082264006103713, + "learning_rate": 4.5838340092763444e-07, + "loss": 0.7726, + "step": 10120 + }, + { + "epoch": 0.9062398567351279, + "grad_norm": 1.0123992821896415, + "learning_rate": 4.5751576990285654e-07, + "loss": 0.804, + "step": 10121 + }, + { + "epoch": 0.9063293972802059, + "grad_norm": 0.9972070069634262, + "learning_rate": 4.566489415607567e-07, + "loss": 0.8332, + "step": 10122 + }, + { + "epoch": 0.906418937825284, + "grad_norm": 1.0163971681306823, + "learning_rate": 4.5578291597424995e-07, + "loss": 0.7979, + "step": 10123 + }, + { + "epoch": 0.9065084783703621, + "grad_norm": 1.0401426624712895, + "learning_rate": 4.5491769321617916e-07, + "loss": 0.8442, + "step": 10124 + }, + { + "epoch": 0.9065980189154401, + "grad_norm": 0.9318571258489935, + "learning_rate": 4.5405327335932946e-07, + "loss": 0.8376, + "step": 10125 + }, + { + "epoch": 0.9066875594605183, + "grad_norm": 1.0706044477015795, + "learning_rate": 4.5318965647641153e-07, + "loss": 0.8298, + "step": 10126 + }, + { + "epoch": 0.9067771000055963, + "grad_norm": 1.0621141142874881, + "learning_rate": 4.5232684264006845e-07, + "loss": 0.7918, + "step": 10127 + }, + { + "epoch": 0.9068666405506743, + "grad_norm": 1.0272380538193457, + "learning_rate": 4.514648319228798e-07, + "loss": 0.7986, + "step": 10128 + }, + { + "epoch": 0.9069561810957524, + "grad_norm": 0.9323940423354363, + "learning_rate": 4.5060362439735326e-07, + "loss": 0.7786, + "step": 10129 + }, + { + "epoch": 0.9070457216408305, + "grad_norm": 0.9685156727642298, + "learning_rate": 4.4974322013592865e-07, + "loss": 0.8252, + "step": 10130 + }, + { + "epoch": 0.9071352621859086, + "grad_norm": 0.9884631665684678, + "learning_rate": 4.4888361921098466e-07, + "loss": 0.8122, + "step": 10131 + }, + { + "epoch": 0.9072248027309866, + "grad_norm": 1.0370423356327139, + "learning_rate": 4.4802482169482687e-07, + "loss": 0.8216, + "step": 10132 + }, + { + "epoch": 0.9073143432760646, + "grad_norm": 1.0412646465163535, + "learning_rate": 4.471668276596941e-07, + "loss": 0.8337, + "step": 10133 + }, + { + "epoch": 0.9074038838211428, + "grad_norm": 1.1843716308736492, + "learning_rate": 4.4630963717775864e-07, + "loss": 0.804, + "step": 10134 + }, + { + "epoch": 0.9074934243662208, + "grad_norm": 0.9016651865895908, + "learning_rate": 4.4545325032112284e-07, + "loss": 0.7711, + "step": 10135 + }, + { + "epoch": 0.9075829649112989, + "grad_norm": 0.9886539876548629, + "learning_rate": 4.445976671618224e-07, + "loss": 0.766, + "step": 10136 + }, + { + "epoch": 0.907672505456377, + "grad_norm": 1.0446380252464238, + "learning_rate": 4.4374288777182973e-07, + "loss": 0.8285, + "step": 10137 + }, + { + "epoch": 0.907762046001455, + "grad_norm": 0.9307301307100393, + "learning_rate": 4.42888912223044e-07, + "loss": 0.8114, + "step": 10138 + }, + { + "epoch": 0.9078515865465331, + "grad_norm": 1.0145652387066293, + "learning_rate": 4.4203574058730105e-07, + "loss": 0.7678, + "step": 10139 + }, + { + "epoch": 0.9079411270916111, + "grad_norm": 0.9407210564805037, + "learning_rate": 4.4118337293636346e-07, + "loss": 0.7867, + "step": 10140 + }, + { + "epoch": 0.9080306676366893, + "grad_norm": 1.0252578729277835, + "learning_rate": 4.4033180934193065e-07, + "loss": 0.7869, + "step": 10141 + }, + { + "epoch": 0.9081202081817673, + "grad_norm": 1.0430196845598696, + "learning_rate": 4.3948104987563414e-07, + "loss": 0.797, + "step": 10142 + }, + { + "epoch": 0.9082097487268453, + "grad_norm": 0.9958909556896179, + "learning_rate": 4.3863109460903554e-07, + "loss": 0.7784, + "step": 10143 + }, + { + "epoch": 0.9082992892719235, + "grad_norm": 0.9211012379629752, + "learning_rate": 4.3778194361363323e-07, + "loss": 0.788, + "step": 10144 + }, + { + "epoch": 0.9083888298170015, + "grad_norm": 1.0138301343921006, + "learning_rate": 4.369335969608546e-07, + "loss": 0.826, + "step": 10145 + }, + { + "epoch": 0.9084783703620796, + "grad_norm": 0.9057143437302676, + "learning_rate": 4.36086054722058e-07, + "loss": 0.7801, + "step": 10146 + }, + { + "epoch": 0.9085679109071576, + "grad_norm": 1.0678102513188796, + "learning_rate": 4.352393169685354e-07, + "loss": 0.7603, + "step": 10147 + }, + { + "epoch": 0.9086574514522358, + "grad_norm": 1.3628057258257065, + "learning_rate": 4.343933837715131e-07, + "loss": 0.798, + "step": 10148 + }, + { + "epoch": 0.9087469919973138, + "grad_norm": 0.9315675573957879, + "learning_rate": 4.335482552021464e-07, + "loss": 0.7851, + "step": 10149 + }, + { + "epoch": 0.9088365325423918, + "grad_norm": 0.9553972345262876, + "learning_rate": 4.3270393133152845e-07, + "loss": 0.8499, + "step": 10150 + }, + { + "epoch": 0.9089260730874699, + "grad_norm": 1.0400301828637, + "learning_rate": 4.31860412230678e-07, + "loss": 0.8176, + "step": 10151 + }, + { + "epoch": 0.909015613632548, + "grad_norm": 0.9600373634190053, + "learning_rate": 4.310176979705505e-07, + "loss": 0.8263, + "step": 10152 + }, + { + "epoch": 0.909105154177626, + "grad_norm": 0.9263208593672583, + "learning_rate": 4.301757886220315e-07, + "loss": 0.8405, + "step": 10153 + }, + { + "epoch": 0.9091946947227041, + "grad_norm": 0.928051505557771, + "learning_rate": 4.2933468425593984e-07, + "loss": 0.8087, + "step": 10154 + }, + { + "epoch": 0.9092842352677822, + "grad_norm": 1.024351940536971, + "learning_rate": 4.284943849430245e-07, + "loss": 0.8081, + "step": 10155 + }, + { + "epoch": 0.9093737758128603, + "grad_norm": 0.9950679271675924, + "learning_rate": 4.2765489075397457e-07, + "loss": 0.8267, + "step": 10156 + }, + { + "epoch": 0.9094633163579383, + "grad_norm": 0.9504087689479536, + "learning_rate": 4.268162017594002e-07, + "loss": 0.7857, + "step": 10157 + }, + { + "epoch": 0.9095528569030163, + "grad_norm": 1.0887880979556708, + "learning_rate": 4.2597831802985044e-07, + "loss": 0.8338, + "step": 10158 + }, + { + "epoch": 0.9096423974480945, + "grad_norm": 0.8642062703817855, + "learning_rate": 4.2514123963580564e-07, + "loss": 0.8047, + "step": 10159 + }, + { + "epoch": 0.9097319379931725, + "grad_norm": 0.9896844748287289, + "learning_rate": 4.243049666476784e-07, + "loss": 0.798, + "step": 10160 + }, + { + "epoch": 0.9098214785382506, + "grad_norm": 0.9746433301020835, + "learning_rate": 4.2346949913581236e-07, + "loss": 0.8103, + "step": 10161 + }, + { + "epoch": 0.9099110190833287, + "grad_norm": 1.0602153839573412, + "learning_rate": 4.226348371704858e-07, + "loss": 0.7734, + "step": 10162 + }, + { + "epoch": 0.9100005596284068, + "grad_norm": 1.1885229280885539, + "learning_rate": 4.218009808219059e-07, + "loss": 0.8571, + "step": 10163 + }, + { + "epoch": 0.9100901001734848, + "grad_norm": 0.9180805827794428, + "learning_rate": 4.2096793016021655e-07, + "loss": 0.7572, + "step": 10164 + }, + { + "epoch": 0.9101796407185628, + "grad_norm": 0.9973093324549029, + "learning_rate": 4.201356852554883e-07, + "loss": 0.7732, + "step": 10165 + }, + { + "epoch": 0.910269181263641, + "grad_norm": 1.0270850759923835, + "learning_rate": 4.193042461777286e-07, + "loss": 0.7463, + "step": 10166 + }, + { + "epoch": 0.910358721808719, + "grad_norm": 0.906425058716286, + "learning_rate": 4.184736129968758e-07, + "loss": 0.8019, + "step": 10167 + }, + { + "epoch": 0.910448262353797, + "grad_norm": 0.9900453178096095, + "learning_rate": 4.176437857827986e-07, + "loss": 0.7878, + "step": 10168 + }, + { + "epoch": 0.9105378028988751, + "grad_norm": 0.8977143647306958, + "learning_rate": 4.168147646053e-07, + "loss": 0.7941, + "step": 10169 + }, + { + "epoch": 0.9106273434439532, + "grad_norm": 0.9872389206654621, + "learning_rate": 4.1598654953411535e-07, + "loss": 0.7914, + "step": 10170 + }, + { + "epoch": 0.9107168839890313, + "grad_norm": 1.0319970666729261, + "learning_rate": 4.1515914063890993e-07, + "loss": 0.7406, + "step": 10171 + }, + { + "epoch": 0.9108064245341093, + "grad_norm": 1.0257465439504205, + "learning_rate": 4.1433253798928374e-07, + "loss": 0.7766, + "step": 10172 + }, + { + "epoch": 0.9108959650791875, + "grad_norm": 1.034188943002644, + "learning_rate": 4.135067416547678e-07, + "loss": 0.823, + "step": 10173 + }, + { + "epoch": 0.9109855056242655, + "grad_norm": 0.9158666103136256, + "learning_rate": 4.126817517048243e-07, + "loss": 0.762, + "step": 10174 + }, + { + "epoch": 0.9110750461693435, + "grad_norm": 0.9446223979817144, + "learning_rate": 4.11857568208851e-07, + "loss": 0.816, + "step": 10175 + }, + { + "epoch": 0.9111645867144216, + "grad_norm": 0.9531483832959262, + "learning_rate": 4.110341912361726e-07, + "loss": 0.7757, + "step": 10176 + }, + { + "epoch": 0.9112541272594997, + "grad_norm": 1.0616937631812924, + "learning_rate": 4.102116208560514e-07, + "loss": 0.7469, + "step": 10177 + }, + { + "epoch": 0.9113436678045778, + "grad_norm": 1.0062312838250378, + "learning_rate": 4.0938985713767864e-07, + "loss": 0.7843, + "step": 10178 + }, + { + "epoch": 0.9114332083496558, + "grad_norm": 1.0058391514229243, + "learning_rate": 4.0856890015017803e-07, + "loss": 0.8034, + "step": 10179 + }, + { + "epoch": 0.911522748894734, + "grad_norm": 0.9376062084849668, + "learning_rate": 4.077487499626054e-07, + "loss": 0.7801, + "step": 10180 + }, + { + "epoch": 0.911612289439812, + "grad_norm": 1.0009489326886032, + "learning_rate": 4.0692940664395e-07, + "loss": 0.8122, + "step": 10181 + }, + { + "epoch": 0.91170182998489, + "grad_norm": 1.0748307119914122, + "learning_rate": 4.061108702631311e-07, + "loss": 0.7995, + "step": 10182 + }, + { + "epoch": 0.9117913705299681, + "grad_norm": 1.0781528884024503, + "learning_rate": 4.0529314088900487e-07, + "loss": 0.8007, + "step": 10183 + }, + { + "epoch": 0.9118809110750462, + "grad_norm": 0.990521916376194, + "learning_rate": 4.044762185903495e-07, + "loss": 0.8206, + "step": 10184 + }, + { + "epoch": 0.9119704516201242, + "grad_norm": 1.123736018925702, + "learning_rate": 4.036601034358878e-07, + "loss": 0.7949, + "step": 10185 + }, + { + "epoch": 0.9120599921652023, + "grad_norm": 0.8628727479393513, + "learning_rate": 4.02844795494266e-07, + "loss": 0.7432, + "step": 10186 + }, + { + "epoch": 0.9121495327102803, + "grad_norm": 1.2678452501147484, + "learning_rate": 4.0203029483406595e-07, + "loss": 0.8428, + "step": 10187 + }, + { + "epoch": 0.9122390732553585, + "grad_norm": 0.9471598808735879, + "learning_rate": 4.0121660152380173e-07, + "loss": 0.7749, + "step": 10188 + }, + { + "epoch": 0.9123286138004365, + "grad_norm": 0.8510305240144038, + "learning_rate": 4.0040371563191627e-07, + "loss": 0.7768, + "step": 10189 + }, + { + "epoch": 0.9124181543455145, + "grad_norm": 1.1740486285560436, + "learning_rate": 3.995916372267872e-07, + "loss": 0.756, + "step": 10190 + }, + { + "epoch": 0.9125076948905927, + "grad_norm": 1.0382179407886767, + "learning_rate": 3.9878036637672535e-07, + "loss": 0.8139, + "step": 10191 + }, + { + "epoch": 0.9125972354356707, + "grad_norm": 1.262502287741117, + "learning_rate": 3.9796990314997176e-07, + "loss": 0.7537, + "step": 10192 + }, + { + "epoch": 0.9126867759807488, + "grad_norm": 1.0480601614789575, + "learning_rate": 3.9716024761469963e-07, + "loss": 0.8344, + "step": 10193 + }, + { + "epoch": 0.9127763165258268, + "grad_norm": 1.0270592052910643, + "learning_rate": 3.963513998390156e-07, + "loss": 0.799, + "step": 10194 + }, + { + "epoch": 0.912865857070905, + "grad_norm": 1.0804660201421288, + "learning_rate": 3.955433598909553e-07, + "loss": 0.7522, + "step": 10195 + }, + { + "epoch": 0.912955397615983, + "grad_norm": 1.009607226771179, + "learning_rate": 3.947361278384898e-07, + "loss": 0.8016, + "step": 10196 + }, + { + "epoch": 0.913044938161061, + "grad_norm": 0.9831734748289264, + "learning_rate": 3.9392970374951935e-07, + "loss": 0.8159, + "step": 10197 + }, + { + "epoch": 0.9131344787061392, + "grad_norm": 0.9031422659253104, + "learning_rate": 3.931240876918796e-07, + "loss": 0.7399, + "step": 10198 + }, + { + "epoch": 0.9132240192512172, + "grad_norm": 1.141100402046188, + "learning_rate": 3.923192797333375e-07, + "loss": 0.7608, + "step": 10199 + }, + { + "epoch": 0.9133135597962952, + "grad_norm": 0.9437089718228813, + "learning_rate": 3.915152799415867e-07, + "loss": 0.7851, + "step": 10200 + }, + { + "epoch": 0.9134031003413733, + "grad_norm": 1.0448268550414508, + "learning_rate": 3.9071208838426077e-07, + "loss": 0.8008, + "step": 10201 + }, + { + "epoch": 0.9134926408864514, + "grad_norm": 1.3473923993908299, + "learning_rate": 3.899097051289191e-07, + "loss": 0.798, + "step": 10202 + }, + { + "epoch": 0.9135821814315295, + "grad_norm": 0.8617714468052282, + "learning_rate": 3.891081302430555e-07, + "loss": 0.709, + "step": 10203 + }, + { + "epoch": 0.9136717219766075, + "grad_norm": 0.9085286574816174, + "learning_rate": 3.883073637940982e-07, + "loss": 0.7427, + "step": 10204 + }, + { + "epoch": 0.9137612625216855, + "grad_norm": 0.9788919857980458, + "learning_rate": 3.875074058494055e-07, + "loss": 0.8121, + "step": 10205 + }, + { + "epoch": 0.9138508030667637, + "grad_norm": 0.9906544647316243, + "learning_rate": 3.867082564762636e-07, + "loss": 0.8012, + "step": 10206 + }, + { + "epoch": 0.9139403436118417, + "grad_norm": 0.9351380561191347, + "learning_rate": 3.859099157418966e-07, + "loss": 0.7901, + "step": 10207 + }, + { + "epoch": 0.9140298841569198, + "grad_norm": 1.0301687794620427, + "learning_rate": 3.851123837134585e-07, + "loss": 0.7747, + "step": 10208 + }, + { + "epoch": 0.9141194247019979, + "grad_norm": 0.950858494470719, + "learning_rate": 3.8431566045803335e-07, + "loss": 0.8272, + "step": 10209 + }, + { + "epoch": 0.914208965247076, + "grad_norm": 0.9586689899143684, + "learning_rate": 3.835197460426421e-07, + "loss": 0.8256, + "step": 10210 + }, + { + "epoch": 0.914298505792154, + "grad_norm": 1.095436161544864, + "learning_rate": 3.8272464053423106e-07, + "loss": 0.8512, + "step": 10211 + }, + { + "epoch": 0.914388046337232, + "grad_norm": 1.005235550853481, + "learning_rate": 3.8193034399968465e-07, + "loss": 0.7989, + "step": 10212 + }, + { + "epoch": 0.9144775868823102, + "grad_norm": 0.974354920986707, + "learning_rate": 3.811368565058138e-07, + "loss": 0.7909, + "step": 10213 + }, + { + "epoch": 0.9145671274273882, + "grad_norm": 1.0260295532449546, + "learning_rate": 3.803441781193662e-07, + "loss": 0.8174, + "step": 10214 + }, + { + "epoch": 0.9146566679724663, + "grad_norm": 1.023667998690655, + "learning_rate": 3.7955230890701743e-07, + "loss": 0.8216, + "step": 10215 + }, + { + "epoch": 0.9147462085175444, + "grad_norm": 0.9335557702771213, + "learning_rate": 3.7876124893538093e-07, + "loss": 0.8065, + "step": 10216 + }, + { + "epoch": 0.9148357490626224, + "grad_norm": 1.0419615955520867, + "learning_rate": 3.779709982709945e-07, + "loss": 0.8072, + "step": 10217 + }, + { + "epoch": 0.9149252896077005, + "grad_norm": 1.0283557518177207, + "learning_rate": 3.7718155698033166e-07, + "loss": 0.8066, + "step": 10218 + }, + { + "epoch": 0.9150148301527785, + "grad_norm": 1.4801867096547554, + "learning_rate": 3.763929251297982e-07, + "loss": 0.8334, + "step": 10219 + }, + { + "epoch": 0.9151043706978567, + "grad_norm": 0.9288379508981409, + "learning_rate": 3.7560510278573215e-07, + "loss": 0.7398, + "step": 10220 + }, + { + "epoch": 0.9151939112429347, + "grad_norm": 0.90143203968346, + "learning_rate": 3.748180900144016e-07, + "loss": 0.7875, + "step": 10221 + }, + { + "epoch": 0.9152834517880127, + "grad_norm": 1.0819278691546608, + "learning_rate": 3.7403188688200697e-07, + "loss": 0.8123, + "step": 10222 + }, + { + "epoch": 0.9153729923330908, + "grad_norm": 0.961700817108955, + "learning_rate": 3.73246493454682e-07, + "loss": 0.8046, + "step": 10223 + }, + { + "epoch": 0.9154625328781689, + "grad_norm": 0.9379860371131326, + "learning_rate": 3.7246190979849164e-07, + "loss": 0.7576, + "step": 10224 + }, + { + "epoch": 0.915552073423247, + "grad_norm": 0.9357138820755269, + "learning_rate": 3.7167813597943305e-07, + "loss": 0.837, + "step": 10225 + }, + { + "epoch": 0.915641613968325, + "grad_norm": 0.9985275547669544, + "learning_rate": 3.708951720634324e-07, + "loss": 0.7893, + "step": 10226 + }, + { + "epoch": 0.9157311545134031, + "grad_norm": 0.9334485696251853, + "learning_rate": 3.701130181163515e-07, + "loss": 0.7995, + "step": 10227 + }, + { + "epoch": 0.9158206950584812, + "grad_norm": 0.959824260452471, + "learning_rate": 3.693316742039832e-07, + "loss": 0.8478, + "step": 10228 + }, + { + "epoch": 0.9159102356035592, + "grad_norm": 1.076958330532077, + "learning_rate": 3.6855114039205164e-07, + "loss": 0.7893, + "step": 10229 + }, + { + "epoch": 0.9159997761486373, + "grad_norm": 0.9601203776817674, + "learning_rate": 3.6777141674621095e-07, + "loss": 0.7753, + "step": 10230 + }, + { + "epoch": 0.9160893166937154, + "grad_norm": 0.9981316968393739, + "learning_rate": 3.6699250333204984e-07, + "loss": 0.7932, + "step": 10231 + }, + { + "epoch": 0.9161788572387934, + "grad_norm": 1.1356403369756547, + "learning_rate": 3.6621440021508916e-07, + "loss": 0.8022, + "step": 10232 + }, + { + "epoch": 0.9162683977838715, + "grad_norm": 0.9584375790747502, + "learning_rate": 3.654371074607788e-07, + "loss": 0.8468, + "step": 10233 + }, + { + "epoch": 0.9163579383289496, + "grad_norm": 0.8981791017133977, + "learning_rate": 3.646606251345031e-07, + "loss": 0.7901, + "step": 10234 + }, + { + "epoch": 0.9164474788740277, + "grad_norm": 1.0212996232050626, + "learning_rate": 3.638849533015776e-07, + "loss": 0.8039, + "step": 10235 + }, + { + "epoch": 0.9165370194191057, + "grad_norm": 0.9762218321327993, + "learning_rate": 3.631100920272479e-07, + "loss": 0.8268, + "step": 10236 + }, + { + "epoch": 0.9166265599641837, + "grad_norm": 0.9567346393948778, + "learning_rate": 3.62336041376693e-07, + "loss": 0.7728, + "step": 10237 + }, + { + "epoch": 0.9167161005092619, + "grad_norm": 0.919520551745331, + "learning_rate": 3.615628014150241e-07, + "loss": 0.7774, + "step": 10238 + }, + { + "epoch": 0.9168056410543399, + "grad_norm": 1.0762646118226438, + "learning_rate": 3.6079037220728475e-07, + "loss": 0.7836, + "step": 10239 + }, + { + "epoch": 0.916895181599418, + "grad_norm": 1.0924485726285225, + "learning_rate": 3.600187538184463e-07, + "loss": 0.8134, + "step": 10240 + }, + { + "epoch": 0.916984722144496, + "grad_norm": 1.0753690952790407, + "learning_rate": 3.5924794631341797e-07, + "loss": 0.8113, + "step": 10241 + }, + { + "epoch": 0.9170742626895741, + "grad_norm": 0.9986894702516604, + "learning_rate": 3.584779497570345e-07, + "loss": 0.7979, + "step": 10242 + }, + { + "epoch": 0.9171638032346522, + "grad_norm": 0.9876691529749223, + "learning_rate": 3.5770876421406974e-07, + "loss": 0.7847, + "step": 10243 + }, + { + "epoch": 0.9172533437797302, + "grad_norm": 0.9212064134206783, + "learning_rate": 3.5694038974921854e-07, + "loss": 0.7636, + "step": 10244 + }, + { + "epoch": 0.9173428843248084, + "grad_norm": 1.0202913456382599, + "learning_rate": 3.5617282642712025e-07, + "loss": 0.7814, + "step": 10245 + }, + { + "epoch": 0.9174324248698864, + "grad_norm": 0.9392893567436356, + "learning_rate": 3.5540607431233665e-07, + "loss": 0.7895, + "step": 10246 + }, + { + "epoch": 0.9175219654149644, + "grad_norm": 0.9483487718985076, + "learning_rate": 3.546401334693661e-07, + "loss": 0.8258, + "step": 10247 + }, + { + "epoch": 0.9176115059600425, + "grad_norm": 0.9518491887397156, + "learning_rate": 3.5387500396263486e-07, + "loss": 0.7746, + "step": 10248 + }, + { + "epoch": 0.9177010465051206, + "grad_norm": 0.962848039465841, + "learning_rate": 3.5311068585650697e-07, + "loss": 0.7786, + "step": 10249 + }, + { + "epoch": 0.9177905870501987, + "grad_norm": 0.9081570365689157, + "learning_rate": 3.5234717921526997e-07, + "loss": 0.763, + "step": 10250 + }, + { + "epoch": 0.9178801275952767, + "grad_norm": 1.1049134053822405, + "learning_rate": 3.5158448410314796e-07, + "loss": 0.8214, + "step": 10251 + }, + { + "epoch": 0.9179696681403549, + "grad_norm": 0.9728374112404232, + "learning_rate": 3.508226005842996e-07, + "loss": 0.7774, + "step": 10252 + }, + { + "epoch": 0.9180592086854329, + "grad_norm": 1.1548049432173089, + "learning_rate": 3.500615287228093e-07, + "loss": 0.8208, + "step": 10253 + }, + { + "epoch": 0.9181487492305109, + "grad_norm": 1.054341147029551, + "learning_rate": 3.493012685826991e-07, + "loss": 0.8193, + "step": 10254 + }, + { + "epoch": 0.918238289775589, + "grad_norm": 0.9251262072918132, + "learning_rate": 3.485418202279156e-07, + "loss": 0.829, + "step": 10255 + }, + { + "epoch": 0.9183278303206671, + "grad_norm": 0.9895891884770561, + "learning_rate": 3.477831837223433e-07, + "loss": 0.7604, + "step": 10256 + }, + { + "epoch": 0.9184173708657452, + "grad_norm": 1.0290115796664598, + "learning_rate": 3.470253591297945e-07, + "loss": 0.799, + "step": 10257 + }, + { + "epoch": 0.9185069114108232, + "grad_norm": 1.0921393300558306, + "learning_rate": 3.462683465140182e-07, + "loss": 0.8361, + "step": 10258 + }, + { + "epoch": 0.9185964519559012, + "grad_norm": 1.6036710637757527, + "learning_rate": 3.455121459386901e-07, + "loss": 0.8026, + "step": 10259 + }, + { + "epoch": 0.9186859925009794, + "grad_norm": 0.9964055039713121, + "learning_rate": 3.447567574674193e-07, + "loss": 0.8651, + "step": 10260 + }, + { + "epoch": 0.9187755330460574, + "grad_norm": 1.1435343128440822, + "learning_rate": 3.4400218116374505e-07, + "loss": 0.8444, + "step": 10261 + }, + { + "epoch": 0.9188650735911355, + "grad_norm": 0.9001133359565945, + "learning_rate": 3.432484170911421e-07, + "loss": 0.8203, + "step": 10262 + }, + { + "epoch": 0.9189546141362136, + "grad_norm": 0.9802295841943113, + "learning_rate": 3.4249546531301194e-07, + "loss": 0.7422, + "step": 10263 + }, + { + "epoch": 0.9190441546812916, + "grad_norm": 1.2147861103605762, + "learning_rate": 3.417433258926939e-07, + "loss": 0.794, + "step": 10264 + }, + { + "epoch": 0.9191336952263697, + "grad_norm": 1.6637536706191507, + "learning_rate": 3.4099199889345515e-07, + "loss": 0.7764, + "step": 10265 + }, + { + "epoch": 0.9192232357714477, + "grad_norm": 1.0152571170785933, + "learning_rate": 3.4024148437849293e-07, + "loss": 0.816, + "step": 10266 + }, + { + "epoch": 0.9193127763165259, + "grad_norm": 0.9804225187867743, + "learning_rate": 3.394917824109378e-07, + "loss": 0.7826, + "step": 10267 + }, + { + "epoch": 0.9194023168616039, + "grad_norm": 0.8952562960633743, + "learning_rate": 3.3874289305385387e-07, + "loss": 0.7971, + "step": 10268 + }, + { + "epoch": 0.9194918574066819, + "grad_norm": 1.0381131654830873, + "learning_rate": 3.379948163702329e-07, + "loss": 0.8116, + "step": 10269 + }, + { + "epoch": 0.9195813979517601, + "grad_norm": 1.0244903444210625, + "learning_rate": 3.3724755242300454e-07, + "loss": 0.809, + "step": 10270 + }, + { + "epoch": 0.9196709384968381, + "grad_norm": 0.9754442902640937, + "learning_rate": 3.36501101275023e-07, + "loss": 0.8143, + "step": 10271 + }, + { + "epoch": 0.9197604790419162, + "grad_norm": 0.9811801563602721, + "learning_rate": 3.3575546298907914e-07, + "loss": 0.7601, + "step": 10272 + }, + { + "epoch": 0.9198500195869942, + "grad_norm": 0.9697593878880849, + "learning_rate": 3.3501063762789167e-07, + "loss": 0.8295, + "step": 10273 + }, + { + "epoch": 0.9199395601320723, + "grad_norm": 1.1223603139606662, + "learning_rate": 3.342666252541149e-07, + "loss": 0.8063, + "step": 10274 + }, + { + "epoch": 0.9200291006771504, + "grad_norm": 0.9491278929281788, + "learning_rate": 3.335234259303299e-07, + "loss": 0.7802, + "step": 10275 + }, + { + "epoch": 0.9201186412222284, + "grad_norm": 1.169816092425431, + "learning_rate": 3.3278103971905787e-07, + "loss": 0.8143, + "step": 10276 + }, + { + "epoch": 0.9202081817673065, + "grad_norm": 1.160915738208693, + "learning_rate": 3.320394666827398e-07, + "loss": 0.8234, + "step": 10277 + }, + { + "epoch": 0.9202977223123846, + "grad_norm": 0.9200495827881482, + "learning_rate": 3.31298706883757e-07, + "loss": 0.786, + "step": 10278 + }, + { + "epoch": 0.9203872628574626, + "grad_norm": 1.0247845313753299, + "learning_rate": 3.3055876038441957e-07, + "loss": 0.7649, + "step": 10279 + }, + { + "epoch": 0.9204768034025407, + "grad_norm": 0.9226900042092755, + "learning_rate": 3.298196272469689e-07, + "loss": 0.7964, + "step": 10280 + }, + { + "epoch": 0.9205663439476188, + "grad_norm": 1.037153589774467, + "learning_rate": 3.290813075335797e-07, + "loss": 0.8249, + "step": 10281 + }, + { + "epoch": 0.9206558844926969, + "grad_norm": 1.0114486902126962, + "learning_rate": 3.283438013063567e-07, + "loss": 0.7942, + "step": 10282 + }, + { + "epoch": 0.9207454250377749, + "grad_norm": 0.9007216029574396, + "learning_rate": 3.276071086273347e-07, + "loss": 0.8047, + "step": 10283 + }, + { + "epoch": 0.9208349655828529, + "grad_norm": 0.944909183193198, + "learning_rate": 3.2687122955848416e-07, + "loss": 0.8241, + "step": 10284 + }, + { + "epoch": 0.9209245061279311, + "grad_norm": 0.9951093603143992, + "learning_rate": 3.2613616416170334e-07, + "loss": 0.761, + "step": 10285 + }, + { + "epoch": 0.9210140466730091, + "grad_norm": 0.9956023000366161, + "learning_rate": 3.25401912498825e-07, + "loss": 0.7973, + "step": 10286 + }, + { + "epoch": 0.9211035872180872, + "grad_norm": 1.1392744362956087, + "learning_rate": 3.246684746316109e-07, + "loss": 0.7902, + "step": 10287 + }, + { + "epoch": 0.9211931277631653, + "grad_norm": 1.059350103027795, + "learning_rate": 3.239358506217549e-07, + "loss": 0.8146, + "step": 10288 + }, + { + "epoch": 0.9212826683082433, + "grad_norm": 0.9903693958007836, + "learning_rate": 3.232040405308845e-07, + "loss": 0.7529, + "step": 10289 + }, + { + "epoch": 0.9213722088533214, + "grad_norm": 0.9631068734171713, + "learning_rate": 3.224730444205559e-07, + "loss": 0.8133, + "step": 10290 + }, + { + "epoch": 0.9214617493983994, + "grad_norm": 0.9861696943105579, + "learning_rate": 3.2174286235225895e-07, + "loss": 0.8438, + "step": 10291 + }, + { + "epoch": 0.9215512899434776, + "grad_norm": 1.1105409002779312, + "learning_rate": 3.2101349438741324e-07, + "loss": 0.8627, + "step": 10292 + }, + { + "epoch": 0.9216408304885556, + "grad_norm": 0.9394942590410027, + "learning_rate": 3.20284940587372e-07, + "loss": 0.8236, + "step": 10293 + }, + { + "epoch": 0.9217303710336336, + "grad_norm": 1.0301808724016983, + "learning_rate": 3.195572010134185e-07, + "loss": 0.7757, + "step": 10294 + }, + { + "epoch": 0.9218199115787117, + "grad_norm": 0.9860910615224818, + "learning_rate": 3.1883027572676697e-07, + "loss": 0.8276, + "step": 10295 + }, + { + "epoch": 0.9219094521237898, + "grad_norm": 0.9416708530185449, + "learning_rate": 3.181041647885641e-07, + "loss": 0.7481, + "step": 10296 + }, + { + "epoch": 0.9219989926688679, + "grad_norm": 0.8926805369350793, + "learning_rate": 3.1737886825988995e-07, + "loss": 0.7517, + "step": 10297 + }, + { + "epoch": 0.9220885332139459, + "grad_norm": 0.8924847220579502, + "learning_rate": 3.166543862017513e-07, + "loss": 0.7453, + "step": 10298 + }, + { + "epoch": 0.922178073759024, + "grad_norm": 1.0101931714195473, + "learning_rate": 3.159307186750915e-07, + "loss": 0.791, + "step": 10299 + }, + { + "epoch": 0.9222676143041021, + "grad_norm": 1.030110910704043, + "learning_rate": 3.152078657407809e-07, + "loss": 0.7684, + "step": 10300 + }, + { + "epoch": 0.9223571548491801, + "grad_norm": 0.944199747066465, + "learning_rate": 3.144858274596263e-07, + "loss": 0.8038, + "step": 10301 + }, + { + "epoch": 0.9224466953942582, + "grad_norm": 0.9859854548067637, + "learning_rate": 3.137646038923603e-07, + "loss": 0.8124, + "step": 10302 + }, + { + "epoch": 0.9225362359393363, + "grad_norm": 1.0820241874930916, + "learning_rate": 3.1304419509965324e-07, + "loss": 0.7333, + "step": 10303 + }, + { + "epoch": 0.9226257764844144, + "grad_norm": 0.9875040169485647, + "learning_rate": 3.1232460114209994e-07, + "loss": 0.8067, + "step": 10304 + }, + { + "epoch": 0.9227153170294924, + "grad_norm": 1.059337545399125, + "learning_rate": 3.116058220802309e-07, + "loss": 0.7892, + "step": 10305 + }, + { + "epoch": 0.9228048575745705, + "grad_norm": 1.1345716548424762, + "learning_rate": 3.1088785797451004e-07, + "loss": 0.77, + "step": 10306 + }, + { + "epoch": 0.9228943981196486, + "grad_norm": 0.9082387943931942, + "learning_rate": 3.1017070888532895e-07, + "loss": 0.7913, + "step": 10307 + }, + { + "epoch": 0.9229839386647266, + "grad_norm": 1.0800572438110203, + "learning_rate": 3.0945437487301054e-07, + "loss": 0.8557, + "step": 10308 + }, + { + "epoch": 0.9230734792098046, + "grad_norm": 0.9727558260436585, + "learning_rate": 3.0873885599781326e-07, + "loss": 0.8255, + "step": 10309 + }, + { + "epoch": 0.9231630197548828, + "grad_norm": 1.122570728119037, + "learning_rate": 3.080241523199212e-07, + "loss": 0.7331, + "step": 10310 + }, + { + "epoch": 0.9232525602999608, + "grad_norm": 0.9674791684600307, + "learning_rate": 3.07310263899453e-07, + "loss": 0.8036, + "step": 10311 + }, + { + "epoch": 0.9233421008450389, + "grad_norm": 0.9632815091071751, + "learning_rate": 3.0659719079646045e-07, + "loss": 0.7544, + "step": 10312 + }, + { + "epoch": 0.9234316413901169, + "grad_norm": 0.9610519144862579, + "learning_rate": 3.058849330709246e-07, + "loss": 0.8489, + "step": 10313 + }, + { + "epoch": 0.9235211819351951, + "grad_norm": 0.9901522043304055, + "learning_rate": 3.051734907827586e-07, + "loss": 0.7595, + "step": 10314 + }, + { + "epoch": 0.9236107224802731, + "grad_norm": 1.2710529545449645, + "learning_rate": 3.0446286399180567e-07, + "loss": 0.8001, + "step": 10315 + }, + { + "epoch": 0.9237002630253511, + "grad_norm": 0.9065470831554353, + "learning_rate": 3.037530527578414e-07, + "loss": 0.7901, + "step": 10316 + }, + { + "epoch": 0.9237898035704293, + "grad_norm": 0.9823717561159129, + "learning_rate": 3.030440571405724e-07, + "loss": 0.8213, + "step": 10317 + }, + { + "epoch": 0.9238793441155073, + "grad_norm": 0.9493127558503596, + "learning_rate": 3.0233587719963875e-07, + "loss": 0.8097, + "step": 10318 + }, + { + "epoch": 0.9239688846605854, + "grad_norm": 0.9483944054844584, + "learning_rate": 3.0162851299460836e-07, + "loss": 0.7701, + "step": 10319 + }, + { + "epoch": 0.9240584252056634, + "grad_norm": 0.9532077109712128, + "learning_rate": 3.009219645849859e-07, + "loss": 0.8277, + "step": 10320 + }, + { + "epoch": 0.9241479657507415, + "grad_norm": 1.1378269722144438, + "learning_rate": 3.0021623203019933e-07, + "loss": 0.7869, + "step": 10321 + }, + { + "epoch": 0.9242375062958196, + "grad_norm": 0.9190880425942959, + "learning_rate": 2.9951131538961453e-07, + "loss": 0.7729, + "step": 10322 + }, + { + "epoch": 0.9243270468408976, + "grad_norm": 0.9922502567049982, + "learning_rate": 2.9880721472252627e-07, + "loss": 0.8062, + "step": 10323 + }, + { + "epoch": 0.9244165873859758, + "grad_norm": 0.9252633115390057, + "learning_rate": 2.9810393008816275e-07, + "loss": 0.7611, + "step": 10324 + }, + { + "epoch": 0.9245061279310538, + "grad_norm": 0.9539961758438952, + "learning_rate": 2.974014615456822e-07, + "loss": 0.777, + "step": 10325 + }, + { + "epoch": 0.9245956684761318, + "grad_norm": 0.9429084171187704, + "learning_rate": 2.9669980915417175e-07, + "loss": 0.7313, + "step": 10326 + }, + { + "epoch": 0.9246852090212099, + "grad_norm": 1.0522027215298702, + "learning_rate": 2.959989729726531e-07, + "loss": 0.7939, + "step": 10327 + }, + { + "epoch": 0.924774749566288, + "grad_norm": 1.0881795568192887, + "learning_rate": 2.9529895306007805e-07, + "loss": 0.8458, + "step": 10328 + }, + { + "epoch": 0.9248642901113661, + "grad_norm": 0.9690530505580998, + "learning_rate": 2.945997494753294e-07, + "loss": 0.8775, + "step": 10329 + }, + { + "epoch": 0.9249538306564441, + "grad_norm": 0.909305688869949, + "learning_rate": 2.9390136227722464e-07, + "loss": 0.7908, + "step": 10330 + }, + { + "epoch": 0.9250433712015221, + "grad_norm": 1.0150985933068009, + "learning_rate": 2.9320379152450783e-07, + "loss": 0.8191, + "step": 10331 + }, + { + "epoch": 0.9251329117466003, + "grad_norm": 0.9587437953238741, + "learning_rate": 2.925070372758565e-07, + "loss": 0.7941, + "step": 10332 + }, + { + "epoch": 0.9252224522916783, + "grad_norm": 1.120583201473498, + "learning_rate": 2.9181109958987817e-07, + "loss": 0.7995, + "step": 10333 + }, + { + "epoch": 0.9253119928367564, + "grad_norm": 0.8789668274939847, + "learning_rate": 2.9111597852511495e-07, + "loss": 0.7506, + "step": 10334 + }, + { + "epoch": 0.9254015333818345, + "grad_norm": 1.0986920550165604, + "learning_rate": 2.9042167414003674e-07, + "loss": 0.7957, + "step": 10335 + }, + { + "epoch": 0.9254910739269125, + "grad_norm": 1.1090794969060618, + "learning_rate": 2.897281864930468e-07, + "loss": 0.8128, + "step": 10336 + }, + { + "epoch": 0.9255806144719906, + "grad_norm": 1.1587259788149673, + "learning_rate": 2.8903551564247956e-07, + "loss": 0.8103, + "step": 10337 + }, + { + "epoch": 0.9256701550170686, + "grad_norm": 1.0380396401821168, + "learning_rate": 2.883436616465984e-07, + "loss": 0.7883, + "step": 10338 + }, + { + "epoch": 0.9257596955621468, + "grad_norm": 0.9692384434054838, + "learning_rate": 2.876526245636013e-07, + "loss": 0.766, + "step": 10339 + }, + { + "epoch": 0.9258492361072248, + "grad_norm": 1.0648099914291804, + "learning_rate": 2.8696240445161617e-07, + "loss": 0.8155, + "step": 10340 + }, + { + "epoch": 0.9259387766523028, + "grad_norm": 0.9918486308179162, + "learning_rate": 2.862730013687021e-07, + "loss": 0.7431, + "step": 10341 + }, + { + "epoch": 0.926028317197381, + "grad_norm": 1.059412567669058, + "learning_rate": 2.855844153728482e-07, + "loss": 0.8154, + "step": 10342 + }, + { + "epoch": 0.926117857742459, + "grad_norm": 1.0525522720107576, + "learning_rate": 2.8489664652197714e-07, + "loss": 0.8666, + "step": 10343 + }, + { + "epoch": 0.9262073982875371, + "grad_norm": 1.012495694735497, + "learning_rate": 2.8420969487394147e-07, + "loss": 0.7846, + "step": 10344 + }, + { + "epoch": 0.9262969388326151, + "grad_norm": 0.976706633798738, + "learning_rate": 2.835235604865261e-07, + "loss": 0.7858, + "step": 10345 + }, + { + "epoch": 0.9263864793776933, + "grad_norm": 0.9018973504000815, + "learning_rate": 2.828382434174448e-07, + "loss": 0.7854, + "step": 10346 + }, + { + "epoch": 0.9264760199227713, + "grad_norm": 0.970085026579723, + "learning_rate": 2.821537437243449e-07, + "loss": 0.794, + "step": 10347 + }, + { + "epoch": 0.9265655604678493, + "grad_norm": 1.0037054561559644, + "learning_rate": 2.8147006146480584e-07, + "loss": 0.8138, + "step": 10348 + }, + { + "epoch": 0.9266551010129274, + "grad_norm": 0.8810066634005758, + "learning_rate": 2.8078719669633383e-07, + "loss": 0.7904, + "step": 10349 + }, + { + "epoch": 0.9267446415580055, + "grad_norm": 1.0135292821936814, + "learning_rate": 2.8010514947637177e-07, + "loss": 0.8122, + "step": 10350 + }, + { + "epoch": 0.9268341821030835, + "grad_norm": 0.9306043484605416, + "learning_rate": 2.794239198622906e-07, + "loss": 0.7808, + "step": 10351 + }, + { + "epoch": 0.9269237226481616, + "grad_norm": 1.0871645898060174, + "learning_rate": 2.7874350791139203e-07, + "loss": 0.8072, + "step": 10352 + }, + { + "epoch": 0.9270132631932397, + "grad_norm": 1.126376367334948, + "learning_rate": 2.7806391368091046e-07, + "loss": 0.7444, + "step": 10353 + }, + { + "epoch": 0.9271028037383178, + "grad_norm": 1.058420830710669, + "learning_rate": 2.773851372280123e-07, + "loss": 0.7458, + "step": 10354 + }, + { + "epoch": 0.9271923442833958, + "grad_norm": 1.0891769264821776, + "learning_rate": 2.76707178609793e-07, + "loss": 0.7713, + "step": 10355 + }, + { + "epoch": 0.9272818848284738, + "grad_norm": 0.9484715847668866, + "learning_rate": 2.760300378832803e-07, + "loss": 0.7573, + "step": 10356 + }, + { + "epoch": 0.927371425373552, + "grad_norm": 0.9158990676619223, + "learning_rate": 2.753537151054342e-07, + "loss": 0.8169, + "step": 10357 + }, + { + "epoch": 0.92746096591863, + "grad_norm": 0.9800790731279037, + "learning_rate": 2.7467821033314466e-07, + "loss": 0.7589, + "step": 10358 + }, + { + "epoch": 0.9275505064637081, + "grad_norm": 0.995090075901634, + "learning_rate": 2.740035236232297e-07, + "loss": 0.7251, + "step": 10359 + }, + { + "epoch": 0.9276400470087862, + "grad_norm": 0.9738402382800051, + "learning_rate": 2.733296550324449e-07, + "loss": 0.7655, + "step": 10360 + }, + { + "epoch": 0.9277295875538643, + "grad_norm": 1.1565707429976642, + "learning_rate": 2.726566046174739e-07, + "loss": 0.7754, + "step": 10361 + }, + { + "epoch": 0.9278191280989423, + "grad_norm": 0.8982566934106699, + "learning_rate": 2.7198437243493025e-07, + "loss": 0.7621, + "step": 10362 + }, + { + "epoch": 0.9279086686440203, + "grad_norm": 1.0640298414119185, + "learning_rate": 2.71312958541361e-07, + "loss": 0.8194, + "step": 10363 + }, + { + "epoch": 0.9279982091890985, + "grad_norm": 0.9072130316880089, + "learning_rate": 2.706423629932431e-07, + "loss": 0.7721, + "step": 10364 + }, + { + "epoch": 0.9280877497341765, + "grad_norm": 0.9423744965404699, + "learning_rate": 2.699725858469826e-07, + "loss": 0.8501, + "step": 10365 + }, + { + "epoch": 0.9281772902792546, + "grad_norm": 1.1217944256901895, + "learning_rate": 2.693036271589222e-07, + "loss": 0.8126, + "step": 10366 + }, + { + "epoch": 0.9282668308243326, + "grad_norm": 0.9436714953809203, + "learning_rate": 2.686354869853303e-07, + "loss": 0.7585, + "step": 10367 + }, + { + "epoch": 0.9283563713694107, + "grad_norm": 1.039714796580645, + "learning_rate": 2.6796816538241065e-07, + "loss": 0.857, + "step": 10368 + }, + { + "epoch": 0.9284459119144888, + "grad_norm": 1.014289499471726, + "learning_rate": 2.673016624062963e-07, + "loss": 0.8392, + "step": 10369 + }, + { + "epoch": 0.9285354524595668, + "grad_norm": 0.9231815213737606, + "learning_rate": 2.6663597811304897e-07, + "loss": 0.7816, + "step": 10370 + }, + { + "epoch": 0.928624993004645, + "grad_norm": 0.9471998627660329, + "learning_rate": 2.659711125586628e-07, + "loss": 0.7977, + "step": 10371 + }, + { + "epoch": 0.928714533549723, + "grad_norm": 0.896761752933092, + "learning_rate": 2.6530706579906863e-07, + "loss": 0.7985, + "step": 10372 + }, + { + "epoch": 0.928804074094801, + "grad_norm": 0.9602115457422237, + "learning_rate": 2.646438378901217e-07, + "loss": 0.7916, + "step": 10373 + }, + { + "epoch": 0.9288936146398791, + "grad_norm": 0.9579676116823409, + "learning_rate": 2.639814288876108e-07, + "loss": 0.8112, + "step": 10374 + }, + { + "epoch": 0.9289831551849572, + "grad_norm": 0.9668924661263862, + "learning_rate": 2.6331983884725466e-07, + "loss": 0.8005, + "step": 10375 + }, + { + "epoch": 0.9290726957300353, + "grad_norm": 0.9538131929728025, + "learning_rate": 2.626590678247043e-07, + "loss": 0.8422, + "step": 10376 + }, + { + "epoch": 0.9291622362751133, + "grad_norm": 1.0596792609344523, + "learning_rate": 2.6199911587554197e-07, + "loss": 0.7663, + "step": 10377 + }, + { + "epoch": 0.9292517768201914, + "grad_norm": 0.9471124023156818, + "learning_rate": 2.6133998305528094e-07, + "loss": 0.7525, + "step": 10378 + }, + { + "epoch": 0.9293413173652695, + "grad_norm": 0.9745855380654572, + "learning_rate": 2.606816694193648e-07, + "loss": 0.7865, + "step": 10379 + }, + { + "epoch": 0.9294308579103475, + "grad_norm": 1.0311893063596922, + "learning_rate": 2.6002417502317024e-07, + "loss": 0.7812, + "step": 10380 + }, + { + "epoch": 0.9295203984554256, + "grad_norm": 0.9572733969795126, + "learning_rate": 2.5936749992200193e-07, + "loss": 0.7657, + "step": 10381 + }, + { + "epoch": 0.9296099390005037, + "grad_norm": 1.2680803777364593, + "learning_rate": 2.5871164417109796e-07, + "loss": 0.8401, + "step": 10382 + }, + { + "epoch": 0.9296994795455817, + "grad_norm": 1.030995776714883, + "learning_rate": 2.5805660782562524e-07, + "loss": 0.7937, + "step": 10383 + }, + { + "epoch": 0.9297890200906598, + "grad_norm": 0.9855559696009664, + "learning_rate": 2.574023909406853e-07, + "loss": 0.7523, + "step": 10384 + }, + { + "epoch": 0.9298785606357378, + "grad_norm": 1.0349853667210318, + "learning_rate": 2.5674899357130855e-07, + "loss": 0.8233, + "step": 10385 + }, + { + "epoch": 0.929968101180816, + "grad_norm": 0.9069962726098078, + "learning_rate": 2.560964157724555e-07, + "loss": 0.8279, + "step": 10386 + }, + { + "epoch": 0.930057641725894, + "grad_norm": 0.9962518001381842, + "learning_rate": 2.554446575990199e-07, + "loss": 0.8293, + "step": 10387 + }, + { + "epoch": 0.930147182270972, + "grad_norm": 1.045553853091121, + "learning_rate": 2.547937191058247e-07, + "loss": 0.7602, + "step": 10388 + }, + { + "epoch": 0.9302367228160502, + "grad_norm": 1.0831403246692417, + "learning_rate": 2.54143600347625e-07, + "loss": 0.8274, + "step": 10389 + }, + { + "epoch": 0.9303262633611282, + "grad_norm": 0.9766537188611281, + "learning_rate": 2.534943013791069e-07, + "loss": 0.8449, + "step": 10390 + }, + { + "epoch": 0.9304158039062063, + "grad_norm": 0.9600251548628375, + "learning_rate": 2.5284582225488685e-07, + "loss": 0.7819, + "step": 10391 + }, + { + "epoch": 0.9305053444512843, + "grad_norm": 1.007578000811047, + "learning_rate": 2.521981630295134e-07, + "loss": 0.8106, + "step": 10392 + }, + { + "epoch": 0.9305948849963624, + "grad_norm": 1.0009351910819597, + "learning_rate": 2.515513237574663e-07, + "loss": 0.8332, + "step": 10393 + }, + { + "epoch": 0.9306844255414405, + "grad_norm": 1.8080047228168352, + "learning_rate": 2.509053044931531e-07, + "loss": 0.7763, + "step": 10394 + }, + { + "epoch": 0.9307739660865185, + "grad_norm": 0.9762181347922312, + "learning_rate": 2.5026010529091704e-07, + "loss": 0.8537, + "step": 10395 + }, + { + "epoch": 0.9308635066315967, + "grad_norm": 0.9663398719882882, + "learning_rate": 2.496157262050292e-07, + "loss": 0.7595, + "step": 10396 + }, + { + "epoch": 0.9309530471766747, + "grad_norm": 1.037134227478139, + "learning_rate": 2.4897216728969274e-07, + "loss": 0.8423, + "step": 10397 + }, + { + "epoch": 0.9310425877217527, + "grad_norm": 0.9161485366988351, + "learning_rate": 2.4832942859904117e-07, + "loss": 0.7623, + "step": 10398 + }, + { + "epoch": 0.9311321282668308, + "grad_norm": 1.0167785297189118, + "learning_rate": 2.476875101871412e-07, + "loss": 0.8529, + "step": 10399 + }, + { + "epoch": 0.9312216688119089, + "grad_norm": 0.9052264599008792, + "learning_rate": 2.4704641210798853e-07, + "loss": 0.7476, + "step": 10400 + }, + { + "epoch": 0.931311209356987, + "grad_norm": 1.050125075135331, + "learning_rate": 2.464061344155089e-07, + "loss": 0.8333, + "step": 10401 + }, + { + "epoch": 0.931400749902065, + "grad_norm": 0.930114328107802, + "learning_rate": 2.457666771635614e-07, + "loss": 0.7778, + "step": 10402 + }, + { + "epoch": 0.931490290447143, + "grad_norm": 1.0013715082926637, + "learning_rate": 2.451280404059342e-07, + "loss": 0.7943, + "step": 10403 + }, + { + "epoch": 0.9315798309922212, + "grad_norm": 0.9509729367125315, + "learning_rate": 2.444902241963487e-07, + "loss": 0.8126, + "step": 10404 + }, + { + "epoch": 0.9316693715372992, + "grad_norm": 0.9345979818784474, + "learning_rate": 2.438532285884543e-07, + "loss": 0.809, + "step": 10405 + }, + { + "epoch": 0.9317589120823773, + "grad_norm": 0.9593798201420923, + "learning_rate": 2.432170536358347e-07, + "loss": 0.8004, + "step": 10406 + }, + { + "epoch": 0.9318484526274554, + "grad_norm": 0.99697336642487, + "learning_rate": 2.4258169939200273e-07, + "loss": 0.8014, + "step": 10407 + }, + { + "epoch": 0.9319379931725335, + "grad_norm": 0.9785393144245268, + "learning_rate": 2.419471659104e-07, + "loss": 0.8055, + "step": 10408 + }, + { + "epoch": 0.9320275337176115, + "grad_norm": 1.028171431211335, + "learning_rate": 2.41313453244405e-07, + "loss": 0.786, + "step": 10409 + }, + { + "epoch": 0.9321170742626895, + "grad_norm": 1.010397680456655, + "learning_rate": 2.4068056144732067e-07, + "loss": 0.8505, + "step": 10410 + }, + { + "epoch": 0.9322066148077677, + "grad_norm": 0.9955135110873424, + "learning_rate": 2.400484905723843e-07, + "loss": 0.7747, + "step": 10411 + }, + { + "epoch": 0.9322961553528457, + "grad_norm": 1.0221097185289496, + "learning_rate": 2.394172406727657e-07, + "loss": 0.8103, + "step": 10412 + }, + { + "epoch": 0.9323856958979237, + "grad_norm": 1.0171951546289935, + "learning_rate": 2.3878681180156015e-07, + "loss": 0.7928, + "step": 10413 + }, + { + "epoch": 0.9324752364430019, + "grad_norm": 1.0998398088031849, + "learning_rate": 2.3815720401179965e-07, + "loss": 0.7884, + "step": 10414 + }, + { + "epoch": 0.9325647769880799, + "grad_norm": 0.8733095362659594, + "learning_rate": 2.3752841735644405e-07, + "loss": 0.7318, + "step": 10415 + }, + { + "epoch": 0.932654317533158, + "grad_norm": 1.0088865572526513, + "learning_rate": 2.369004518883855e-07, + "loss": 0.8084, + "step": 10416 + }, + { + "epoch": 0.932743858078236, + "grad_norm": 0.9864535188476026, + "learning_rate": 2.362733076604451e-07, + "loss": 0.7797, + "step": 10417 + }, + { + "epoch": 0.9328333986233142, + "grad_norm": 0.9482907388659072, + "learning_rate": 2.3564698472537838e-07, + "loss": 0.8122, + "step": 10418 + }, + { + "epoch": 0.9329229391683922, + "grad_norm": 1.0061781130828806, + "learning_rate": 2.350214831358666e-07, + "loss": 0.7581, + "step": 10419 + }, + { + "epoch": 0.9330124797134702, + "grad_norm": 1.2253064826067683, + "learning_rate": 2.343968029445276e-07, + "loss": 0.7633, + "step": 10420 + }, + { + "epoch": 0.9331020202585483, + "grad_norm": 0.9833587246362245, + "learning_rate": 2.3377294420390494e-07, + "loss": 0.7206, + "step": 10421 + }, + { + "epoch": 0.9331915608036264, + "grad_norm": 0.9290378360302113, + "learning_rate": 2.3314990696647888e-07, + "loss": 0.7992, + "step": 10422 + }, + { + "epoch": 0.9332811013487045, + "grad_norm": 0.8893130120937318, + "learning_rate": 2.3252769128465524e-07, + "loss": 0.7661, + "step": 10423 + }, + { + "epoch": 0.9333706418937825, + "grad_norm": 1.0420498809111451, + "learning_rate": 2.319062972107722e-07, + "loss": 0.8284, + "step": 10424 + }, + { + "epoch": 0.9334601824388606, + "grad_norm": 1.1484917327750357, + "learning_rate": 2.3128572479709898e-07, + "loss": 0.796, + "step": 10425 + }, + { + "epoch": 0.9335497229839387, + "grad_norm": 1.0013306662768982, + "learning_rate": 2.3066597409583836e-07, + "loss": 0.8265, + "step": 10426 + }, + { + "epoch": 0.9336392635290167, + "grad_norm": 0.9208649945924663, + "learning_rate": 2.300470451591197e-07, + "loss": 0.8429, + "step": 10427 + }, + { + "epoch": 0.9337288040740948, + "grad_norm": 0.9834931805118609, + "learning_rate": 2.29428938039008e-07, + "loss": 0.7619, + "step": 10428 + }, + { + "epoch": 0.9338183446191729, + "grad_norm": 1.0542958281207289, + "learning_rate": 2.2881165278749395e-07, + "loss": 0.8299, + "step": 10429 + }, + { + "epoch": 0.9339078851642509, + "grad_norm": 0.9784948682955003, + "learning_rate": 2.2819518945650265e-07, + "loss": 0.7543, + "step": 10430 + }, + { + "epoch": 0.933997425709329, + "grad_norm": 0.9222639783693087, + "learning_rate": 2.2757954809788708e-07, + "loss": 0.8038, + "step": 10431 + }, + { + "epoch": 0.9340869662544071, + "grad_norm": 0.9693582647389698, + "learning_rate": 2.2696472876343467e-07, + "loss": 0.8179, + "step": 10432 + }, + { + "epoch": 0.9341765067994852, + "grad_norm": 1.0020495750456926, + "learning_rate": 2.2635073150486297e-07, + "loss": 0.7546, + "step": 10433 + }, + { + "epoch": 0.9342660473445632, + "grad_norm": 0.9935241366593474, + "learning_rate": 2.2573755637381844e-07, + "loss": 0.8453, + "step": 10434 + }, + { + "epoch": 0.9343555878896412, + "grad_norm": 0.9632003375841415, + "learning_rate": 2.251252034218787e-07, + "loss": 0.8288, + "step": 10435 + }, + { + "epoch": 0.9344451284347194, + "grad_norm": 1.0186367505331855, + "learning_rate": 2.2451367270055368e-07, + "loss": 0.7858, + "step": 10436 + }, + { + "epoch": 0.9345346689797974, + "grad_norm": 1.0128222554324635, + "learning_rate": 2.239029642612822e-07, + "loss": 0.8095, + "step": 10437 + }, + { + "epoch": 0.9346242095248755, + "grad_norm": 1.0641396031550858, + "learning_rate": 2.2329307815543656e-07, + "loss": 0.784, + "step": 10438 + }, + { + "epoch": 0.9347137500699535, + "grad_norm": 1.0232975166969698, + "learning_rate": 2.2268401443431787e-07, + "loss": 0.8325, + "step": 10439 + }, + { + "epoch": 0.9348032906150316, + "grad_norm": 0.9366500324068437, + "learning_rate": 2.220757731491585e-07, + "loss": 0.8368, + "step": 10440 + }, + { + "epoch": 0.9348928311601097, + "grad_norm": 1.0107139582661775, + "learning_rate": 2.2146835435112202e-07, + "loss": 0.7973, + "step": 10441 + }, + { + "epoch": 0.9349823717051877, + "grad_norm": 0.9500843459456265, + "learning_rate": 2.2086175809130195e-07, + "loss": 0.7387, + "step": 10442 + }, + { + "epoch": 0.9350719122502659, + "grad_norm": 1.0255843173409078, + "learning_rate": 2.2025598442072304e-07, + "loss": 0.7849, + "step": 10443 + }, + { + "epoch": 0.9351614527953439, + "grad_norm": 0.9332186133563786, + "learning_rate": 2.196510333903412e-07, + "loss": 0.8313, + "step": 10444 + }, + { + "epoch": 0.9352509933404219, + "grad_norm": 1.0885072414475259, + "learning_rate": 2.1904690505104466e-07, + "loss": 0.7944, + "step": 10445 + }, + { + "epoch": 0.9353405338855, + "grad_norm": 1.0428802716226617, + "learning_rate": 2.1844359945364824e-07, + "loss": 0.7758, + "step": 10446 + }, + { + "epoch": 0.9354300744305781, + "grad_norm": 1.1410478269059265, + "learning_rate": 2.178411166489014e-07, + "loss": 0.8481, + "step": 10447 + }, + { + "epoch": 0.9355196149756562, + "grad_norm": 0.9136794874718338, + "learning_rate": 2.1723945668748248e-07, + "loss": 0.7544, + "step": 10448 + }, + { + "epoch": 0.9356091555207342, + "grad_norm": 0.9040025365359545, + "learning_rate": 2.16638619620001e-07, + "loss": 0.7958, + "step": 10449 + }, + { + "epoch": 0.9356986960658124, + "grad_norm": 1.038759869576706, + "learning_rate": 2.1603860549699763e-07, + "loss": 0.7916, + "step": 10450 + }, + { + "epoch": 0.9357882366108904, + "grad_norm": 1.036919434584511, + "learning_rate": 2.1543941436894534e-07, + "loss": 0.8351, + "step": 10451 + }, + { + "epoch": 0.9358777771559684, + "grad_norm": 0.962887606867669, + "learning_rate": 2.1484104628624268e-07, + "loss": 0.7997, + "step": 10452 + }, + { + "epoch": 0.9359673177010465, + "grad_norm": 0.9400624084996615, + "learning_rate": 2.14243501299225e-07, + "loss": 0.8222, + "step": 10453 + }, + { + "epoch": 0.9360568582461246, + "grad_norm": 0.9504122725053432, + "learning_rate": 2.1364677945815538e-07, + "loss": 0.7356, + "step": 10454 + }, + { + "epoch": 0.9361463987912026, + "grad_norm": 0.9413958258616596, + "learning_rate": 2.13050880813227e-07, + "loss": 0.7469, + "step": 10455 + }, + { + "epoch": 0.9362359393362807, + "grad_norm": 1.0792866056927848, + "learning_rate": 2.1245580541456645e-07, + "loss": 0.8069, + "step": 10456 + }, + { + "epoch": 0.9363254798813587, + "grad_norm": 1.02385093299912, + "learning_rate": 2.1186155331222925e-07, + "loss": 0.7427, + "step": 10457 + }, + { + "epoch": 0.9364150204264369, + "grad_norm": 0.9970507994924301, + "learning_rate": 2.1126812455620094e-07, + "loss": 0.7801, + "step": 10458 + }, + { + "epoch": 0.9365045609715149, + "grad_norm": 0.949199296158414, + "learning_rate": 2.106755191963994e-07, + "loss": 0.8132, + "step": 10459 + }, + { + "epoch": 0.936594101516593, + "grad_norm": 0.9494750461259707, + "learning_rate": 2.100837372826725e-07, + "loss": 0.8062, + "step": 10460 + }, + { + "epoch": 0.9366836420616711, + "grad_norm": 1.0188024357883734, + "learning_rate": 2.0949277886479935e-07, + "loss": 0.7645, + "step": 10461 + }, + { + "epoch": 0.9367731826067491, + "grad_norm": 0.9718496989019507, + "learning_rate": 2.0890264399248905e-07, + "loss": 0.7946, + "step": 10462 + }, + { + "epoch": 0.9368627231518272, + "grad_norm": 0.9347843431944246, + "learning_rate": 2.083133327153819e-07, + "loss": 0.7864, + "step": 10463 + }, + { + "epoch": 0.9369522636969052, + "grad_norm": 1.1337913709690801, + "learning_rate": 2.0772484508304937e-07, + "loss": 0.7678, + "step": 10464 + }, + { + "epoch": 0.9370418042419834, + "grad_norm": 0.9797317131732842, + "learning_rate": 2.0713718114499293e-07, + "loss": 0.8076, + "step": 10465 + }, + { + "epoch": 0.9371313447870614, + "grad_norm": 0.917629630970039, + "learning_rate": 2.065503409506453e-07, + "loss": 0.8375, + "step": 10466 + }, + { + "epoch": 0.9372208853321394, + "grad_norm": 0.9186325146478544, + "learning_rate": 2.059643245493681e-07, + "loss": 0.745, + "step": 10467 + }, + { + "epoch": 0.9373104258772176, + "grad_norm": 1.0885336496063627, + "learning_rate": 2.0537913199045633e-07, + "loss": 0.8239, + "step": 10468 + }, + { + "epoch": 0.9373999664222956, + "grad_norm": 0.9097677422967195, + "learning_rate": 2.0479476332313398e-07, + "loss": 0.8174, + "step": 10469 + }, + { + "epoch": 0.9374895069673737, + "grad_norm": 0.9072592642426942, + "learning_rate": 2.0421121859655723e-07, + "loss": 0.8063, + "step": 10470 + }, + { + "epoch": 0.9375790475124517, + "grad_norm": 1.0102842139427806, + "learning_rate": 2.036284978598102e-07, + "loss": 0.7682, + "step": 10471 + }, + { + "epoch": 0.9376685880575298, + "grad_norm": 1.1211751436145219, + "learning_rate": 2.0304660116191145e-07, + "loss": 0.781, + "step": 10472 + }, + { + "epoch": 0.9377581286026079, + "grad_norm": 1.0157958911437328, + "learning_rate": 2.0246552855180625e-07, + "loss": 0.8311, + "step": 10473 + }, + { + "epoch": 0.9378476691476859, + "grad_norm": 0.9507851809664931, + "learning_rate": 2.0188528007837328e-07, + "loss": 0.834, + "step": 10474 + }, + { + "epoch": 0.937937209692764, + "grad_norm": 1.0379071841054388, + "learning_rate": 2.013058557904224e-07, + "loss": 0.8404, + "step": 10475 + }, + { + "epoch": 0.9380267502378421, + "grad_norm": 1.0170820987516789, + "learning_rate": 2.0072725573669128e-07, + "loss": 0.798, + "step": 10476 + }, + { + "epoch": 0.9381162907829201, + "grad_norm": 1.075043281581752, + "learning_rate": 2.00149479965851e-07, + "loss": 0.8131, + "step": 10477 + }, + { + "epoch": 0.9382058313279982, + "grad_norm": 1.0946551493812278, + "learning_rate": 1.9957252852650267e-07, + "loss": 0.7644, + "step": 10478 + }, + { + "epoch": 0.9382953718730763, + "grad_norm": 1.0513174801381848, + "learning_rate": 1.9899640146717413e-07, + "loss": 0.7836, + "step": 10479 + }, + { + "epoch": 0.9383849124181544, + "grad_norm": 0.9709426708148006, + "learning_rate": 1.984210988363311e-07, + "loss": 0.7197, + "step": 10480 + }, + { + "epoch": 0.9384744529632324, + "grad_norm": 0.9800868760815739, + "learning_rate": 1.9784662068236483e-07, + "loss": 0.8066, + "step": 10481 + }, + { + "epoch": 0.9385639935083104, + "grad_norm": 0.9780341942172683, + "learning_rate": 1.9727296705359777e-07, + "loss": 0.7665, + "step": 10482 + }, + { + "epoch": 0.9386535340533886, + "grad_norm": 0.9085362740329684, + "learning_rate": 1.967001379982858e-07, + "loss": 0.8012, + "step": 10483 + }, + { + "epoch": 0.9387430745984666, + "grad_norm": 0.9368651048329844, + "learning_rate": 1.9612813356461146e-07, + "loss": 0.7757, + "step": 10484 + }, + { + "epoch": 0.9388326151435447, + "grad_norm": 1.1444718004476282, + "learning_rate": 1.9555695380068963e-07, + "loss": 0.7801, + "step": 10485 + }, + { + "epoch": 0.9389221556886228, + "grad_norm": 0.9178771368671131, + "learning_rate": 1.949865987545685e-07, + "loss": 0.7575, + "step": 10486 + }, + { + "epoch": 0.9390116962337008, + "grad_norm": 1.2017330091134577, + "learning_rate": 1.9441706847422193e-07, + "loss": 0.812, + "step": 10487 + }, + { + "epoch": 0.9391012367787789, + "grad_norm": 0.9815427041940191, + "learning_rate": 1.9384836300755937e-07, + "loss": 0.7722, + "step": 10488 + }, + { + "epoch": 0.9391907773238569, + "grad_norm": 0.9570668878069648, + "learning_rate": 1.9328048240241704e-07, + "loss": 0.7861, + "step": 10489 + }, + { + "epoch": 0.9392803178689351, + "grad_norm": 1.0396498270520502, + "learning_rate": 1.9271342670656336e-07, + "loss": 0.7125, + "step": 10490 + }, + { + "epoch": 0.9393698584140131, + "grad_norm": 0.9985456335543632, + "learning_rate": 1.921471959676957e-07, + "loss": 0.8076, + "step": 10491 + }, + { + "epoch": 0.9394593989590911, + "grad_norm": 0.9907317496304813, + "learning_rate": 1.9158179023344602e-07, + "loss": 0.8234, + "step": 10492 + }, + { + "epoch": 0.9395489395041692, + "grad_norm": 0.9654378895058732, + "learning_rate": 1.9101720955137293e-07, + "loss": 0.8299, + "step": 10493 + }, + { + "epoch": 0.9396384800492473, + "grad_norm": 1.0074574281156012, + "learning_rate": 1.9045345396896842e-07, + "loss": 0.7905, + "step": 10494 + }, + { + "epoch": 0.9397280205943254, + "grad_norm": 1.0285614162846088, + "learning_rate": 1.8989052353365345e-07, + "loss": 0.8124, + "step": 10495 + }, + { + "epoch": 0.9398175611394034, + "grad_norm": 1.0362353772999737, + "learning_rate": 1.8932841829277794e-07, + "loss": 0.7841, + "step": 10496 + }, + { + "epoch": 0.9399071016844815, + "grad_norm": 1.083685695554076, + "learning_rate": 1.8876713829362626e-07, + "loss": 0.8015, + "step": 10497 + }, + { + "epoch": 0.9399966422295596, + "grad_norm": 1.0059396100346234, + "learning_rate": 1.8820668358341065e-07, + "loss": 0.7471, + "step": 10498 + }, + { + "epoch": 0.9400861827746376, + "grad_norm": 0.985909761466985, + "learning_rate": 1.8764705420927566e-07, + "loss": 0.7722, + "step": 10499 + }, + { + "epoch": 0.9401757233197157, + "grad_norm": 1.0856857488873042, + "learning_rate": 1.8708825021829468e-07, + "loss": 0.711, + "step": 10500 + }, + { + "epoch": 0.9402652638647938, + "grad_norm": 1.054403568688193, + "learning_rate": 1.865302716574735e-07, + "loss": 0.7739, + "step": 10501 + }, + { + "epoch": 0.9403548044098718, + "grad_norm": 1.0526527826025391, + "learning_rate": 1.8597311857374568e-07, + "loss": 0.8174, + "step": 10502 + }, + { + "epoch": 0.9404443449549499, + "grad_norm": 1.092840794807833, + "learning_rate": 1.8541679101397814e-07, + "loss": 0.8139, + "step": 10503 + }, + { + "epoch": 0.940533885500028, + "grad_norm": 0.9613845143083771, + "learning_rate": 1.8486128902496682e-07, + "loss": 0.8113, + "step": 10504 + }, + { + "epoch": 0.9406234260451061, + "grad_norm": 0.9789444516415102, + "learning_rate": 1.8430661265344095e-07, + "loss": 0.8193, + "step": 10505 + }, + { + "epoch": 0.9407129665901841, + "grad_norm": 1.0209292311231506, + "learning_rate": 1.8375276194605552e-07, + "loss": 0.7375, + "step": 10506 + }, + { + "epoch": 0.9408025071352621, + "grad_norm": 1.0154420577946865, + "learning_rate": 1.8319973694939986e-07, + "loss": 0.8375, + "step": 10507 + }, + { + "epoch": 0.9408920476803403, + "grad_norm": 0.9827808467265221, + "learning_rate": 1.8264753770999233e-07, + "loss": 0.8073, + "step": 10508 + }, + { + "epoch": 0.9409815882254183, + "grad_norm": 1.0592262294798354, + "learning_rate": 1.8209616427428134e-07, + "loss": 0.8171, + "step": 10509 + }, + { + "epoch": 0.9410711287704964, + "grad_norm": 1.0551366290391107, + "learning_rate": 1.8154561668864645e-07, + "loss": 0.8252, + "step": 10510 + }, + { + "epoch": 0.9411606693155744, + "grad_norm": 0.9872608581185702, + "learning_rate": 1.8099589499940062e-07, + "loss": 0.815, + "step": 10511 + }, + { + "epoch": 0.9412502098606526, + "grad_norm": 0.9978466270788319, + "learning_rate": 1.8044699925278242e-07, + "loss": 0.8025, + "step": 10512 + }, + { + "epoch": 0.9413397504057306, + "grad_norm": 0.9176123158204633, + "learning_rate": 1.798989294949638e-07, + "loss": 0.762, + "step": 10513 + }, + { + "epoch": 0.9414292909508086, + "grad_norm": 0.9655092882387789, + "learning_rate": 1.7935168577204676e-07, + "loss": 0.7515, + "step": 10514 + }, + { + "epoch": 0.9415188314958868, + "grad_norm": 0.9617660578138079, + "learning_rate": 1.7880526813006226e-07, + "loss": 0.7529, + "step": 10515 + }, + { + "epoch": 0.9416083720409648, + "grad_norm": 0.917844488395302, + "learning_rate": 1.7825967661497466e-07, + "loss": 0.755, + "step": 10516 + }, + { + "epoch": 0.9416979125860429, + "grad_norm": 0.9137419306686104, + "learning_rate": 1.7771491127267726e-07, + "loss": 0.8, + "step": 10517 + }, + { + "epoch": 0.9417874531311209, + "grad_norm": 0.891426292033392, + "learning_rate": 1.7717097214899338e-07, + "loss": 0.7431, + "step": 10518 + }, + { + "epoch": 0.941876993676199, + "grad_norm": 1.0092366914009525, + "learning_rate": 1.7662785928967752e-07, + "loss": 0.7765, + "step": 10519 + }, + { + "epoch": 0.9419665342212771, + "grad_norm": 0.9800397999646994, + "learning_rate": 1.7608557274041428e-07, + "loss": 0.7955, + "step": 10520 + }, + { + "epoch": 0.9420560747663551, + "grad_norm": 0.9256999760073314, + "learning_rate": 1.7554411254682047e-07, + "loss": 0.8051, + "step": 10521 + }, + { + "epoch": 0.9421456153114333, + "grad_norm": 0.9182907826140562, + "learning_rate": 1.7500347875443968e-07, + "loss": 0.8692, + "step": 10522 + }, + { + "epoch": 0.9422351558565113, + "grad_norm": 1.1121737860956646, + "learning_rate": 1.7446367140874998e-07, + "loss": 0.778, + "step": 10523 + }, + { + "epoch": 0.9423246964015893, + "grad_norm": 0.9280995317634912, + "learning_rate": 1.7392469055515837e-07, + "loss": 0.7778, + "step": 10524 + }, + { + "epoch": 0.9424142369466674, + "grad_norm": 0.9869076547135597, + "learning_rate": 1.733865362390008e-07, + "loss": 0.7608, + "step": 10525 + }, + { + "epoch": 0.9425037774917455, + "grad_norm": 1.0329562250546835, + "learning_rate": 1.7284920850554664e-07, + "loss": 0.8239, + "step": 10526 + }, + { + "epoch": 0.9425933180368236, + "grad_norm": 1.0569717671041021, + "learning_rate": 1.7231270739999195e-07, + "loss": 0.8099, + "step": 10527 + }, + { + "epoch": 0.9426828585819016, + "grad_norm": 0.9692978270052119, + "learning_rate": 1.7177703296746838e-07, + "loss": 0.8226, + "step": 10528 + }, + { + "epoch": 0.9427723991269796, + "grad_norm": 0.9883768428363052, + "learning_rate": 1.7124218525303217e-07, + "loss": 0.8111, + "step": 10529 + }, + { + "epoch": 0.9428619396720578, + "grad_norm": 1.003751295938683, + "learning_rate": 1.7070816430167503e-07, + "loss": 0.8548, + "step": 10530 + }, + { + "epoch": 0.9429514802171358, + "grad_norm": 1.0120636166209647, + "learning_rate": 1.701749701583155e-07, + "loss": 0.7997, + "step": 10531 + }, + { + "epoch": 0.9430410207622139, + "grad_norm": 1.1157242678924864, + "learning_rate": 1.6964260286780666e-07, + "loss": 0.7993, + "step": 10532 + }, + { + "epoch": 0.943130561307292, + "grad_norm": 1.0290609021136858, + "learning_rate": 1.6911106247492592e-07, + "loss": 0.7867, + "step": 10533 + }, + { + "epoch": 0.94322010185237, + "grad_norm": 0.9879479982881689, + "learning_rate": 1.6858034902438757e-07, + "loss": 0.7872, + "step": 10534 + }, + { + "epoch": 0.9433096423974481, + "grad_norm": 1.1033960939862946, + "learning_rate": 1.6805046256083257e-07, + "loss": 0.769, + "step": 10535 + }, + { + "epoch": 0.9433991829425261, + "grad_norm": 1.0116193686039905, + "learning_rate": 1.6752140312883304e-07, + "loss": 0.8357, + "step": 10536 + }, + { + "epoch": 0.9434887234876043, + "grad_norm": 1.0233721592929788, + "learning_rate": 1.6699317077289223e-07, + "loss": 0.8229, + "step": 10537 + }, + { + "epoch": 0.9435782640326823, + "grad_norm": 0.9630626997699553, + "learning_rate": 1.6646576553744465e-07, + "loss": 0.7961, + "step": 10538 + }, + { + "epoch": 0.9436678045777603, + "grad_norm": 0.9743169789566054, + "learning_rate": 1.6593918746684923e-07, + "loss": 0.7356, + "step": 10539 + }, + { + "epoch": 0.9437573451228385, + "grad_norm": 0.9595195360946134, + "learning_rate": 1.65413436605405e-07, + "loss": 0.7884, + "step": 10540 + }, + { + "epoch": 0.9438468856679165, + "grad_norm": 0.9378856016892926, + "learning_rate": 1.6488851299733322e-07, + "loss": 0.756, + "step": 10541 + }, + { + "epoch": 0.9439364262129946, + "grad_norm": 1.0150204949502133, + "learning_rate": 1.643644166867908e-07, + "loss": 0.7944, + "step": 10542 + }, + { + "epoch": 0.9440259667580726, + "grad_norm": 1.0190050036785487, + "learning_rate": 1.6384114771786254e-07, + "loss": 0.807, + "step": 10543 + }, + { + "epoch": 0.9441155073031507, + "grad_norm": 0.9289392608148778, + "learning_rate": 1.6331870613456423e-07, + "loss": 0.7648, + "step": 10544 + }, + { + "epoch": 0.9442050478482288, + "grad_norm": 0.9457360813246329, + "learning_rate": 1.6279709198084082e-07, + "loss": 0.7796, + "step": 10545 + }, + { + "epoch": 0.9442945883933068, + "grad_norm": 0.9560795275673031, + "learning_rate": 1.6227630530056825e-07, + "loss": 0.7979, + "step": 10546 + }, + { + "epoch": 0.9443841289383849, + "grad_norm": 0.9466778412735403, + "learning_rate": 1.6175634613755597e-07, + "loss": 0.7764, + "step": 10547 + }, + { + "epoch": 0.944473669483463, + "grad_norm": 1.0349731811488116, + "learning_rate": 1.6123721453553897e-07, + "loss": 0.7694, + "step": 10548 + }, + { + "epoch": 0.944563210028541, + "grad_norm": 0.9824597761244583, + "learning_rate": 1.607189105381879e-07, + "loss": 0.823, + "step": 10549 + }, + { + "epoch": 0.9446527505736191, + "grad_norm": 1.1755373311349047, + "learning_rate": 1.6020143418909783e-07, + "loss": 0.8099, + "step": 10550 + }, + { + "epoch": 0.9447422911186972, + "grad_norm": 1.0214590778626063, + "learning_rate": 1.5968478553179733e-07, + "loss": 0.7795, + "step": 10551 + }, + { + "epoch": 0.9448318316637753, + "grad_norm": 0.923884689396745, + "learning_rate": 1.5916896460974608e-07, + "loss": 0.7848, + "step": 10552 + }, + { + "epoch": 0.9449213722088533, + "grad_norm": 1.0381815190055639, + "learning_rate": 1.5865397146633265e-07, + "loss": 0.7458, + "step": 10553 + }, + { + "epoch": 0.9450109127539313, + "grad_norm": 0.9663942748447644, + "learning_rate": 1.581398061448791e-07, + "loss": 0.7625, + "step": 10554 + }, + { + "epoch": 0.9451004532990095, + "grad_norm": 0.8617052443269132, + "learning_rate": 1.5762646868863195e-07, + "loss": 0.7375, + "step": 10555 + }, + { + "epoch": 0.9451899938440875, + "grad_norm": 0.9519206086421542, + "learning_rate": 1.5711395914077333e-07, + "loss": 0.8045, + "step": 10556 + }, + { + "epoch": 0.9452795343891656, + "grad_norm": 1.0685310697504005, + "learning_rate": 1.5660227754441316e-07, + "loss": 0.786, + "step": 10557 + }, + { + "epoch": 0.9453690749342437, + "grad_norm": 1.1451355224528967, + "learning_rate": 1.5609142394259257e-07, + "loss": 0.8234, + "step": 10558 + }, + { + "epoch": 0.9454586154793218, + "grad_norm": 1.002885238597944, + "learning_rate": 1.5558139837828278e-07, + "loss": 0.8074, + "step": 10559 + }, + { + "epoch": 0.9455481560243998, + "grad_norm": 1.2939504662471963, + "learning_rate": 1.5507220089438724e-07, + "loss": 0.804, + "step": 10560 + }, + { + "epoch": 0.9456376965694778, + "grad_norm": 0.9893762602582188, + "learning_rate": 1.54563831533735e-07, + "loss": 0.763, + "step": 10561 + }, + { + "epoch": 0.945727237114556, + "grad_norm": 0.9627461590038338, + "learning_rate": 1.5405629033909075e-07, + "loss": 0.7811, + "step": 10562 + }, + { + "epoch": 0.945816777659634, + "grad_norm": 1.010902898651545, + "learning_rate": 1.535495773531459e-07, + "loss": 0.8186, + "step": 10563 + }, + { + "epoch": 0.945906318204712, + "grad_norm": 0.9812904854451682, + "learning_rate": 1.5304369261852304e-07, + "loss": 0.7711, + "step": 10564 + }, + { + "epoch": 0.9459958587497901, + "grad_norm": 0.9615552488581134, + "learning_rate": 1.525386361777781e-07, + "loss": 0.7715, + "step": 10565 + }, + { + "epoch": 0.9460853992948682, + "grad_norm": 0.9437096278595699, + "learning_rate": 1.5203440807339265e-07, + "loss": 0.8143, + "step": 10566 + }, + { + "epoch": 0.9461749398399463, + "grad_norm": 0.9748468924276358, + "learning_rate": 1.5153100834778057e-07, + "loss": 0.8562, + "step": 10567 + }, + { + "epoch": 0.9462644803850243, + "grad_norm": 0.9567760334628974, + "learning_rate": 1.5102843704328684e-07, + "loss": 0.7504, + "step": 10568 + }, + { + "epoch": 0.9463540209301025, + "grad_norm": 0.9205170139724177, + "learning_rate": 1.5052669420218656e-07, + "loss": 0.7727, + "step": 10569 + }, + { + "epoch": 0.9464435614751805, + "grad_norm": 1.0058719554159496, + "learning_rate": 1.5002577986668376e-07, + "loss": 0.7357, + "step": 10570 + }, + { + "epoch": 0.9465331020202585, + "grad_norm": 1.0760287779525304, + "learning_rate": 1.495256940789147e-07, + "loss": 0.7586, + "step": 10571 + }, + { + "epoch": 0.9466226425653366, + "grad_norm": 0.9049619192721745, + "learning_rate": 1.4902643688094465e-07, + "loss": 0.782, + "step": 10572 + }, + { + "epoch": 0.9467121831104147, + "grad_norm": 1.0097372518213306, + "learning_rate": 1.4852800831476887e-07, + "loss": 0.7529, + "step": 10573 + }, + { + "epoch": 0.9468017236554928, + "grad_norm": 0.9873071979192511, + "learning_rate": 1.4803040842231385e-07, + "loss": 0.8063, + "step": 10574 + }, + { + "epoch": 0.9468912642005708, + "grad_norm": 1.1024028769655165, + "learning_rate": 1.4753363724543723e-07, + "loss": 0.8335, + "step": 10575 + }, + { + "epoch": 0.9469808047456489, + "grad_norm": 0.9299046625198809, + "learning_rate": 1.4703769482592335e-07, + "loss": 0.7689, + "step": 10576 + }, + { + "epoch": 0.947070345290727, + "grad_norm": 1.0078546292811292, + "learning_rate": 1.4654258120549102e-07, + "loss": 0.7946, + "step": 10577 + }, + { + "epoch": 0.947159885835805, + "grad_norm": 1.018350369987424, + "learning_rate": 1.460482964257881e-07, + "loss": 0.7383, + "step": 10578 + }, + { + "epoch": 0.947249426380883, + "grad_norm": 0.9372374689687759, + "learning_rate": 1.455548405283913e-07, + "loss": 0.8234, + "step": 10579 + }, + { + "epoch": 0.9473389669259612, + "grad_norm": 0.9916344862173925, + "learning_rate": 1.4506221355480744e-07, + "loss": 0.7273, + "step": 10580 + }, + { + "epoch": 0.9474285074710392, + "grad_norm": 1.0274132283379285, + "learning_rate": 1.4457041554647667e-07, + "loss": 0.7589, + "step": 10581 + }, + { + "epoch": 0.9475180480161173, + "grad_norm": 0.9393736670457288, + "learning_rate": 1.4407944654476702e-07, + "loss": 0.7951, + "step": 10582 + }, + { + "epoch": 0.9476075885611953, + "grad_norm": 1.0835777818320282, + "learning_rate": 1.4358930659097658e-07, + "loss": 0.7515, + "step": 10583 + }, + { + "epoch": 0.9476971291062735, + "grad_norm": 0.8851659204513486, + "learning_rate": 1.430999957263335e-07, + "loss": 0.7468, + "step": 10584 + }, + { + "epoch": 0.9477866696513515, + "grad_norm": 0.9695539500596535, + "learning_rate": 1.4261151399199924e-07, + "loss": 0.8184, + "step": 10585 + }, + { + "epoch": 0.9478762101964295, + "grad_norm": 1.0622914114536484, + "learning_rate": 1.4212386142906209e-07, + "loss": 0.8493, + "step": 10586 + }, + { + "epoch": 0.9479657507415077, + "grad_norm": 1.0075261186914495, + "learning_rate": 1.4163703807854147e-07, + "loss": 0.7961, + "step": 10587 + }, + { + "epoch": 0.9480552912865857, + "grad_norm": 0.9989404182267662, + "learning_rate": 1.411510439813868e-07, + "loss": 0.8317, + "step": 10588 + }, + { + "epoch": 0.9481448318316638, + "grad_norm": 0.9566753800221245, + "learning_rate": 1.4066587917848097e-07, + "loss": 0.8235, + "step": 10589 + }, + { + "epoch": 0.9482343723767418, + "grad_norm": 1.4457440422862284, + "learning_rate": 1.401815437106313e-07, + "loss": 0.8025, + "step": 10590 + }, + { + "epoch": 0.94832391292182, + "grad_norm": 0.9798218385394535, + "learning_rate": 1.3969803761858082e-07, + "loss": 0.7196, + "step": 10591 + }, + { + "epoch": 0.948413453466898, + "grad_norm": 0.9430661497168401, + "learning_rate": 1.3921536094299914e-07, + "loss": 0.7587, + "step": 10592 + }, + { + "epoch": 0.948502994011976, + "grad_norm": 1.4948437096893703, + "learning_rate": 1.3873351372448828e-07, + "loss": 0.7924, + "step": 10593 + }, + { + "epoch": 0.9485925345570542, + "grad_norm": 0.9803300803573628, + "learning_rate": 1.3825249600357915e-07, + "loss": 0.76, + "step": 10594 + }, + { + "epoch": 0.9486820751021322, + "grad_norm": 1.003604409507791, + "learning_rate": 1.3777230782073382e-07, + "loss": 0.822, + "step": 10595 + }, + { + "epoch": 0.9487716156472102, + "grad_norm": 0.9901994852247739, + "learning_rate": 1.372929492163433e-07, + "loss": 0.7626, + "step": 10596 + }, + { + "epoch": 0.9488611561922883, + "grad_norm": 1.0032595140646359, + "learning_rate": 1.3681442023073089e-07, + "loss": 0.818, + "step": 10597 + }, + { + "epoch": 0.9489506967373664, + "grad_norm": 1.071070828266927, + "learning_rate": 1.3633672090414775e-07, + "loss": 0.7883, + "step": 10598 + }, + { + "epoch": 0.9490402372824445, + "grad_norm": 0.9307142156168312, + "learning_rate": 1.3585985127677724e-07, + "loss": 0.8253, + "step": 10599 + }, + { + "epoch": 0.9491297778275225, + "grad_norm": 0.951937796914392, + "learning_rate": 1.353838113887307e-07, + "loss": 0.8376, + "step": 10600 + }, + { + "epoch": 0.9492193183726005, + "grad_norm": 0.93505506198809, + "learning_rate": 1.3490860128005267e-07, + "loss": 0.8021, + "step": 10601 + }, + { + "epoch": 0.9493088589176787, + "grad_norm": 0.9815630071241641, + "learning_rate": 1.344342209907168e-07, + "loss": 0.7855, + "step": 10602 + }, + { + "epoch": 0.9493983994627567, + "grad_norm": 0.9499900554125869, + "learning_rate": 1.3396067056062444e-07, + "loss": 0.7707, + "step": 10603 + }, + { + "epoch": 0.9494879400078348, + "grad_norm": 1.0721293651676682, + "learning_rate": 1.3348795002961046e-07, + "loss": 0.8306, + "step": 10604 + }, + { + "epoch": 0.9495774805529129, + "grad_norm": 0.8941313027061598, + "learning_rate": 1.3301605943743744e-07, + "loss": 0.8176, + "step": 10605 + }, + { + "epoch": 0.949667021097991, + "grad_norm": 1.0424319293277788, + "learning_rate": 1.3254499882379922e-07, + "loss": 0.7843, + "step": 10606 + }, + { + "epoch": 0.949756561643069, + "grad_norm": 0.9298724380798908, + "learning_rate": 1.320747682283219e-07, + "loss": 0.743, + "step": 10607 + }, + { + "epoch": 0.949846102188147, + "grad_norm": 0.872563212442681, + "learning_rate": 1.3160536769055708e-07, + "loss": 0.778, + "step": 10608 + }, + { + "epoch": 0.9499356427332252, + "grad_norm": 0.9999678593960863, + "learning_rate": 1.311367972499922e-07, + "loss": 0.8207, + "step": 10609 + }, + { + "epoch": 0.9500251832783032, + "grad_norm": 0.9639668169959477, + "learning_rate": 1.3066905694604004e-07, + "loss": 0.8024, + "step": 10610 + }, + { + "epoch": 0.9501147238233812, + "grad_norm": 0.9703339776921578, + "learning_rate": 1.3020214681804477e-07, + "loss": 0.8155, + "step": 10611 + }, + { + "epoch": 0.9502042643684594, + "grad_norm": 1.1661844948212763, + "learning_rate": 1.2973606690528162e-07, + "loss": 0.8309, + "step": 10612 + }, + { + "epoch": 0.9502938049135374, + "grad_norm": 1.0429892588027683, + "learning_rate": 1.29270817246957e-07, + "loss": 0.7525, + "step": 10613 + }, + { + "epoch": 0.9503833454586155, + "grad_norm": 1.1153590224096566, + "learning_rate": 1.288063978822063e-07, + "loss": 0.8284, + "step": 10614 + }, + { + "epoch": 0.9504728860036935, + "grad_norm": 1.0367178884872523, + "learning_rate": 1.2834280885009375e-07, + "loss": 0.8415, + "step": 10615 + }, + { + "epoch": 0.9505624265487717, + "grad_norm": 1.2801265988405155, + "learning_rate": 1.2788005018961492e-07, + "loss": 0.7822, + "step": 10616 + }, + { + "epoch": 0.9506519670938497, + "grad_norm": 1.2338212012812513, + "learning_rate": 1.2741812193969528e-07, + "loss": 0.844, + "step": 10617 + }, + { + "epoch": 0.9507415076389277, + "grad_norm": 0.9407184995249785, + "learning_rate": 1.2695702413919152e-07, + "loss": 0.7949, + "step": 10618 + }, + { + "epoch": 0.9508310481840058, + "grad_norm": 0.962092215626412, + "learning_rate": 1.2649675682689044e-07, + "loss": 0.7774, + "step": 10619 + }, + { + "epoch": 0.9509205887290839, + "grad_norm": 0.9780304283020984, + "learning_rate": 1.260373200415077e-07, + "loss": 0.7737, + "step": 10620 + }, + { + "epoch": 0.951010129274162, + "grad_norm": 0.9790475839881357, + "learning_rate": 1.2557871382168795e-07, + "loss": 0.8311, + "step": 10621 + }, + { + "epoch": 0.95109966981924, + "grad_norm": 0.9963308247141596, + "learning_rate": 1.2512093820600922e-07, + "loss": 0.7662, + "step": 10622 + }, + { + "epoch": 0.9511892103643181, + "grad_norm": 1.090963492528114, + "learning_rate": 1.2466399323297851e-07, + "loss": 0.7544, + "step": 10623 + }, + { + "epoch": 0.9512787509093962, + "grad_norm": 1.0057320245272516, + "learning_rate": 1.2420787894103058e-07, + "loss": 0.7859, + "step": 10624 + }, + { + "epoch": 0.9513682914544742, + "grad_norm": 1.065061393013988, + "learning_rate": 1.237525953685359e-07, + "loss": 0.7875, + "step": 10625 + }, + { + "epoch": 0.9514578319995523, + "grad_norm": 0.8964377964519797, + "learning_rate": 1.2329814255378713e-07, + "loss": 0.7374, + "step": 10626 + }, + { + "epoch": 0.9515473725446304, + "grad_norm": 1.0713444173270354, + "learning_rate": 1.2284452053501483e-07, + "loss": 0.8013, + "step": 10627 + }, + { + "epoch": 0.9516369130897084, + "grad_norm": 0.9770274185596978, + "learning_rate": 1.22391729350374e-07, + "loss": 0.8114, + "step": 10628 + }, + { + "epoch": 0.9517264536347865, + "grad_norm": 0.9606472233247016, + "learning_rate": 1.2193976903795203e-07, + "loss": 0.8134, + "step": 10629 + }, + { + "epoch": 0.9518159941798646, + "grad_norm": 0.9490257693443686, + "learning_rate": 1.214886396357684e-07, + "loss": 0.7389, + "step": 10630 + }, + { + "epoch": 0.9519055347249427, + "grad_norm": 1.0000073650405197, + "learning_rate": 1.210383411817684e-07, + "loss": 0.8299, + "step": 10631 + }, + { + "epoch": 0.9519950752700207, + "grad_norm": 0.9518960583625684, + "learning_rate": 1.2058887371383054e-07, + "loss": 0.7163, + "step": 10632 + }, + { + "epoch": 0.9520846158150987, + "grad_norm": 1.037474257880494, + "learning_rate": 1.2014023726976242e-07, + "loss": 0.7652, + "step": 10633 + }, + { + "epoch": 0.9521741563601769, + "grad_norm": 1.055329942281204, + "learning_rate": 1.1969243188730273e-07, + "loss": 0.8264, + "step": 10634 + }, + { + "epoch": 0.9522636969052549, + "grad_norm": 1.0482411176673405, + "learning_rate": 1.1924545760411798e-07, + "loss": 0.76, + "step": 10635 + }, + { + "epoch": 0.952353237450333, + "grad_norm": 0.9400739283147899, + "learning_rate": 1.1879931445780702e-07, + "loss": 0.7875, + "step": 10636 + }, + { + "epoch": 0.952442777995411, + "grad_norm": 1.0088195085030172, + "learning_rate": 1.1835400248589756e-07, + "loss": 0.8164, + "step": 10637 + }, + { + "epoch": 0.9525323185404891, + "grad_norm": 1.0670088165795595, + "learning_rate": 1.1790952172584858e-07, + "loss": 0.843, + "step": 10638 + }, + { + "epoch": 0.9526218590855672, + "grad_norm": 1.0309419294151398, + "learning_rate": 1.174658722150479e-07, + "loss": 0.8123, + "step": 10639 + }, + { + "epoch": 0.9527113996306452, + "grad_norm": 0.9910358758513832, + "learning_rate": 1.1702305399081349e-07, + "loss": 0.7708, + "step": 10640 + }, + { + "epoch": 0.9528009401757234, + "grad_norm": 0.9297155839896183, + "learning_rate": 1.1658106709039441e-07, + "loss": 0.7648, + "step": 10641 + }, + { + "epoch": 0.9528904807208014, + "grad_norm": 0.957882872384158, + "learning_rate": 1.161399115509676e-07, + "loss": 0.7417, + "step": 10642 + }, + { + "epoch": 0.9529800212658794, + "grad_norm": 0.8964124035575063, + "learning_rate": 1.1569958740964449e-07, + "loss": 0.7895, + "step": 10643 + }, + { + "epoch": 0.9530695618109575, + "grad_norm": 0.9155916389922302, + "learning_rate": 1.15260094703461e-07, + "loss": 0.7755, + "step": 10644 + }, + { + "epoch": 0.9531591023560356, + "grad_norm": 1.218252575293368, + "learning_rate": 1.1482143346938757e-07, + "loss": 0.8459, + "step": 10645 + }, + { + "epoch": 0.9532486429011137, + "grad_norm": 0.9898203666733881, + "learning_rate": 1.1438360374432134e-07, + "loss": 0.8456, + "step": 10646 + }, + { + "epoch": 0.9533381834461917, + "grad_norm": 1.103660416204914, + "learning_rate": 1.1394660556509285e-07, + "loss": 0.8236, + "step": 10647 + }, + { + "epoch": 0.9534277239912698, + "grad_norm": 1.2989330019185708, + "learning_rate": 1.1351043896846048e-07, + "loss": 0.7945, + "step": 10648 + }, + { + "epoch": 0.9535172645363479, + "grad_norm": 1.0603891802204617, + "learning_rate": 1.1307510399111266e-07, + "loss": 0.7717, + "step": 10649 + }, + { + "epoch": 0.9536068050814259, + "grad_norm": 0.9182954179885463, + "learning_rate": 1.1264060066966786e-07, + "loss": 0.8176, + "step": 10650 + }, + { + "epoch": 0.953696345626504, + "grad_norm": 1.0141724099238418, + "learning_rate": 1.1220692904067687e-07, + "loss": 0.8355, + "step": 10651 + }, + { + "epoch": 0.9537858861715821, + "grad_norm": 1.015956073421443, + "learning_rate": 1.1177408914061604e-07, + "loss": 0.8083, + "step": 10652 + }, + { + "epoch": 0.9538754267166601, + "grad_norm": 1.0649456999798674, + "learning_rate": 1.113420810058985e-07, + "loss": 0.794, + "step": 10653 + }, + { + "epoch": 0.9539649672617382, + "grad_norm": 1.0051863678755355, + "learning_rate": 1.1091090467285848e-07, + "loss": 0.8097, + "step": 10654 + }, + { + "epoch": 0.9540545078068162, + "grad_norm": 0.9796699311175886, + "learning_rate": 1.1048056017776809e-07, + "loss": 0.7538, + "step": 10655 + }, + { + "epoch": 0.9541440483518944, + "grad_norm": 0.9254765725641129, + "learning_rate": 1.1005104755682617e-07, + "loss": 0.7804, + "step": 10656 + }, + { + "epoch": 0.9542335888969724, + "grad_norm": 0.9882063342980724, + "learning_rate": 1.0962236684616157e-07, + "loss": 0.8011, + "step": 10657 + }, + { + "epoch": 0.9543231294420504, + "grad_norm": 1.3708350502973423, + "learning_rate": 1.0919451808183435e-07, + "loss": 0.8598, + "step": 10658 + }, + { + "epoch": 0.9544126699871286, + "grad_norm": 1.3766498483472975, + "learning_rate": 1.0876750129983349e-07, + "loss": 0.8307, + "step": 10659 + }, + { + "epoch": 0.9545022105322066, + "grad_norm": 0.9390187108296227, + "learning_rate": 1.0834131653607582e-07, + "loss": 0.7812, + "step": 10660 + }, + { + "epoch": 0.9545917510772847, + "grad_norm": 1.0079062932445724, + "learning_rate": 1.0791596382641378e-07, + "loss": 0.834, + "step": 10661 + }, + { + "epoch": 0.9546812916223627, + "grad_norm": 0.96229420986048, + "learning_rate": 1.0749144320662541e-07, + "loss": 0.7531, + "step": 10662 + }, + { + "epoch": 0.9547708321674409, + "grad_norm": 0.9035627002833151, + "learning_rate": 1.0706775471242104e-07, + "loss": 0.7252, + "step": 10663 + }, + { + "epoch": 0.9548603727125189, + "grad_norm": 0.9622529907786203, + "learning_rate": 1.066448983794377e-07, + "loss": 0.8324, + "step": 10664 + }, + { + "epoch": 0.9549499132575969, + "grad_norm": 0.9872810285582793, + "learning_rate": 1.0622287424324696e-07, + "loss": 0.8197, + "step": 10665 + }, + { + "epoch": 0.9550394538026751, + "grad_norm": 1.0803384847328674, + "learning_rate": 1.0580168233934596e-07, + "loss": 0.7708, + "step": 10666 + }, + { + "epoch": 0.9551289943477531, + "grad_norm": 0.9420107021016394, + "learning_rate": 1.0538132270316526e-07, + "loss": 0.7512, + "step": 10667 + }, + { + "epoch": 0.9552185348928312, + "grad_norm": 0.9613135363148781, + "learning_rate": 1.0496179537006435e-07, + "loss": 0.7751, + "step": 10668 + }, + { + "epoch": 0.9553080754379092, + "grad_norm": 1.0299769318328478, + "learning_rate": 1.0454310037533388e-07, + "loss": 0.7931, + "step": 10669 + }, + { + "epoch": 0.9553976159829873, + "grad_norm": 0.9607330423012813, + "learning_rate": 1.0412523775419014e-07, + "loss": 0.8361, + "step": 10670 + }, + { + "epoch": 0.9554871565280654, + "grad_norm": 0.9794103489741643, + "learning_rate": 1.0370820754178279e-07, + "loss": 0.8507, + "step": 10671 + }, + { + "epoch": 0.9555766970731434, + "grad_norm": 0.914166971626092, + "learning_rate": 1.0329200977319265e-07, + "loss": 0.6974, + "step": 10672 + }, + { + "epoch": 0.9556662376182214, + "grad_norm": 0.9744205034679365, + "learning_rate": 1.0287664448342838e-07, + "loss": 0.791, + "step": 10673 + }, + { + "epoch": 0.9557557781632996, + "grad_norm": 0.9290085611373504, + "learning_rate": 1.024621117074287e-07, + "loss": 0.7745, + "step": 10674 + }, + { + "epoch": 0.9558453187083776, + "grad_norm": 0.9410225610472153, + "learning_rate": 1.020484114800635e-07, + "loss": 0.762, + "step": 10675 + }, + { + "epoch": 0.9559348592534557, + "grad_norm": 1.1130783841409277, + "learning_rate": 1.0163554383613161e-07, + "loss": 0.8089, + "step": 10676 + }, + { + "epoch": 0.9560243997985338, + "grad_norm": 1.0917557655286239, + "learning_rate": 1.0122350881036081e-07, + "loss": 0.7641, + "step": 10677 + }, + { + "epoch": 0.9561139403436119, + "grad_norm": 0.9306129744003709, + "learning_rate": 1.0081230643741114e-07, + "loss": 0.7618, + "step": 10678 + }, + { + "epoch": 0.9562034808886899, + "grad_norm": 0.947991085683517, + "learning_rate": 1.0040193675187271e-07, + "loss": 0.8156, + "step": 10679 + }, + { + "epoch": 0.9562930214337679, + "grad_norm": 0.8929510145425168, + "learning_rate": 9.999239978826459e-08, + "loss": 0.8067, + "step": 10680 + }, + { + "epoch": 0.9563825619788461, + "grad_norm": 0.9904437917492505, + "learning_rate": 9.958369558103254e-08, + "loss": 0.8349, + "step": 10681 + }, + { + "epoch": 0.9564721025239241, + "grad_norm": 1.0777655000349118, + "learning_rate": 9.917582416455796e-08, + "loss": 0.801, + "step": 10682 + }, + { + "epoch": 0.9565616430690022, + "grad_norm": 0.9766062588971706, + "learning_rate": 9.876878557315006e-08, + "loss": 0.7447, + "step": 10683 + }, + { + "epoch": 0.9566511836140803, + "grad_norm": 0.9938630049899553, + "learning_rate": 9.836257984104591e-08, + "loss": 0.8133, + "step": 10684 + }, + { + "epoch": 0.9567407241591583, + "grad_norm": 1.0011471936749594, + "learning_rate": 9.795720700241595e-08, + "loss": 0.8146, + "step": 10685 + }, + { + "epoch": 0.9568302647042364, + "grad_norm": 1.178253758047852, + "learning_rate": 9.755266709135736e-08, + "loss": 0.8414, + "step": 10686 + }, + { + "epoch": 0.9569198052493144, + "grad_norm": 1.02579160710646, + "learning_rate": 9.714896014189845e-08, + "loss": 0.8141, + "step": 10687 + }, + { + "epoch": 0.9570093457943926, + "grad_norm": 0.915020117213658, + "learning_rate": 9.674608618799986e-08, + "loss": 0.813, + "step": 10688 + }, + { + "epoch": 0.9570988863394706, + "grad_norm": 1.0283961868037617, + "learning_rate": 9.634404526354779e-08, + "loss": 0.7973, + "step": 10689 + }, + { + "epoch": 0.9571884268845486, + "grad_norm": 1.0842826273719446, + "learning_rate": 9.594283740236187e-08, + "loss": 0.8192, + "step": 10690 + }, + { + "epoch": 0.9572779674296267, + "grad_norm": 1.0530430326430122, + "learning_rate": 9.554246263819067e-08, + "loss": 0.8001, + "step": 10691 + }, + { + "epoch": 0.9573675079747048, + "grad_norm": 1.040726874036281, + "learning_rate": 9.514292100471056e-08, + "loss": 0.799, + "step": 10692 + }, + { + "epoch": 0.9574570485197829, + "grad_norm": 0.996005404353338, + "learning_rate": 9.474421253553135e-08, + "loss": 0.8194, + "step": 10693 + }, + { + "epoch": 0.9575465890648609, + "grad_norm": 1.048512735214228, + "learning_rate": 9.434633726419173e-08, + "loss": 0.8274, + "step": 10694 + }, + { + "epoch": 0.957636129609939, + "grad_norm": 1.0184722854961523, + "learning_rate": 9.394929522415719e-08, + "loss": 0.8506, + "step": 10695 + }, + { + "epoch": 0.9577256701550171, + "grad_norm": 0.9435227092023951, + "learning_rate": 9.355308644882877e-08, + "loss": 0.7942, + "step": 10696 + }, + { + "epoch": 0.9578152107000951, + "grad_norm": 0.8663202384694958, + "learning_rate": 9.315771097153092e-08, + "loss": 0.8017, + "step": 10697 + }, + { + "epoch": 0.9579047512451732, + "grad_norm": 0.936533555532817, + "learning_rate": 9.276316882552372e-08, + "loss": 0.7981, + "step": 10698 + }, + { + "epoch": 0.9579942917902513, + "grad_norm": 1.033619364141493, + "learning_rate": 9.236946004399394e-08, + "loss": 0.8165, + "step": 10699 + }, + { + "epoch": 0.9580838323353293, + "grad_norm": 0.9672780354091469, + "learning_rate": 9.197658466005843e-08, + "loss": 0.834, + "step": 10700 + }, + { + "epoch": 0.9581733728804074, + "grad_norm": 1.1331011114076677, + "learning_rate": 9.15845427067663e-08, + "loss": 0.8162, + "step": 10701 + }, + { + "epoch": 0.9582629134254855, + "grad_norm": 0.909364142416958, + "learning_rate": 9.119333421709341e-08, + "loss": 0.8013, + "step": 10702 + }, + { + "epoch": 0.9583524539705636, + "grad_norm": 1.0545715700275688, + "learning_rate": 9.080295922394788e-08, + "loss": 0.8256, + "step": 10703 + }, + { + "epoch": 0.9584419945156416, + "grad_norm": 1.120573983545074, + "learning_rate": 9.041341776016565e-08, + "loss": 0.7923, + "step": 10704 + }, + { + "epoch": 0.9585315350607196, + "grad_norm": 1.0474368437261667, + "learning_rate": 9.002470985851386e-08, + "loss": 0.8394, + "step": 10705 + }, + { + "epoch": 0.9586210756057978, + "grad_norm": 1.0291204732826473, + "learning_rate": 8.963683555169078e-08, + "loss": 0.8066, + "step": 10706 + }, + { + "epoch": 0.9587106161508758, + "grad_norm": 1.0311381891936429, + "learning_rate": 8.924979487232255e-08, + "loss": 0.7868, + "step": 10707 + }, + { + "epoch": 0.9588001566959539, + "grad_norm": 1.0105482206935334, + "learning_rate": 8.886358785296423e-08, + "loss": 0.8091, + "step": 10708 + }, + { + "epoch": 0.9588896972410319, + "grad_norm": 1.0188566167049309, + "learning_rate": 8.847821452610316e-08, + "loss": 0.7826, + "step": 10709 + }, + { + "epoch": 0.95897923778611, + "grad_norm": 1.01137759379712, + "learning_rate": 8.809367492415677e-08, + "loss": 0.8001, + "step": 10710 + }, + { + "epoch": 0.9590687783311881, + "grad_norm": 1.023838869857259, + "learning_rate": 8.770996907947027e-08, + "loss": 0.8211, + "step": 10711 + }, + { + "epoch": 0.9591583188762661, + "grad_norm": 0.9887333676523925, + "learning_rate": 8.732709702432007e-08, + "loss": 0.8212, + "step": 10712 + }, + { + "epoch": 0.9592478594213443, + "grad_norm": 1.0600232572798522, + "learning_rate": 8.694505879091263e-08, + "loss": 0.7595, + "step": 10713 + }, + { + "epoch": 0.9593373999664223, + "grad_norm": 1.0856134361660486, + "learning_rate": 8.656385441138227e-08, + "loss": 0.8203, + "step": 10714 + }, + { + "epoch": 0.9594269405115003, + "grad_norm": 0.9167649652956195, + "learning_rate": 8.618348391779551e-08, + "loss": 0.8441, + "step": 10715 + }, + { + "epoch": 0.9595164810565784, + "grad_norm": 1.0070769256538696, + "learning_rate": 8.580394734214792e-08, + "loss": 0.7378, + "step": 10716 + }, + { + "epoch": 0.9596060216016565, + "grad_norm": 0.9868131879287869, + "learning_rate": 8.542524471636504e-08, + "loss": 0.7931, + "step": 10717 + }, + { + "epoch": 0.9596955621467346, + "grad_norm": 0.9758084856321736, + "learning_rate": 8.504737607230252e-08, + "loss": 0.8303, + "step": 10718 + }, + { + "epoch": 0.9597851026918126, + "grad_norm": 0.9630950799962955, + "learning_rate": 8.467034144174491e-08, + "loss": 0.7638, + "step": 10719 + }, + { + "epoch": 0.9598746432368908, + "grad_norm": 1.1283929233516516, + "learning_rate": 8.429414085640574e-08, + "loss": 0.8005, + "step": 10720 + }, + { + "epoch": 0.9599641837819688, + "grad_norm": 0.9379747067637351, + "learning_rate": 8.391877434793194e-08, + "loss": 0.8308, + "step": 10721 + }, + { + "epoch": 0.9600537243270468, + "grad_norm": 1.0430526069037074, + "learning_rate": 8.354424194789713e-08, + "loss": 0.8318, + "step": 10722 + }, + { + "epoch": 0.9601432648721249, + "grad_norm": 0.9721217077337018, + "learning_rate": 8.317054368780497e-08, + "loss": 0.8205, + "step": 10723 + }, + { + "epoch": 0.960232805417203, + "grad_norm": 1.1012463343682937, + "learning_rate": 8.279767959909257e-08, + "loss": 0.7872, + "step": 10724 + }, + { + "epoch": 0.960322345962281, + "grad_norm": 1.1032419540099363, + "learning_rate": 8.24256497131204e-08, + "loss": 0.8437, + "step": 10725 + }, + { + "epoch": 0.9604118865073591, + "grad_norm": 1.006673084550879, + "learning_rate": 8.20544540611845e-08, + "loss": 0.7575, + "step": 10726 + }, + { + "epoch": 0.9605014270524371, + "grad_norm": 0.9939876509058281, + "learning_rate": 8.168409267450883e-08, + "loss": 0.8057, + "step": 10727 + }, + { + "epoch": 0.9605909675975153, + "grad_norm": 1.002189372674301, + "learning_rate": 8.131456558424622e-08, + "loss": 0.7992, + "step": 10728 + }, + { + "epoch": 0.9606805081425933, + "grad_norm": 1.0878673719911007, + "learning_rate": 8.09458728214807e-08, + "loss": 0.7513, + "step": 10729 + }, + { + "epoch": 0.9607700486876714, + "grad_norm": 0.9334721931125108, + "learning_rate": 8.057801441722524e-08, + "loss": 0.788, + "step": 10730 + }, + { + "epoch": 0.9608595892327495, + "grad_norm": 1.0131028166238258, + "learning_rate": 8.021099040242175e-08, + "loss": 0.8117, + "step": 10731 + }, + { + "epoch": 0.9609491297778275, + "grad_norm": 0.9530102521647551, + "learning_rate": 7.984480080794443e-08, + "loss": 0.793, + "step": 10732 + }, + { + "epoch": 0.9610386703229056, + "grad_norm": 0.9016752457452283, + "learning_rate": 7.947944566459532e-08, + "loss": 0.7445, + "step": 10733 + }, + { + "epoch": 0.9611282108679836, + "grad_norm": 0.972612932130089, + "learning_rate": 7.911492500310758e-08, + "loss": 0.7652, + "step": 10734 + }, + { + "epoch": 0.9612177514130618, + "grad_norm": 1.0101671197354496, + "learning_rate": 7.875123885414337e-08, + "loss": 0.7746, + "step": 10735 + }, + { + "epoch": 0.9613072919581398, + "grad_norm": 1.0569272783740187, + "learning_rate": 7.83883872482949e-08, + "loss": 0.8063, + "step": 10736 + }, + { + "epoch": 0.9613968325032178, + "grad_norm": 0.887543913209278, + "learning_rate": 7.802637021608329e-08, + "loss": 0.8054, + "step": 10737 + }, + { + "epoch": 0.961486373048296, + "grad_norm": 0.9589668848409285, + "learning_rate": 7.766518778795972e-08, + "loss": 0.7705, + "step": 10738 + }, + { + "epoch": 0.961575913593374, + "grad_norm": 0.9177599437614837, + "learning_rate": 7.730483999430661e-08, + "loss": 0.811, + "step": 10739 + }, + { + "epoch": 0.9616654541384521, + "grad_norm": 0.9873938517712042, + "learning_rate": 7.694532686543632e-08, + "loss": 0.8221, + "step": 10740 + }, + { + "epoch": 0.9617549946835301, + "grad_norm": 1.1130843923784588, + "learning_rate": 7.658664843158914e-08, + "loss": 0.7601, + "step": 10741 + }, + { + "epoch": 0.9618445352286082, + "grad_norm": 1.0127411071774635, + "learning_rate": 7.622880472293537e-08, + "loss": 0.7857, + "step": 10742 + }, + { + "epoch": 0.9619340757736863, + "grad_norm": 0.9832283983248711, + "learning_rate": 7.587179576957537e-08, + "loss": 0.8982, + "step": 10743 + }, + { + "epoch": 0.9620236163187643, + "grad_norm": 1.0562070421441245, + "learning_rate": 7.551562160153957e-08, + "loss": 0.8803, + "step": 10744 + }, + { + "epoch": 0.9621131568638424, + "grad_norm": 0.9007844840785783, + "learning_rate": 7.516028224878957e-08, + "loss": 0.7833, + "step": 10745 + }, + { + "epoch": 0.9622026974089205, + "grad_norm": 0.8696844899468402, + "learning_rate": 7.480577774121478e-08, + "loss": 0.7702, + "step": 10746 + }, + { + "epoch": 0.9622922379539985, + "grad_norm": 0.9495309562581002, + "learning_rate": 7.445210810863357e-08, + "loss": 0.8133, + "step": 10747 + }, + { + "epoch": 0.9623817784990766, + "grad_norm": 1.11055758773311, + "learning_rate": 7.40992733807977e-08, + "loss": 0.7542, + "step": 10748 + }, + { + "epoch": 0.9624713190441547, + "grad_norm": 0.9524018960485578, + "learning_rate": 7.374727358738454e-08, + "loss": 0.8098, + "step": 10749 + }, + { + "epoch": 0.9625608595892328, + "grad_norm": 1.0183370538093015, + "learning_rate": 7.339610875800485e-08, + "loss": 0.8367, + "step": 10750 + }, + { + "epoch": 0.9626504001343108, + "grad_norm": 0.9102362230603674, + "learning_rate": 7.30457789221961e-08, + "loss": 0.7889, + "step": 10751 + }, + { + "epoch": 0.9627399406793888, + "grad_norm": 0.9700603445062228, + "learning_rate": 7.269628410942808e-08, + "loss": 0.7416, + "step": 10752 + }, + { + "epoch": 0.962829481224467, + "grad_norm": 1.021629753837941, + "learning_rate": 7.234762434909725e-08, + "loss": 0.8563, + "step": 10753 + }, + { + "epoch": 0.962919021769545, + "grad_norm": 0.9728270123423797, + "learning_rate": 7.199979967053461e-08, + "loss": 0.7743, + "step": 10754 + }, + { + "epoch": 0.9630085623146231, + "grad_norm": 1.0251613038647325, + "learning_rate": 7.165281010299452e-08, + "loss": 0.725, + "step": 10755 + }, + { + "epoch": 0.9630981028597012, + "grad_norm": 1.0684647688296331, + "learning_rate": 7.130665567566808e-08, + "loss": 0.8202, + "step": 10756 + }, + { + "epoch": 0.9631876434047792, + "grad_norm": 1.00897035927911, + "learning_rate": 7.096133641767088e-08, + "loss": 0.7555, + "step": 10757 + }, + { + "epoch": 0.9632771839498573, + "grad_norm": 0.9735896219928971, + "learning_rate": 7.061685235804972e-08, + "loss": 0.7934, + "step": 10758 + }, + { + "epoch": 0.9633667244949353, + "grad_norm": 0.9471928711425164, + "learning_rate": 7.027320352578137e-08, + "loss": 0.74, + "step": 10759 + }, + { + "epoch": 0.9634562650400135, + "grad_norm": 0.9021493190171377, + "learning_rate": 6.993038994977386e-08, + "loss": 0.7347, + "step": 10760 + }, + { + "epoch": 0.9635458055850915, + "grad_norm": 0.9787628717453836, + "learning_rate": 6.958841165886299e-08, + "loss": 0.7287, + "step": 10761 + }, + { + "epoch": 0.9636353461301695, + "grad_norm": 0.9771052321076897, + "learning_rate": 6.924726868181464e-08, + "loss": 0.8171, + "step": 10762 + }, + { + "epoch": 0.9637248866752476, + "grad_norm": 0.9818512616284012, + "learning_rate": 6.890696104732475e-08, + "loss": 0.7583, + "step": 10763 + }, + { + "epoch": 0.9638144272203257, + "grad_norm": 0.9653019922177514, + "learning_rate": 6.85674887840182e-08, + "loss": 0.7692, + "step": 10764 + }, + { + "epoch": 0.9639039677654038, + "grad_norm": 1.0539220449500888, + "learning_rate": 6.822885192045215e-08, + "loss": 0.7901, + "step": 10765 + }, + { + "epoch": 0.9639935083104818, + "grad_norm": 0.984672347571423, + "learning_rate": 6.789105048510935e-08, + "loss": 0.7769, + "step": 10766 + }, + { + "epoch": 0.96408304885556, + "grad_norm": 1.078862941483327, + "learning_rate": 6.755408450640599e-08, + "loss": 0.7894, + "step": 10767 + }, + { + "epoch": 0.964172589400638, + "grad_norm": 1.14397365618563, + "learning_rate": 6.721795401268493e-08, + "loss": 0.8711, + "step": 10768 + }, + { + "epoch": 0.964262129945716, + "grad_norm": 1.10631340995849, + "learning_rate": 6.688265903222247e-08, + "loss": 0.8284, + "step": 10769 + }, + { + "epoch": 0.9643516704907941, + "grad_norm": 0.9255328016932481, + "learning_rate": 6.654819959322268e-08, + "loss": 0.7704, + "step": 10770 + }, + { + "epoch": 0.9644412110358722, + "grad_norm": 1.0169822620107298, + "learning_rate": 6.62145757238164e-08, + "loss": 0.8035, + "step": 10771 + }, + { + "epoch": 0.9645307515809503, + "grad_norm": 0.9470005735548787, + "learning_rate": 6.588178745207008e-08, + "loss": 0.7842, + "step": 10772 + }, + { + "epoch": 0.9646202921260283, + "grad_norm": 0.9791359742993925, + "learning_rate": 6.554983480597576e-08, + "loss": 0.8205, + "step": 10773 + }, + { + "epoch": 0.9647098326711064, + "grad_norm": 0.9686201893409735, + "learning_rate": 6.521871781345446e-08, + "loss": 0.7997, + "step": 10774 + }, + { + "epoch": 0.9647993732161845, + "grad_norm": 1.1272040213586003, + "learning_rate": 6.488843650236054e-08, + "loss": 0.8078, + "step": 10775 + }, + { + "epoch": 0.9648889137612625, + "grad_norm": 0.9855648531827726, + "learning_rate": 6.455899090047623e-08, + "loss": 0.8036, + "step": 10776 + }, + { + "epoch": 0.9649784543063405, + "grad_norm": 0.9400190269580695, + "learning_rate": 6.42303810355116e-08, + "loss": 0.7537, + "step": 10777 + }, + { + "epoch": 0.9650679948514187, + "grad_norm": 1.0167767901886637, + "learning_rate": 6.390260693511119e-08, + "loss": 0.7952, + "step": 10778 + }, + { + "epoch": 0.9651575353964967, + "grad_norm": 1.0092617018081764, + "learning_rate": 6.357566862684406e-08, + "loss": 0.7748, + "step": 10779 + }, + { + "epoch": 0.9652470759415748, + "grad_norm": 0.8930946494348282, + "learning_rate": 6.324956613821153e-08, + "loss": 0.7548, + "step": 10780 + }, + { + "epoch": 0.9653366164866528, + "grad_norm": 1.06087981184842, + "learning_rate": 6.292429949664502e-08, + "loss": 0.7988, + "step": 10781 + }, + { + "epoch": 0.965426157031731, + "grad_norm": 0.8781480498745912, + "learning_rate": 6.259986872950485e-08, + "loss": 0.7879, + "step": 10782 + }, + { + "epoch": 0.965515697576809, + "grad_norm": 1.063333256649386, + "learning_rate": 6.227627386408031e-08, + "loss": 0.7479, + "step": 10783 + }, + { + "epoch": 0.965605238121887, + "grad_norm": 1.0951482394660654, + "learning_rate": 6.195351492759183e-08, + "loss": 0.8082, + "step": 10784 + }, + { + "epoch": 0.9656947786669652, + "grad_norm": 1.0381692512860752, + "learning_rate": 6.16315919471877e-08, + "loss": 0.7676, + "step": 10785 + }, + { + "epoch": 0.9657843192120432, + "grad_norm": 0.9260969546095864, + "learning_rate": 6.13105049499474e-08, + "loss": 0.8167, + "step": 10786 + }, + { + "epoch": 0.9658738597571213, + "grad_norm": 1.0479636750775732, + "learning_rate": 6.09902539628815e-08, + "loss": 0.7742, + "step": 10787 + }, + { + "epoch": 0.9659634003021993, + "grad_norm": 1.2213792251467075, + "learning_rate": 6.067083901292625e-08, + "loss": 0.7547, + "step": 10788 + }, + { + "epoch": 0.9660529408472774, + "grad_norm": 0.9671806654773634, + "learning_rate": 6.035226012695239e-08, + "loss": 0.8019, + "step": 10789 + }, + { + "epoch": 0.9661424813923555, + "grad_norm": 1.0582673159394054, + "learning_rate": 6.003451733175402e-08, + "loss": 0.7623, + "step": 10790 + }, + { + "epoch": 0.9662320219374335, + "grad_norm": 0.9099283361199353, + "learning_rate": 5.971761065406201e-08, + "loss": 0.8098, + "step": 10791 + }, + { + "epoch": 0.9663215624825117, + "grad_norm": 0.9406632993251882, + "learning_rate": 5.9401540120531674e-08, + "loss": 0.776, + "step": 10792 + }, + { + "epoch": 0.9664111030275897, + "grad_norm": 0.9518705821517812, + "learning_rate": 5.908630575774954e-08, + "loss": 0.7892, + "step": 10793 + }, + { + "epoch": 0.9665006435726677, + "grad_norm": 0.9996671578251665, + "learning_rate": 5.877190759223328e-08, + "loss": 0.8284, + "step": 10794 + }, + { + "epoch": 0.9665901841177458, + "grad_norm": 0.984071282205227, + "learning_rate": 5.8458345650429513e-08, + "loss": 0.7692, + "step": 10795 + }, + { + "epoch": 0.9666797246628239, + "grad_norm": 0.9322092240780453, + "learning_rate": 5.8145619958712704e-08, + "loss": 0.8146, + "step": 10796 + }, + { + "epoch": 0.966769265207902, + "grad_norm": 1.0359515777335124, + "learning_rate": 5.783373054338848e-08, + "loss": 0.8068, + "step": 10797 + }, + { + "epoch": 0.96685880575298, + "grad_norm": 0.9987766199450244, + "learning_rate": 5.7522677430691396e-08, + "loss": 0.807, + "step": 10798 + }, + { + "epoch": 0.966948346298058, + "grad_norm": 0.9553711570893652, + "learning_rate": 5.7212460646788314e-08, + "loss": 0.7175, + "step": 10799 + }, + { + "epoch": 0.9670378868431362, + "grad_norm": 0.9886142039827353, + "learning_rate": 5.69030802177728e-08, + "loss": 0.7791, + "step": 10800 + }, + { + "epoch": 0.9671274273882142, + "grad_norm": 0.9550426514146412, + "learning_rate": 5.659453616966737e-08, + "loss": 0.7917, + "step": 10801 + }, + { + "epoch": 0.9672169679332923, + "grad_norm": 1.0574861568027605, + "learning_rate": 5.628682852842793e-08, + "loss": 0.8289, + "step": 10802 + }, + { + "epoch": 0.9673065084783704, + "grad_norm": 1.0528018845226228, + "learning_rate": 5.5979957319935996e-08, + "loss": 0.7745, + "step": 10803 + }, + { + "epoch": 0.9673960490234484, + "grad_norm": 0.9371964017601132, + "learning_rate": 5.5673922570006475e-08, + "loss": 0.7556, + "step": 10804 + }, + { + "epoch": 0.9674855895685265, + "grad_norm": 0.970024857904332, + "learning_rate": 5.5368724304379896e-08, + "loss": 0.7752, + "step": 10805 + }, + { + "epoch": 0.9675751301136045, + "grad_norm": 0.9354010024366369, + "learning_rate": 5.506436254873016e-08, + "loss": 0.7994, + "step": 10806 + }, + { + "epoch": 0.9676646706586827, + "grad_norm": 1.114516516099089, + "learning_rate": 5.4760837328659e-08, + "loss": 0.7858, + "step": 10807 + }, + { + "epoch": 0.9677542112037607, + "grad_norm": 0.9980220188459672, + "learning_rate": 5.445814866969712e-08, + "loss": 0.7997, + "step": 10808 + }, + { + "epoch": 0.9678437517488387, + "grad_norm": 0.9904212513112618, + "learning_rate": 5.4156296597306366e-08, + "loss": 0.8071, + "step": 10809 + }, + { + "epoch": 0.9679332922939169, + "grad_norm": 1.0247963569767937, + "learning_rate": 5.385528113687755e-08, + "loss": 0.7907, + "step": 10810 + }, + { + "epoch": 0.9680228328389949, + "grad_norm": 0.8767082477989512, + "learning_rate": 5.35551023137304e-08, + "loss": 0.7996, + "step": 10811 + }, + { + "epoch": 0.968112373384073, + "grad_norm": 1.116565585243958, + "learning_rate": 5.325576015311584e-08, + "loss": 0.8162, + "step": 10812 + }, + { + "epoch": 0.968201913929151, + "grad_norm": 1.006974753004568, + "learning_rate": 5.295725468021373e-08, + "loss": 0.7997, + "step": 10813 + }, + { + "epoch": 0.9682914544742292, + "grad_norm": 1.0026658797022288, + "learning_rate": 5.2659585920131765e-08, + "loss": 0.813, + "step": 10814 + }, + { + "epoch": 0.9683809950193072, + "grad_norm": 0.903062581312795, + "learning_rate": 5.2362753897911015e-08, + "loss": 0.7584, + "step": 10815 + }, + { + "epoch": 0.9684705355643852, + "grad_norm": 1.011843672505144, + "learning_rate": 5.206675863851818e-08, + "loss": 0.8096, + "step": 10816 + }, + { + "epoch": 0.9685600761094633, + "grad_norm": 1.2486023911472193, + "learning_rate": 5.177160016685334e-08, + "loss": 0.7996, + "step": 10817 + }, + { + "epoch": 0.9686496166545414, + "grad_norm": 0.9954910158165448, + "learning_rate": 5.14772785077422e-08, + "loss": 0.8332, + "step": 10818 + }, + { + "epoch": 0.9687391571996194, + "grad_norm": 1.110040433154663, + "learning_rate": 5.118379368594384e-08, + "loss": 0.7948, + "step": 10819 + }, + { + "epoch": 0.9688286977446975, + "grad_norm": 1.429613524166745, + "learning_rate": 5.0891145726144066e-08, + "loss": 0.8149, + "step": 10820 + }, + { + "epoch": 0.9689182382897756, + "grad_norm": 0.9781741424716999, + "learning_rate": 5.0599334652959854e-08, + "loss": 0.8404, + "step": 10821 + }, + { + "epoch": 0.9690077788348537, + "grad_norm": 1.2503484822645612, + "learning_rate": 5.0308360490937125e-08, + "loss": 0.7868, + "step": 10822 + }, + { + "epoch": 0.9690973193799317, + "grad_norm": 1.277293310630612, + "learning_rate": 5.0018223264552967e-08, + "loss": 0.8009, + "step": 10823 + }, + { + "epoch": 0.9691868599250097, + "grad_norm": 1.1525367241737872, + "learning_rate": 4.972892299821119e-08, + "loss": 0.7799, + "step": 10824 + }, + { + "epoch": 0.9692764004700879, + "grad_norm": 0.9834685864305659, + "learning_rate": 4.944045971624678e-08, + "loss": 0.7469, + "step": 10825 + }, + { + "epoch": 0.9693659410151659, + "grad_norm": 1.1050614090312476, + "learning_rate": 4.9152833442925876e-08, + "loss": 0.8154, + "step": 10826 + }, + { + "epoch": 0.969455481560244, + "grad_norm": 1.0580024624141107, + "learning_rate": 4.886604420244245e-08, + "loss": 0.7871, + "step": 10827 + }, + { + "epoch": 0.9695450221053221, + "grad_norm": 0.9532963638373693, + "learning_rate": 4.8580092018918334e-08, + "loss": 0.7736, + "step": 10828 + }, + { + "epoch": 0.9696345626504002, + "grad_norm": 0.951326407840951, + "learning_rate": 4.829497691640872e-08, + "loss": 0.7833, + "step": 10829 + }, + { + "epoch": 0.9697241031954782, + "grad_norm": 0.9375876146204878, + "learning_rate": 4.8010698918895535e-08, + "loss": 0.7633, + "step": 10830 + }, + { + "epoch": 0.9698136437405562, + "grad_norm": 0.9351884901397687, + "learning_rate": 4.772725805029188e-08, + "loss": 0.8129, + "step": 10831 + }, + { + "epoch": 0.9699031842856344, + "grad_norm": 0.8931821379813093, + "learning_rate": 4.744465433443979e-08, + "loss": 0.7591, + "step": 10832 + }, + { + "epoch": 0.9699927248307124, + "grad_norm": 1.0224944716172502, + "learning_rate": 4.7162887795111353e-08, + "loss": 0.8174, + "step": 10833 + }, + { + "epoch": 0.9700822653757905, + "grad_norm": 1.8390359022996827, + "learning_rate": 4.688195845600763e-08, + "loss": 0.7824, + "step": 10834 + }, + { + "epoch": 0.9701718059208685, + "grad_norm": 1.0301385948422506, + "learning_rate": 4.660186634075858e-08, + "loss": 0.815, + "step": 10835 + }, + { + "epoch": 0.9702613464659466, + "grad_norm": 1.0445084759442553, + "learning_rate": 4.6322611472925383e-08, + "loss": 0.852, + "step": 10836 + }, + { + "epoch": 0.9703508870110247, + "grad_norm": 1.0145575960527322, + "learning_rate": 4.604419387599812e-08, + "loss": 0.7771, + "step": 10837 + }, + { + "epoch": 0.9704404275561027, + "grad_norm": 1.012950325419236, + "learning_rate": 4.5766613573396956e-08, + "loss": 0.8043, + "step": 10838 + }, + { + "epoch": 0.9705299681011809, + "grad_norm": 1.053777496774982, + "learning_rate": 4.548987058846988e-08, + "loss": 0.7762, + "step": 10839 + }, + { + "epoch": 0.9706195086462589, + "grad_norm": 0.9808388785012142, + "learning_rate": 4.521396494449604e-08, + "loss": 0.8047, + "step": 10840 + }, + { + "epoch": 0.9707090491913369, + "grad_norm": 0.9736352042078391, + "learning_rate": 4.493889666468354e-08, + "loss": 0.8456, + "step": 10841 + }, + { + "epoch": 0.970798589736415, + "grad_norm": 1.0525845701416303, + "learning_rate": 4.4664665772170547e-08, + "loss": 0.8311, + "step": 10842 + }, + { + "epoch": 0.9708881302814931, + "grad_norm": 1.0756805797050957, + "learning_rate": 4.439127229002416e-08, + "loss": 0.8258, + "step": 10843 + }, + { + "epoch": 0.9709776708265712, + "grad_norm": 0.93351865202235, + "learning_rate": 4.411871624124264e-08, + "loss": 0.7949, + "step": 10844 + }, + { + "epoch": 0.9710672113716492, + "grad_norm": 0.9888040629321048, + "learning_rate": 4.3846997648751e-08, + "loss": 0.7613, + "step": 10845 + }, + { + "epoch": 0.9711567519167273, + "grad_norm": 1.0388408064091816, + "learning_rate": 4.3576116535405387e-08, + "loss": 0.8137, + "step": 10846 + }, + { + "epoch": 0.9712462924618054, + "grad_norm": 1.1335329691142393, + "learning_rate": 4.3306072923990914e-08, + "loss": 0.8336, + "step": 10847 + }, + { + "epoch": 0.9713358330068834, + "grad_norm": 1.0229264833433342, + "learning_rate": 4.303686683722497e-08, + "loss": 0.8153, + "step": 10848 + }, + { + "epoch": 0.9714253735519615, + "grad_norm": 0.8987098264269682, + "learning_rate": 4.276849829775165e-08, + "loss": 0.8302, + "step": 10849 + }, + { + "epoch": 0.9715149140970396, + "grad_norm": 1.0170094464792827, + "learning_rate": 4.2500967328142904e-08, + "loss": 0.782, + "step": 10850 + }, + { + "epoch": 0.9716044546421176, + "grad_norm": 1.1266490167829915, + "learning_rate": 4.223427395090518e-08, + "loss": 0.7498, + "step": 10851 + }, + { + "epoch": 0.9716939951871957, + "grad_norm": 0.958345580669655, + "learning_rate": 4.1968418188470525e-08, + "loss": 0.8101, + "step": 10852 + }, + { + "epoch": 0.9717835357322737, + "grad_norm": 1.0599976204903112, + "learning_rate": 4.170340006320217e-08, + "loss": 0.8593, + "step": 10853 + }, + { + "epoch": 0.9718730762773519, + "grad_norm": 0.8819897464838972, + "learning_rate": 4.143921959739339e-08, + "loss": 0.8116, + "step": 10854 + }, + { + "epoch": 0.9719626168224299, + "grad_norm": 0.937699032394238, + "learning_rate": 4.1175876813265295e-08, + "loss": 0.7696, + "step": 10855 + }, + { + "epoch": 0.9720521573675079, + "grad_norm": 0.9799334135639653, + "learning_rate": 4.0913371732969055e-08, + "loss": 0.8072, + "step": 10856 + }, + { + "epoch": 0.9721416979125861, + "grad_norm": 0.9796239606188051, + "learning_rate": 4.065170437858701e-08, + "loss": 0.8262, + "step": 10857 + }, + { + "epoch": 0.9722312384576641, + "grad_norm": 1.0430276111872807, + "learning_rate": 4.0390874772128216e-08, + "loss": 0.821, + "step": 10858 + }, + { + "epoch": 0.9723207790027422, + "grad_norm": 1.0868197667135415, + "learning_rate": 4.0130882935532914e-08, + "loss": 0.7982, + "step": 10859 + }, + { + "epoch": 0.9724103195478202, + "grad_norm": 0.9526364002645701, + "learning_rate": 3.987172889067359e-08, + "loss": 0.7877, + "step": 10860 + }, + { + "epoch": 0.9724998600928983, + "grad_norm": 1.0347415758233793, + "learning_rate": 3.9613412659346154e-08, + "loss": 0.7985, + "step": 10861 + }, + { + "epoch": 0.9725894006379764, + "grad_norm": 0.9344835938203859, + "learning_rate": 3.935593426327988e-08, + "loss": 0.7868, + "step": 10862 + }, + { + "epoch": 0.9726789411830544, + "grad_norm": 1.110291548457916, + "learning_rate": 3.909929372413413e-08, + "loss": 0.8187, + "step": 10863 + }, + { + "epoch": 0.9727684817281326, + "grad_norm": 1.0301198424078752, + "learning_rate": 3.884349106349716e-08, + "loss": 0.8085, + "step": 10864 + }, + { + "epoch": 0.9728580222732106, + "grad_norm": 1.0098307129498267, + "learning_rate": 3.858852630288401e-08, + "loss": 0.8005, + "step": 10865 + }, + { + "epoch": 0.9729475628182886, + "grad_norm": 0.9335698018717342, + "learning_rate": 3.8334399463743063e-08, + "loss": 0.7949, + "step": 10866 + }, + { + "epoch": 0.9730371033633667, + "grad_norm": 1.0809478207144838, + "learning_rate": 3.808111056745056e-08, + "loss": 0.7716, + "step": 10867 + }, + { + "epoch": 0.9731266439084448, + "grad_norm": 1.0465248748184246, + "learning_rate": 3.7828659635311683e-08, + "loss": 0.799, + "step": 10868 + }, + { + "epoch": 0.9732161844535229, + "grad_norm": 0.8643911985209095, + "learning_rate": 3.7577046688562765e-08, + "loss": 0.7609, + "step": 10869 + }, + { + "epoch": 0.9733057249986009, + "grad_norm": 0.9826457685941364, + "learning_rate": 3.7326271748368005e-08, + "loss": 0.8705, + "step": 10870 + }, + { + "epoch": 0.973395265543679, + "grad_norm": 0.9156518439591341, + "learning_rate": 3.707633483582163e-08, + "loss": 0.7889, + "step": 10871 + }, + { + "epoch": 0.9734848060887571, + "grad_norm": 0.9564442721887093, + "learning_rate": 3.682723597194793e-08, + "loss": 0.7797, + "step": 10872 + }, + { + "epoch": 0.9735743466338351, + "grad_norm": 0.9847541797183128, + "learning_rate": 3.657897517770015e-08, + "loss": 0.8664, + "step": 10873 + }, + { + "epoch": 0.9736638871789132, + "grad_norm": 1.092664361711944, + "learning_rate": 3.6331552473960475e-08, + "loss": 0.7621, + "step": 10874 + }, + { + "epoch": 0.9737534277239913, + "grad_norm": 1.0380940451746594, + "learning_rate": 3.6084967881542255e-08, + "loss": 0.7994, + "step": 10875 + }, + { + "epoch": 0.9738429682690694, + "grad_norm": 0.9540290425948933, + "learning_rate": 3.5839221421187783e-08, + "loss": 0.7876, + "step": 10876 + }, + { + "epoch": 0.9739325088141474, + "grad_norm": 0.9305595497566058, + "learning_rate": 3.5594313113567204e-08, + "loss": 0.7615, + "step": 10877 + }, + { + "epoch": 0.9740220493592254, + "grad_norm": 0.9612148170748019, + "learning_rate": 3.53502429792818e-08, + "loss": 0.7715, + "step": 10878 + }, + { + "epoch": 0.9741115899043036, + "grad_norm": 1.060420905037074, + "learning_rate": 3.510701103886183e-08, + "loss": 0.8097, + "step": 10879 + }, + { + "epoch": 0.9742011304493816, + "grad_norm": 0.9248796308503917, + "learning_rate": 3.486461731276869e-08, + "loss": 0.7496, + "step": 10880 + }, + { + "epoch": 0.9742906709944597, + "grad_norm": 1.0252440774836882, + "learning_rate": 3.4623061821389417e-08, + "loss": 0.8469, + "step": 10881 + }, + { + "epoch": 0.9743802115395378, + "grad_norm": 1.128621839803474, + "learning_rate": 3.438234458504441e-08, + "loss": 0.815, + "step": 10882 + }, + { + "epoch": 0.9744697520846158, + "grad_norm": 0.931926578307456, + "learning_rate": 3.4142465623980825e-08, + "loss": 0.7584, + "step": 10883 + }, + { + "epoch": 0.9745592926296939, + "grad_norm": 0.9220423625907225, + "learning_rate": 3.390342495837806e-08, + "loss": 0.7887, + "step": 10884 + }, + { + "epoch": 0.9746488331747719, + "grad_norm": 0.8478271567160813, + "learning_rate": 3.366522260834226e-08, + "loss": 0.7425, + "step": 10885 + }, + { + "epoch": 0.9747383737198501, + "grad_norm": 0.9860442092337542, + "learning_rate": 3.342785859391073e-08, + "loss": 0.788, + "step": 10886 + }, + { + "epoch": 0.9748279142649281, + "grad_norm": 1.0907144225169243, + "learning_rate": 3.3191332935050837e-08, + "loss": 0.7783, + "step": 10887 + }, + { + "epoch": 0.9749174548100061, + "grad_norm": 1.0742627107821257, + "learning_rate": 3.2955645651655544e-08, + "loss": 0.8355, + "step": 10888 + }, + { + "epoch": 0.9750069953550842, + "grad_norm": 1.0046721141989614, + "learning_rate": 3.272079676355233e-08, + "loss": 0.8343, + "step": 10889 + }, + { + "epoch": 0.9750965359001623, + "grad_norm": 1.020325117524468, + "learning_rate": 3.2486786290494287e-08, + "loss": 0.7647, + "step": 10890 + }, + { + "epoch": 0.9751860764452404, + "grad_norm": 0.897369159065843, + "learning_rate": 3.2253614252167884e-08, + "loss": 0.797, + "step": 10891 + }, + { + "epoch": 0.9752756169903184, + "grad_norm": 0.9703177332404401, + "learning_rate": 3.202128066818522e-08, + "loss": 0.7985, + "step": 10892 + }, + { + "epoch": 0.9753651575353965, + "grad_norm": 1.0692641174684516, + "learning_rate": 3.178978555808954e-08, + "loss": 0.788, + "step": 10893 + }, + { + "epoch": 0.9754546980804746, + "grad_norm": 1.0525563316038185, + "learning_rate": 3.155912894135304e-08, + "loss": 0.8774, + "step": 10894 + }, + { + "epoch": 0.9755442386255526, + "grad_norm": 1.0532747830822367, + "learning_rate": 3.132931083737911e-08, + "loss": 0.8092, + "step": 10895 + }, + { + "epoch": 0.9756337791706307, + "grad_norm": 1.0268324065995567, + "learning_rate": 3.110033126549894e-08, + "loss": 0.8093, + "step": 10896 + }, + { + "epoch": 0.9757233197157088, + "grad_norm": 0.9689220458155984, + "learning_rate": 3.0872190244972676e-08, + "loss": 0.81, + "step": 10897 + }, + { + "epoch": 0.9758128602607868, + "grad_norm": 0.8758630710981218, + "learning_rate": 3.064488779499164e-08, + "loss": 0.7614, + "step": 10898 + }, + { + "epoch": 0.9759024008058649, + "grad_norm": 0.942146098434114, + "learning_rate": 3.041842393467609e-08, + "loss": 0.7905, + "step": 10899 + }, + { + "epoch": 0.975991941350943, + "grad_norm": 0.8864566659068037, + "learning_rate": 3.019279868307412e-08, + "loss": 0.7726, + "step": 10900 + }, + { + "epoch": 0.9760814818960211, + "grad_norm": 1.0591996455307302, + "learning_rate": 2.9968012059163886e-08, + "loss": 0.7742, + "step": 10901 + }, + { + "epoch": 0.9761710224410991, + "grad_norm": 0.8732837357472804, + "learning_rate": 2.974406408185693e-08, + "loss": 0.7276, + "step": 10902 + }, + { + "epoch": 0.9762605629861771, + "grad_norm": 0.9759263803764883, + "learning_rate": 2.9520954769988176e-08, + "loss": 0.8225, + "step": 10903 + }, + { + "epoch": 0.9763501035312553, + "grad_norm": 1.0239633000084492, + "learning_rate": 2.929868414232706e-08, + "loss": 0.7708, + "step": 10904 + }, + { + "epoch": 0.9764396440763333, + "grad_norm": 1.0095945091621976, + "learning_rate": 2.907725221756863e-08, + "loss": 0.7987, + "step": 10905 + }, + { + "epoch": 0.9765291846214114, + "grad_norm": 1.0287527367881886, + "learning_rate": 2.8856659014339095e-08, + "loss": 0.8576, + "step": 10906 + }, + { + "epoch": 0.9766187251664894, + "grad_norm": 1.0216037843003316, + "learning_rate": 2.863690455119361e-08, + "loss": 0.8174, + "step": 10907 + }, + { + "epoch": 0.9767082657115675, + "grad_norm": 1.0253402093837434, + "learning_rate": 2.8417988846619615e-08, + "loss": 0.81, + "step": 10908 + }, + { + "epoch": 0.9767978062566456, + "grad_norm": 1.1188792402825865, + "learning_rate": 2.8199911919029043e-08, + "loss": 0.8397, + "step": 10909 + }, + { + "epoch": 0.9768873468017236, + "grad_norm": 0.8724473692947046, + "learning_rate": 2.7982673786767223e-08, + "loss": 0.7583, + "step": 10910 + }, + { + "epoch": 0.9769768873468018, + "grad_norm": 0.9281583561583105, + "learning_rate": 2.7766274468106204e-08, + "loss": 0.8535, + "step": 10911 + }, + { + "epoch": 0.9770664278918798, + "grad_norm": 0.9084828165092352, + "learning_rate": 2.755071398125031e-08, + "loss": 0.7961, + "step": 10912 + }, + { + "epoch": 0.9771559684369578, + "grad_norm": 1.1263858022417552, + "learning_rate": 2.7335992344330597e-08, + "loss": 0.7653, + "step": 10913 + }, + { + "epoch": 0.9772455089820359, + "grad_norm": 1.1099044673229395, + "learning_rate": 2.7122109575410393e-08, + "loss": 0.8113, + "step": 10914 + }, + { + "epoch": 0.977335049527114, + "grad_norm": 1.0294592583817066, + "learning_rate": 2.690906569247864e-08, + "loss": 0.7801, + "step": 10915 + }, + { + "epoch": 0.9774245900721921, + "grad_norm": 0.9644686802549949, + "learning_rate": 2.6696860713457674e-08, + "loss": 0.8051, + "step": 10916 + }, + { + "epoch": 0.9775141306172701, + "grad_norm": 1.0222813314860248, + "learning_rate": 2.6485494656195432e-08, + "loss": 0.7773, + "step": 10917 + }, + { + "epoch": 0.9776036711623483, + "grad_norm": 1.1636561975875346, + "learning_rate": 2.6274967538473252e-08, + "loss": 0.7945, + "step": 10918 + }, + { + "epoch": 0.9776932117074263, + "grad_norm": 0.9736701299019339, + "learning_rate": 2.6065279378000296e-08, + "loss": 0.7824, + "step": 10919 + }, + { + "epoch": 0.9777827522525043, + "grad_norm": 0.9747604071312382, + "learning_rate": 2.5856430192413574e-08, + "loss": 0.8019, + "step": 10920 + }, + { + "epoch": 0.9778722927975824, + "grad_norm": 0.9109892000822356, + "learning_rate": 2.564841999928014e-08, + "loss": 0.816, + "step": 10921 + }, + { + "epoch": 0.9779618333426605, + "grad_norm": 1.0705611436158202, + "learning_rate": 2.544124881609933e-08, + "loss": 0.7476, + "step": 10922 + }, + { + "epoch": 0.9780513738877386, + "grad_norm": 1.020725733439833, + "learning_rate": 2.5234916660296094e-08, + "loss": 0.8691, + "step": 10923 + }, + { + "epoch": 0.9781409144328166, + "grad_norm": 0.9705013988332137, + "learning_rate": 2.502942354922655e-08, + "loss": 0.7698, + "step": 10924 + }, + { + "epoch": 0.9782304549778946, + "grad_norm": 0.9258290911143892, + "learning_rate": 2.482476950017576e-08, + "loss": 0.7358, + "step": 10925 + }, + { + "epoch": 0.9783199955229728, + "grad_norm": 0.9699969233202095, + "learning_rate": 2.4620954530361062e-08, + "loss": 0.7877, + "step": 10926 + }, + { + "epoch": 0.9784095360680508, + "grad_norm": 1.0396309005777478, + "learning_rate": 2.44179786569243e-08, + "loss": 0.8202, + "step": 10927 + }, + { + "epoch": 0.9784990766131288, + "grad_norm": 1.0580992920994223, + "learning_rate": 2.4215841896938486e-08, + "loss": 0.7709, + "step": 10928 + }, + { + "epoch": 0.978588617158207, + "grad_norm": 0.9894416669961281, + "learning_rate": 2.40145442674089e-08, + "loss": 0.829, + "step": 10929 + }, + { + "epoch": 0.978678157703285, + "grad_norm": 1.3381440525317723, + "learning_rate": 2.381408578526756e-08, + "loss": 0.7512, + "step": 10930 + }, + { + "epoch": 0.9787676982483631, + "grad_norm": 1.068536036442939, + "learning_rate": 2.361446646737431e-08, + "loss": 0.8112, + "step": 10931 + }, + { + "epoch": 0.9788572387934411, + "grad_norm": 0.986426829083777, + "learning_rate": 2.341568633052349e-08, + "loss": 0.8148, + "step": 10932 + }, + { + "epoch": 0.9789467793385193, + "grad_norm": 0.9552644367163482, + "learning_rate": 2.3217745391433954e-08, + "loss": 0.8852, + "step": 10933 + }, + { + "epoch": 0.9790363198835973, + "grad_norm": 0.970275697693054, + "learning_rate": 2.3020643666756824e-08, + "loss": 0.7448, + "step": 10934 + }, + { + "epoch": 0.9791258604286753, + "grad_norm": 0.9967750359043535, + "learning_rate": 2.2824381173069953e-08, + "loss": 0.7869, + "step": 10935 + }, + { + "epoch": 0.9792154009737535, + "grad_norm": 0.9664024954562596, + "learning_rate": 2.2628957926884576e-08, + "loss": 0.8052, + "step": 10936 + }, + { + "epoch": 0.9793049415188315, + "grad_norm": 1.1131865925126674, + "learning_rate": 2.2434373944637544e-08, + "loss": 0.8333, + "step": 10937 + }, + { + "epoch": 0.9793944820639096, + "grad_norm": 1.0452815764423837, + "learning_rate": 2.2240629242696878e-08, + "loss": 0.7916, + "step": 10938 + }, + { + "epoch": 0.9794840226089876, + "grad_norm": 1.0587639729220244, + "learning_rate": 2.2047723837359538e-08, + "loss": 0.8147, + "step": 10939 + }, + { + "epoch": 0.9795735631540657, + "grad_norm": 1.035995143617918, + "learning_rate": 2.1855657744853653e-08, + "loss": 0.7835, + "step": 10940 + }, + { + "epoch": 0.9796631036991438, + "grad_norm": 1.0640113398286637, + "learning_rate": 2.1664430981332972e-08, + "loss": 0.8035, + "step": 10941 + }, + { + "epoch": 0.9797526442442218, + "grad_norm": 0.9788596806174482, + "learning_rate": 2.147404356288463e-08, + "loss": 0.8305, + "step": 10942 + }, + { + "epoch": 0.9798421847892999, + "grad_norm": 1.1431515022476078, + "learning_rate": 2.1284495505521362e-08, + "loss": 0.8701, + "step": 10943 + }, + { + "epoch": 0.979931725334378, + "grad_norm": 0.9199979162908835, + "learning_rate": 2.1095786825190423e-08, + "loss": 0.8364, + "step": 10944 + }, + { + "epoch": 0.980021265879456, + "grad_norm": 1.0763467704641456, + "learning_rate": 2.0907917537762446e-08, + "loss": 0.7866, + "step": 10945 + }, + { + "epoch": 0.9801108064245341, + "grad_norm": 1.0164574572704694, + "learning_rate": 2.0720887659041457e-08, + "loss": 0.8108, + "step": 10946 + }, + { + "epoch": 0.9802003469696122, + "grad_norm": 0.9682160783684138, + "learning_rate": 2.0534697204761534e-08, + "loss": 0.8189, + "step": 10947 + }, + { + "epoch": 0.9802898875146903, + "grad_norm": 1.0125320763172467, + "learning_rate": 2.0349346190581265e-08, + "loss": 0.7439, + "step": 10948 + }, + { + "epoch": 0.9803794280597683, + "grad_norm": 0.9276760062447196, + "learning_rate": 2.0164834632092622e-08, + "loss": 0.8046, + "step": 10949 + }, + { + "epoch": 0.9804689686048463, + "grad_norm": 1.1083794236571993, + "learning_rate": 1.9981162544817634e-08, + "loss": 0.7891, + "step": 10950 + }, + { + "epoch": 0.9805585091499245, + "grad_norm": 0.9256740873449438, + "learning_rate": 1.9798329944206164e-08, + "loss": 0.773, + "step": 10951 + }, + { + "epoch": 0.9806480496950025, + "grad_norm": 1.031328111929455, + "learning_rate": 1.961633684563591e-08, + "loss": 0.8109, + "step": 10952 + }, + { + "epoch": 0.9807375902400806, + "grad_norm": 1.0534182157455327, + "learning_rate": 1.9435183264415734e-08, + "loss": 0.8458, + "step": 10953 + }, + { + "epoch": 0.9808271307851587, + "grad_norm": 0.9323390261957298, + "learning_rate": 1.9254869215785677e-08, + "loss": 0.8113, + "step": 10954 + }, + { + "epoch": 0.9809166713302367, + "grad_norm": 0.9485777404632014, + "learning_rate": 1.9075394714910267e-08, + "loss": 0.8016, + "step": 10955 + }, + { + "epoch": 0.9810062118753148, + "grad_norm": 1.4360089363589001, + "learning_rate": 1.889675977688854e-08, + "loss": 0.7844, + "step": 10956 + }, + { + "epoch": 0.9810957524203928, + "grad_norm": 0.9874012611705577, + "learning_rate": 1.8718964416745146e-08, + "loss": 0.8294, + "step": 10957 + }, + { + "epoch": 0.981185292965471, + "grad_norm": 0.9785488442259475, + "learning_rate": 1.8542008649437003e-08, + "loss": 0.8114, + "step": 10958 + }, + { + "epoch": 0.981274833510549, + "grad_norm": 0.9000012868210979, + "learning_rate": 1.836589248984888e-08, + "loss": 0.7877, + "step": 10959 + }, + { + "epoch": 0.981364374055627, + "grad_norm": 1.1160896065277681, + "learning_rate": 1.8190615952794477e-08, + "loss": 0.822, + "step": 10960 + }, + { + "epoch": 0.9814539146007051, + "grad_norm": 0.9216385427260639, + "learning_rate": 1.8016179053016445e-08, + "loss": 0.7525, + "step": 10961 + }, + { + "epoch": 0.9815434551457832, + "grad_norm": 0.9361958883370017, + "learning_rate": 1.784258180519083e-08, + "loss": 0.7798, + "step": 10962 + }, + { + "epoch": 0.9816329956908613, + "grad_norm": 1.017260121657136, + "learning_rate": 1.7669824223917053e-08, + "loss": 0.8268, + "step": 10963 + }, + { + "epoch": 0.9817225362359393, + "grad_norm": 1.0557202173605085, + "learning_rate": 1.7497906323729053e-08, + "loss": 0.8136, + "step": 10964 + }, + { + "epoch": 0.9818120767810175, + "grad_norm": 1.0288222428077731, + "learning_rate": 1.732682811908748e-08, + "loss": 0.8305, + "step": 10965 + }, + { + "epoch": 0.9819016173260955, + "grad_norm": 1.1262011212845917, + "learning_rate": 1.7156589624381937e-08, + "loss": 0.769, + "step": 10966 + }, + { + "epoch": 0.9819911578711735, + "grad_norm": 0.9815835051855141, + "learning_rate": 1.698719085393208e-08, + "loss": 0.7982, + "step": 10967 + }, + { + "epoch": 0.9820806984162516, + "grad_norm": 1.0941168022296672, + "learning_rate": 1.681863182198984e-08, + "loss": 0.8283, + "step": 10968 + }, + { + "epoch": 0.9821702389613297, + "grad_norm": 0.9535843934831546, + "learning_rate": 1.6650912542730547e-08, + "loss": 0.8017, + "step": 10969 + }, + { + "epoch": 0.9822597795064077, + "grad_norm": 0.9622204618916594, + "learning_rate": 1.6484033030265134e-08, + "loss": 0.7836, + "step": 10970 + }, + { + "epoch": 0.9823493200514858, + "grad_norm": 0.9507054811883398, + "learning_rate": 1.6317993298627933e-08, + "loss": 0.8457, + "step": 10971 + }, + { + "epoch": 0.9824388605965639, + "grad_norm": 0.9272066635170336, + "learning_rate": 1.6152793361788877e-08, + "loss": 0.762, + "step": 10972 + }, + { + "epoch": 0.982528401141642, + "grad_norm": 0.9770987698433586, + "learning_rate": 1.59884332336413e-08, + "loss": 0.813, + "step": 10973 + }, + { + "epoch": 0.98261794168672, + "grad_norm": 1.1171921762524795, + "learning_rate": 1.5824912928011914e-08, + "loss": 0.7917, + "step": 10974 + }, + { + "epoch": 0.982707482231798, + "grad_norm": 0.9544845724412198, + "learning_rate": 1.566223245865528e-08, + "loss": 0.8596, + "step": 10975 + }, + { + "epoch": 0.9827970227768762, + "grad_norm": 1.3158842504284802, + "learning_rate": 1.5500391839256002e-08, + "loss": 0.812, + "step": 10976 + }, + { + "epoch": 0.9828865633219542, + "grad_norm": 0.8741930793865039, + "learning_rate": 1.5339391083427635e-08, + "loss": 0.7926, + "step": 10977 + }, + { + "epoch": 0.9829761038670323, + "grad_norm": 0.9067389175997302, + "learning_rate": 1.517923020471268e-08, + "loss": 0.7931, + "step": 10978 + }, + { + "epoch": 0.9830656444121103, + "grad_norm": 0.9217560976770917, + "learning_rate": 1.5019909216582585e-08, + "loss": 0.8444, + "step": 10979 + }, + { + "epoch": 0.9831551849571885, + "grad_norm": 1.0479441396390379, + "learning_rate": 1.486142813243996e-08, + "loss": 0.7898, + "step": 10980 + }, + { + "epoch": 0.9832447255022665, + "grad_norm": 1.028276892511461, + "learning_rate": 1.4703786965615252e-08, + "loss": 0.7937, + "step": 10981 + }, + { + "epoch": 0.9833342660473445, + "grad_norm": 0.985480121205418, + "learning_rate": 1.4546985729368968e-08, + "loss": 0.7807, + "step": 10982 + }, + { + "epoch": 0.9834238065924227, + "grad_norm": 0.9822224671535137, + "learning_rate": 1.4391024436890555e-08, + "loss": 0.8421, + "step": 10983 + }, + { + "epoch": 0.9835133471375007, + "grad_norm": 0.9526151762628563, + "learning_rate": 1.423590310129841e-08, + "loss": 0.7936, + "step": 10984 + }, + { + "epoch": 0.9836028876825788, + "grad_norm": 0.9431625456922188, + "learning_rate": 1.4081621735642093e-08, + "loss": 0.8225, + "step": 10985 + }, + { + "epoch": 0.9836924282276568, + "grad_norm": 1.111826916103104, + "learning_rate": 1.3928180352899001e-08, + "loss": 0.8651, + "step": 10986 + }, + { + "epoch": 0.9837819687727349, + "grad_norm": 0.8751763648724818, + "learning_rate": 1.3775578965975477e-08, + "loss": 0.7704, + "step": 10987 + }, + { + "epoch": 0.983871509317813, + "grad_norm": 0.9597224539181783, + "learning_rate": 1.3623817587707922e-08, + "loss": 0.7981, + "step": 10988 + }, + { + "epoch": 0.983961049862891, + "grad_norm": 1.0562373323568417, + "learning_rate": 1.3472896230861676e-08, + "loss": 0.7977, + "step": 10989 + }, + { + "epoch": 0.9840505904079692, + "grad_norm": 0.978583733833062, + "learning_rate": 1.3322814908133252e-08, + "loss": 0.7609, + "step": 10990 + }, + { + "epoch": 0.9841401309530472, + "grad_norm": 0.9274077148424624, + "learning_rate": 1.3173573632144775e-08, + "loss": 0.7867, + "step": 10991 + }, + { + "epoch": 0.9842296714981252, + "grad_norm": 0.9484605628557444, + "learning_rate": 1.3025172415451758e-08, + "loss": 0.8194, + "step": 10992 + }, + { + "epoch": 0.9843192120432033, + "grad_norm": 1.0130882956670826, + "learning_rate": 1.2877611270537549e-08, + "loss": 0.8207, + "step": 10993 + }, + { + "epoch": 0.9844087525882814, + "grad_norm": 0.995597020613136, + "learning_rate": 1.273089020981222e-08, + "loss": 0.7757, + "step": 10994 + }, + { + "epoch": 0.9844982931333595, + "grad_norm": 0.906379058666672, + "learning_rate": 1.2585009245620339e-08, + "loss": 0.7423, + "step": 10995 + }, + { + "epoch": 0.9845878336784375, + "grad_norm": 0.9850607950800196, + "learning_rate": 1.2439968390229873e-08, + "loss": 0.7973, + "step": 10996 + }, + { + "epoch": 0.9846773742235155, + "grad_norm": 1.080642028153105, + "learning_rate": 1.2295767655844393e-08, + "loss": 0.7988, + "step": 10997 + }, + { + "epoch": 0.9847669147685937, + "grad_norm": 0.9862044383105814, + "learning_rate": 1.2152407054590864e-08, + "loss": 0.8188, + "step": 10998 + }, + { + "epoch": 0.9848564553136717, + "grad_norm": 1.0068202491803395, + "learning_rate": 1.2009886598529642e-08, + "loss": 0.7911, + "step": 10999 + }, + { + "epoch": 0.9849459958587498, + "grad_norm": 1.122672060710015, + "learning_rate": 1.186820629964891e-08, + "loss": 0.8394, + "step": 11000 + }, + { + "epoch": 0.9850355364038279, + "grad_norm": 1.045875661063741, + "learning_rate": 1.1727366169865806e-08, + "loss": 0.8245, + "step": 11001 + }, + { + "epoch": 0.9851250769489059, + "grad_norm": 1.0684597219690246, + "learning_rate": 1.158736622102863e-08, + "loss": 0.8683, + "step": 11002 + }, + { + "epoch": 0.985214617493984, + "grad_norm": 1.0515237779637685, + "learning_rate": 1.1448206464912404e-08, + "loss": 0.8061, + "step": 11003 + }, + { + "epoch": 0.985304158039062, + "grad_norm": 1.0071626301247134, + "learning_rate": 1.1309886913223323e-08, + "loss": 0.7743, + "step": 11004 + }, + { + "epoch": 0.9853936985841402, + "grad_norm": 0.9356441718381159, + "learning_rate": 1.1172407577596523e-08, + "loss": 0.8001, + "step": 11005 + }, + { + "epoch": 0.9854832391292182, + "grad_norm": 1.0623259826415612, + "learning_rate": 1.1035768469596086e-08, + "loss": 0.8388, + "step": 11006 + }, + { + "epoch": 0.9855727796742962, + "grad_norm": 0.9092533712444809, + "learning_rate": 1.0899969600716153e-08, + "loss": 0.7985, + "step": 11007 + }, + { + "epoch": 0.9856623202193744, + "grad_norm": 0.9817629691734051, + "learning_rate": 1.0765010982378698e-08, + "loss": 0.7738, + "step": 11008 + }, + { + "epoch": 0.9857518607644524, + "grad_norm": 0.9809402057490023, + "learning_rate": 1.0630892625936862e-08, + "loss": 0.7879, + "step": 11009 + }, + { + "epoch": 0.9858414013095305, + "grad_norm": 0.9899907416098209, + "learning_rate": 1.049761454267162e-08, + "loss": 0.7767, + "step": 11010 + }, + { + "epoch": 0.9859309418546085, + "grad_norm": 0.9907172123871733, + "learning_rate": 1.0365176743795113e-08, + "loss": 0.7578, + "step": 11011 + }, + { + "epoch": 0.9860204823996866, + "grad_norm": 1.052098009341602, + "learning_rate": 1.0233579240446213e-08, + "loss": 0.7909, + "step": 11012 + }, + { + "epoch": 0.9861100229447647, + "grad_norm": 1.05610311290053, + "learning_rate": 1.0102822043694948e-08, + "loss": 0.8376, + "step": 11013 + }, + { + "epoch": 0.9861995634898427, + "grad_norm": 0.9242004720657334, + "learning_rate": 9.972905164539193e-09, + "loss": 0.7879, + "step": 11014 + }, + { + "epoch": 0.9862891040349208, + "grad_norm": 1.0161138754084202, + "learning_rate": 9.84382861390909e-09, + "loss": 0.7602, + "step": 11015 + }, + { + "epoch": 0.9863786445799989, + "grad_norm": 1.0374981083068733, + "learning_rate": 9.715592402660401e-09, + "loss": 0.7592, + "step": 11016 + }, + { + "epoch": 0.986468185125077, + "grad_norm": 0.9025882924506432, + "learning_rate": 9.588196541582273e-09, + "loss": 0.7758, + "step": 11017 + }, + { + "epoch": 0.986557725670155, + "grad_norm": 0.938375491987435, + "learning_rate": 9.461641041388358e-09, + "loss": 0.7818, + "step": 11018 + }, + { + "epoch": 0.9866472662152331, + "grad_norm": 1.0676738386003928, + "learning_rate": 9.335925912724587e-09, + "loss": 0.8026, + "step": 11019 + }, + { + "epoch": 0.9867368067603112, + "grad_norm": 1.028499195631394, + "learning_rate": 9.21105116616583e-09, + "loss": 0.766, + "step": 11020 + }, + { + "epoch": 0.9868263473053892, + "grad_norm": 0.9882958018704673, + "learning_rate": 9.08701681221702e-09, + "loss": 0.8672, + "step": 11021 + }, + { + "epoch": 0.9869158878504672, + "grad_norm": 1.0071212069310187, + "learning_rate": 8.963822861310923e-09, + "loss": 0.839, + "step": 11022 + }, + { + "epoch": 0.9870054283955454, + "grad_norm": 0.8846753898922584, + "learning_rate": 8.84146932381036e-09, + "loss": 0.7407, + "step": 11023 + }, + { + "epoch": 0.9870949689406234, + "grad_norm": 1.033192646202552, + "learning_rate": 8.719956210007096e-09, + "loss": 0.7839, + "step": 11024 + }, + { + "epoch": 0.9871845094857015, + "grad_norm": 0.9907469946929138, + "learning_rate": 8.599283530122959e-09, + "loss": 0.7854, + "step": 11025 + }, + { + "epoch": 0.9872740500307796, + "grad_norm": 0.9497709036072383, + "learning_rate": 8.479451294307605e-09, + "loss": 0.7756, + "step": 11026 + }, + { + "epoch": 0.9873635905758577, + "grad_norm": 1.190187552531041, + "learning_rate": 8.36045951264075e-09, + "loss": 0.8271, + "step": 11027 + }, + { + "epoch": 0.9874531311209357, + "grad_norm": 1.014434213549999, + "learning_rate": 8.242308195133276e-09, + "loss": 0.805, + "step": 11028 + }, + { + "epoch": 0.9875426716660137, + "grad_norm": 0.9848531631454394, + "learning_rate": 8.124997351721675e-09, + "loss": 0.7877, + "step": 11029 + }, + { + "epoch": 0.9876322122110919, + "grad_norm": 0.947036178356658, + "learning_rate": 8.008526992275834e-09, + "loss": 0.7691, + "step": 11030 + }, + { + "epoch": 0.9877217527561699, + "grad_norm": 1.1101027349334025, + "learning_rate": 7.892897126591248e-09, + "loss": 0.8159, + "step": 11031 + }, + { + "epoch": 0.987811293301248, + "grad_norm": 0.9590515781520789, + "learning_rate": 7.778107764394583e-09, + "loss": 0.8027, + "step": 11032 + }, + { + "epoch": 0.987900833846326, + "grad_norm": 0.8690743994982413, + "learning_rate": 7.664158915341447e-09, + "loss": 0.7356, + "step": 11033 + }, + { + "epoch": 0.9879903743914041, + "grad_norm": 1.0441380654827883, + "learning_rate": 7.551050589018615e-09, + "loss": 0.8266, + "step": 11034 + }, + { + "epoch": 0.9880799149364822, + "grad_norm": 0.9789549264263988, + "learning_rate": 7.438782794937372e-09, + "loss": 0.8313, + "step": 11035 + }, + { + "epoch": 0.9881694554815602, + "grad_norm": 0.9667267313438569, + "learning_rate": 7.3273555425446005e-09, + "loss": 0.8483, + "step": 11036 + }, + { + "epoch": 0.9882589960266384, + "grad_norm": 1.0290506040242104, + "learning_rate": 7.2167688412105866e-09, + "loss": 0.7858, + "step": 11037 + }, + { + "epoch": 0.9883485365717164, + "grad_norm": 0.9357993059290411, + "learning_rate": 7.1070227002378866e-09, + "loss": 0.8057, + "step": 11038 + }, + { + "epoch": 0.9884380771167944, + "grad_norm": 1.103289364350727, + "learning_rate": 6.9981171288591166e-09, + "loss": 0.7493, + "step": 11039 + }, + { + "epoch": 0.9885276176618725, + "grad_norm": 1.0283976445185, + "learning_rate": 6.890052136234726e-09, + "loss": 0.7768, + "step": 11040 + }, + { + "epoch": 0.9886171582069506, + "grad_norm": 0.9804534903792114, + "learning_rate": 6.782827731454111e-09, + "loss": 0.7871, + "step": 11041 + }, + { + "epoch": 0.9887066987520287, + "grad_norm": 1.0133677661855653, + "learning_rate": 6.676443923537834e-09, + "loss": 0.7603, + "step": 11042 + }, + { + "epoch": 0.9887962392971067, + "grad_norm": 1.0599518658517826, + "learning_rate": 6.570900721433182e-09, + "loss": 0.8447, + "step": 11043 + }, + { + "epoch": 0.9888857798421848, + "grad_norm": 1.2534355531964176, + "learning_rate": 6.4661981340186084e-09, + "loss": 0.7948, + "step": 11044 + }, + { + "epoch": 0.9889753203872629, + "grad_norm": 0.9236856424709777, + "learning_rate": 6.362336170101513e-09, + "loss": 0.7322, + "step": 11045 + }, + { + "epoch": 0.9890648609323409, + "grad_norm": 1.0136713322581734, + "learning_rate": 6.25931483841935e-09, + "loss": 0.8319, + "step": 11046 + }, + { + "epoch": 0.989154401477419, + "grad_norm": 0.9263162870994055, + "learning_rate": 6.1571341476363015e-09, + "loss": 0.774, + "step": 11047 + }, + { + "epoch": 0.9892439420224971, + "grad_norm": 0.9335953513451672, + "learning_rate": 6.055794106347712e-09, + "loss": 0.7666, + "step": 11048 + }, + { + "epoch": 0.9893334825675751, + "grad_norm": 0.8718038630342524, + "learning_rate": 5.955294723078986e-09, + "loss": 0.8128, + "step": 11049 + }, + { + "epoch": 0.9894230231126532, + "grad_norm": 0.9155980273481104, + "learning_rate": 5.855636006283361e-09, + "loss": 0.786, + "step": 11050 + }, + { + "epoch": 0.9895125636577312, + "grad_norm": 0.9673132635230739, + "learning_rate": 5.75681796434302e-09, + "loss": 0.76, + "step": 11051 + }, + { + "epoch": 0.9896021042028094, + "grad_norm": 0.99450892025568, + "learning_rate": 5.658840605571314e-09, + "loss": 0.8249, + "step": 11052 + }, + { + "epoch": 0.9896916447478874, + "grad_norm": 1.0005564840208243, + "learning_rate": 5.561703938209428e-09, + "loss": 0.7443, + "step": 11053 + }, + { + "epoch": 0.9897811852929654, + "grad_norm": 1.0537643935337768, + "learning_rate": 5.465407970427494e-09, + "loss": 0.7743, + "step": 11054 + }, + { + "epoch": 0.9898707258380436, + "grad_norm": 1.017756464734135, + "learning_rate": 5.369952710326809e-09, + "loss": 0.8119, + "step": 11055 + }, + { + "epoch": 0.9899602663831216, + "grad_norm": 1.0396235978246284, + "learning_rate": 5.275338165935395e-09, + "loss": 0.7512, + "step": 11056 + }, + { + "epoch": 0.9900498069281997, + "grad_norm": 0.9727641961020701, + "learning_rate": 5.181564345213552e-09, + "loss": 0.7493, + "step": 11057 + }, + { + "epoch": 0.9901393474732777, + "grad_norm": 1.1660452734640803, + "learning_rate": 5.088631256048304e-09, + "loss": 0.7364, + "step": 11058 + }, + { + "epoch": 0.9902288880183558, + "grad_norm": 0.9565587855601493, + "learning_rate": 4.9965389062567316e-09, + "loss": 0.7848, + "step": 11059 + }, + { + "epoch": 0.9903184285634339, + "grad_norm": 1.0564130697219387, + "learning_rate": 4.905287303585971e-09, + "loss": 0.8268, + "step": 11060 + }, + { + "epoch": 0.9904079691085119, + "grad_norm": 0.9450602803807338, + "learning_rate": 4.814876455710993e-09, + "loss": 0.8434, + "step": 11061 + }, + { + "epoch": 0.9904975096535901, + "grad_norm": 0.9203708858435595, + "learning_rate": 4.725306370236827e-09, + "loss": 0.8447, + "step": 11062 + }, + { + "epoch": 0.9905870501986681, + "grad_norm": 0.9663626335468976, + "learning_rate": 4.636577054698554e-09, + "loss": 0.8117, + "step": 11063 + }, + { + "epoch": 0.9906765907437461, + "grad_norm": 1.0744467261084973, + "learning_rate": 4.548688516559097e-09, + "loss": 0.7795, + "step": 11064 + }, + { + "epoch": 0.9907661312888242, + "grad_norm": 0.9159920379576059, + "learning_rate": 4.461640763212538e-09, + "loss": 0.7417, + "step": 11065 + }, + { + "epoch": 0.9908556718339023, + "grad_norm": 0.9918163530451493, + "learning_rate": 4.375433801979689e-09, + "loss": 0.83, + "step": 11066 + }, + { + "epoch": 0.9909452123789804, + "grad_norm": 1.0045341603547748, + "learning_rate": 4.290067640113637e-09, + "loss": 0.8016, + "step": 11067 + }, + { + "epoch": 0.9910347529240584, + "grad_norm": 1.1066627796260093, + "learning_rate": 4.2055422847930846e-09, + "loss": 0.788, + "step": 11068 + }, + { + "epoch": 0.9911242934691364, + "grad_norm": 1.0199953037305114, + "learning_rate": 4.12185774312901e-09, + "loss": 0.7829, + "step": 11069 + }, + { + "epoch": 0.9912138340142146, + "grad_norm": 1.018977449567371, + "learning_rate": 4.039014022160226e-09, + "loss": 0.815, + "step": 11070 + }, + { + "epoch": 0.9913033745592926, + "grad_norm": 0.9095701610202261, + "learning_rate": 3.957011128856714e-09, + "loss": 0.841, + "step": 11071 + }, + { + "epoch": 0.9913929151043707, + "grad_norm": 1.032361202197047, + "learning_rate": 3.875849070115179e-09, + "loss": 0.8595, + "step": 11072 + }, + { + "epoch": 0.9914824556494488, + "grad_norm": 1.032437132546964, + "learning_rate": 3.795527852762382e-09, + "loss": 0.7874, + "step": 11073 + }, + { + "epoch": 0.9915719961945269, + "grad_norm": 0.9958227435716922, + "learning_rate": 3.716047483555141e-09, + "loss": 0.689, + "step": 11074 + }, + { + "epoch": 0.9916615367396049, + "grad_norm": 1.0660261111918978, + "learning_rate": 3.6374079691792185e-09, + "loss": 0.8149, + "step": 11075 + }, + { + "epoch": 0.9917510772846829, + "grad_norm": 0.991064911975881, + "learning_rate": 3.5596093162493238e-09, + "loss": 0.7761, + "step": 11076 + }, + { + "epoch": 0.9918406178297611, + "grad_norm": 1.0044793916797132, + "learning_rate": 3.4826515313091115e-09, + "loss": 0.7715, + "step": 11077 + }, + { + "epoch": 0.9919301583748391, + "grad_norm": 0.9878163815550307, + "learning_rate": 3.4065346208334016e-09, + "loss": 0.7466, + "step": 11078 + }, + { + "epoch": 0.9920196989199171, + "grad_norm": 0.9486239299193588, + "learning_rate": 3.3312585912237406e-09, + "loss": 0.8019, + "step": 11079 + }, + { + "epoch": 0.9921092394649953, + "grad_norm": 0.9968803558888224, + "learning_rate": 3.25682344881173e-09, + "loss": 0.8484, + "step": 11080 + }, + { + "epoch": 0.9921987800100733, + "grad_norm": 1.149436776108533, + "learning_rate": 3.1832291998601384e-09, + "loss": 0.772, + "step": 11081 + }, + { + "epoch": 0.9922883205551514, + "grad_norm": 1.217837298843362, + "learning_rate": 3.1104758505584587e-09, + "loss": 0.7658, + "step": 11082 + }, + { + "epoch": 0.9923778611002294, + "grad_norm": 1.099557874191986, + "learning_rate": 3.0385634070262406e-09, + "loss": 0.7746, + "step": 11083 + }, + { + "epoch": 0.9924674016453076, + "grad_norm": 0.9995373851938801, + "learning_rate": 2.967491875314199e-09, + "loss": 0.8505, + "step": 11084 + }, + { + "epoch": 0.9925569421903856, + "grad_norm": 0.9820065655438729, + "learning_rate": 2.897261261397555e-09, + "loss": 0.8262, + "step": 11085 + }, + { + "epoch": 0.9926464827354636, + "grad_norm": 1.0654981981596758, + "learning_rate": 2.827871571187135e-09, + "loss": 0.7695, + "step": 11086 + }, + { + "epoch": 0.9927360232805417, + "grad_norm": 0.9212408597043569, + "learning_rate": 2.7593228105171623e-09, + "loss": 0.8159, + "step": 11087 + }, + { + "epoch": 0.9928255638256198, + "grad_norm": 1.0067241689655846, + "learning_rate": 2.6916149851563542e-09, + "loss": 0.808, + "step": 11088 + }, + { + "epoch": 0.9929151043706979, + "grad_norm": 0.995624029648079, + "learning_rate": 2.624748100797936e-09, + "loss": 0.7835, + "step": 11089 + }, + { + "epoch": 0.9930046449157759, + "grad_norm": 1.1848262152631013, + "learning_rate": 2.5587221630674063e-09, + "loss": 0.7844, + "step": 11090 + }, + { + "epoch": 0.993094185460854, + "grad_norm": 0.9587342170871609, + "learning_rate": 2.4935371775181015e-09, + "loss": 0.7808, + "step": 11091 + }, + { + "epoch": 0.9931837260059321, + "grad_norm": 1.0960445852989076, + "learning_rate": 2.429193149633413e-09, + "loss": 0.7945, + "step": 11092 + }, + { + "epoch": 0.9932732665510101, + "grad_norm": 0.9586002943106384, + "learning_rate": 2.365690084825678e-09, + "loss": 0.7769, + "step": 11093 + }, + { + "epoch": 0.9933628070960882, + "grad_norm": 1.0641587404932487, + "learning_rate": 2.3030279884372896e-09, + "loss": 0.8284, + "step": 11094 + }, + { + "epoch": 0.9934523476411663, + "grad_norm": 0.9602061072976953, + "learning_rate": 2.2412068657384766e-09, + "loss": 0.7973, + "step": 11095 + }, + { + "epoch": 0.9935418881862443, + "grad_norm": 0.9420386697733488, + "learning_rate": 2.1802267219295236e-09, + "loss": 0.8036, + "step": 11096 + }, + { + "epoch": 0.9936314287313224, + "grad_norm": 0.9974359043957409, + "learning_rate": 2.1200875621407713e-09, + "loss": 0.7813, + "step": 11097 + }, + { + "epoch": 0.9937209692764005, + "grad_norm": 1.0129217304170872, + "learning_rate": 2.0607893914292852e-09, + "loss": 0.768, + "step": 11098 + }, + { + "epoch": 0.9938105098214786, + "grad_norm": 1.0509226284700077, + "learning_rate": 2.002332214783298e-09, + "loss": 0.7718, + "step": 11099 + }, + { + "epoch": 0.9939000503665566, + "grad_norm": 1.0338762829000094, + "learning_rate": 1.9447160371222072e-09, + "loss": 0.8762, + "step": 11100 + }, + { + "epoch": 0.9939895909116346, + "grad_norm": 0.9861582060266968, + "learning_rate": 1.8879408632899166e-09, + "loss": 0.7823, + "step": 11101 + }, + { + "epoch": 0.9940791314567128, + "grad_norm": 0.9499161736587978, + "learning_rate": 1.832006698062605e-09, + "loss": 0.7902, + "step": 11102 + }, + { + "epoch": 0.9941686720017908, + "grad_norm": 0.9549066382923261, + "learning_rate": 1.776913546146508e-09, + "loss": 0.7883, + "step": 11103 + }, + { + "epoch": 0.9942582125468689, + "grad_norm": 1.0268234989776426, + "learning_rate": 1.7226614121756968e-09, + "loss": 0.83, + "step": 11104 + }, + { + "epoch": 0.9943477530919469, + "grad_norm": 0.9476598376405527, + "learning_rate": 1.6692503007131878e-09, + "loss": 0.7663, + "step": 11105 + }, + { + "epoch": 0.994437293637025, + "grad_norm": 0.9207876775314704, + "learning_rate": 1.6166802162509432e-09, + "loss": 0.8003, + "step": 11106 + }, + { + "epoch": 0.9945268341821031, + "grad_norm": 0.8792071443721514, + "learning_rate": 1.5649511632120917e-09, + "loss": 0.7776, + "step": 11107 + }, + { + "epoch": 0.9946163747271811, + "grad_norm": 0.9193413595643799, + "learning_rate": 1.5140631459475973e-09, + "loss": 0.7991, + "step": 11108 + }, + { + "epoch": 0.9947059152722593, + "grad_norm": 0.9414064498691534, + "learning_rate": 1.46401616873737e-09, + "loss": 0.7457, + "step": 11109 + }, + { + "epoch": 0.9947954558173373, + "grad_norm": 0.9567177882706259, + "learning_rate": 1.4148102357924853e-09, + "loss": 0.7999, + "step": 11110 + }, + { + "epoch": 0.9948849963624153, + "grad_norm": 0.92570706442964, + "learning_rate": 1.3664453512518549e-09, + "loss": 0.7937, + "step": 11111 + }, + { + "epoch": 0.9949745369074934, + "grad_norm": 1.142568490233922, + "learning_rate": 1.3189215191822259e-09, + "loss": 0.7767, + "step": 11112 + }, + { + "epoch": 0.9950640774525715, + "grad_norm": 0.9870159645814577, + "learning_rate": 1.272238743582621e-09, + "loss": 0.7766, + "step": 11113 + }, + { + "epoch": 0.9951536179976496, + "grad_norm": 1.0072415293964974, + "learning_rate": 1.2263970283798998e-09, + "loss": 0.7816, + "step": 11114 + }, + { + "epoch": 0.9952431585427276, + "grad_norm": 1.1052734122972252, + "learning_rate": 1.1813963774287563e-09, + "loss": 0.7496, + "step": 11115 + }, + { + "epoch": 0.9953326990878058, + "grad_norm": 0.889485336470331, + "learning_rate": 1.1372367945161612e-09, + "loss": 0.7714, + "step": 11116 + }, + { + "epoch": 0.9954222396328838, + "grad_norm": 0.9992063631291115, + "learning_rate": 1.0939182833558104e-09, + "loss": 0.7983, + "step": 11117 + }, + { + "epoch": 0.9955117801779618, + "grad_norm": 0.9423410990919285, + "learning_rate": 1.0514408475914561e-09, + "loss": 0.7898, + "step": 11118 + }, + { + "epoch": 0.9956013207230399, + "grad_norm": 0.925779656684305, + "learning_rate": 1.009804490795796e-09, + "loss": 0.8263, + "step": 11119 + }, + { + "epoch": 0.995690861268118, + "grad_norm": 0.9631395838148694, + "learning_rate": 9.690092164715835e-10, + "loss": 0.8519, + "step": 11120 + }, + { + "epoch": 0.995780401813196, + "grad_norm": 0.9186420962002961, + "learning_rate": 9.290550280505184e-10, + "loss": 0.776, + "step": 11121 + }, + { + "epoch": 0.9958699423582741, + "grad_norm": 1.0706150219470834, + "learning_rate": 8.899419288943556e-10, + "loss": 0.7873, + "step": 11122 + }, + { + "epoch": 0.9959594829033521, + "grad_norm": 0.8799716788006113, + "learning_rate": 8.516699222915759e-10, + "loss": 0.8478, + "step": 11123 + }, + { + "epoch": 0.9960490234484303, + "grad_norm": 0.9931369049101895, + "learning_rate": 8.14239011461826e-10, + "loss": 0.7947, + "step": 11124 + }, + { + "epoch": 0.9961385639935083, + "grad_norm": 0.9411226261200677, + "learning_rate": 7.776491995536984e-10, + "loss": 0.7935, + "step": 11125 + }, + { + "epoch": 0.9962281045385863, + "grad_norm": 1.033253272459167, + "learning_rate": 7.419004896447313e-10, + "loss": 0.771, + "step": 11126 + }, + { + "epoch": 0.9963176450836645, + "grad_norm": 1.0749758378111818, + "learning_rate": 7.069928847436291e-10, + "loss": 0.7515, + "step": 11127 + }, + { + "epoch": 0.9964071856287425, + "grad_norm": 0.9747974918239087, + "learning_rate": 6.729263877847114e-10, + "loss": 0.7823, + "step": 11128 + }, + { + "epoch": 0.9964967261738206, + "grad_norm": 1.0810498783383968, + "learning_rate": 6.397010016356842e-10, + "loss": 0.8548, + "step": 11129 + }, + { + "epoch": 0.9965862667188986, + "grad_norm": 0.8974041909212097, + "learning_rate": 6.073167290887582e-10, + "loss": 0.7561, + "step": 11130 + }, + { + "epoch": 0.9966758072639768, + "grad_norm": 0.9855959745239473, + "learning_rate": 5.757735728695313e-10, + "loss": 0.8123, + "step": 11131 + }, + { + "epoch": 0.9967653478090548, + "grad_norm": 1.0135532783865846, + "learning_rate": 5.450715356314363e-10, + "loss": 0.7392, + "step": 11132 + }, + { + "epoch": 0.9968548883541328, + "grad_norm": 1.0591160342401547, + "learning_rate": 5.152106199568519e-10, + "loss": 0.8276, + "step": 11133 + }, + { + "epoch": 0.996944428899211, + "grad_norm": 1.0233364566689012, + "learning_rate": 4.861908283571026e-10, + "loss": 0.8671, + "step": 11134 + }, + { + "epoch": 0.997033969444289, + "grad_norm": 1.087326653001518, + "learning_rate": 4.580121632724588e-10, + "loss": 0.834, + "step": 11135 + }, + { + "epoch": 0.997123509989367, + "grad_norm": 1.0844423175944673, + "learning_rate": 4.3067462707546693e-10, + "loss": 0.7852, + "step": 11136 + }, + { + "epoch": 0.9972130505344451, + "grad_norm": 1.0376214459889592, + "learning_rate": 4.041782220642887e-10, + "loss": 0.7822, + "step": 11137 + }, + { + "epoch": 0.9973025910795232, + "grad_norm": 0.8730031302991897, + "learning_rate": 3.785229504682519e-10, + "loss": 0.7918, + "step": 11138 + }, + { + "epoch": 0.9973921316246013, + "grad_norm": 1.125151449284699, + "learning_rate": 3.5370881444452e-10, + "loss": 0.8199, + "step": 11139 + }, + { + "epoch": 0.9974816721696793, + "grad_norm": 0.9624139988481608, + "learning_rate": 3.2973581608142234e-10, + "loss": 0.8703, + "step": 11140 + }, + { + "epoch": 0.9975712127147573, + "grad_norm": 0.921695001158502, + "learning_rate": 3.066039573940138e-10, + "loss": 0.7775, + "step": 11141 + }, + { + "epoch": 0.9976607532598355, + "grad_norm": 0.8950767283416653, + "learning_rate": 2.843132403296256e-10, + "loss": 0.7621, + "step": 11142 + }, + { + "epoch": 0.9977502938049135, + "grad_norm": 0.9349637857208811, + "learning_rate": 2.628636667634243e-10, + "loss": 0.7665, + "step": 11143 + }, + { + "epoch": 0.9978398343499916, + "grad_norm": 1.1041455084647787, + "learning_rate": 2.4225523849841225e-10, + "loss": 0.7699, + "step": 11144 + }, + { + "epoch": 0.9979293748950697, + "grad_norm": 1.0564882772402155, + "learning_rate": 2.224879572676475e-10, + "loss": 0.7886, + "step": 11145 + }, + { + "epoch": 0.9980189154401478, + "grad_norm": 1.037917291989691, + "learning_rate": 2.0356182473646458e-10, + "loss": 0.7898, + "step": 11146 + }, + { + "epoch": 0.9981084559852258, + "grad_norm": 1.019778840356656, + "learning_rate": 1.8547684249470288e-10, + "loss": 0.7716, + "step": 11147 + }, + { + "epoch": 0.9981979965303038, + "grad_norm": 0.9090738421813411, + "learning_rate": 1.6823301206336796e-10, + "loss": 0.7758, + "step": 11148 + }, + { + "epoch": 0.998287537075382, + "grad_norm": 1.0000851338482686, + "learning_rate": 1.518303348946315e-10, + "loss": 0.8103, + "step": 11149 + }, + { + "epoch": 0.99837707762046, + "grad_norm": 1.082956981556173, + "learning_rate": 1.3626881236739053e-10, + "loss": 0.825, + "step": 11150 + }, + { + "epoch": 0.9984666181655381, + "grad_norm": 1.3432620600541343, + "learning_rate": 1.21548445790598e-10, + "loss": 0.785, + "step": 11151 + }, + { + "epoch": 0.9985561587106162, + "grad_norm": 1.061937718697999, + "learning_rate": 1.0766923640215254e-10, + "loss": 0.7637, + "step": 11152 + }, + { + "epoch": 0.9986456992556942, + "grad_norm": 0.9693415064531373, + "learning_rate": 9.463118537000882e-11, + "loss": 0.8187, + "step": 11153 + }, + { + "epoch": 0.9987352398007723, + "grad_norm": 0.9258957249178724, + "learning_rate": 8.243429379106716e-11, + "loss": 0.7979, + "step": 11154 + }, + { + "epoch": 0.9988247803458503, + "grad_norm": 0.9306948430918408, + "learning_rate": 7.107856269006342e-11, + "loss": 0.7536, + "step": 11155 + }, + { + "epoch": 0.9989143208909285, + "grad_norm": 0.9897909968903863, + "learning_rate": 6.056399302400984e-11, + "loss": 0.7299, + "step": 11156 + }, + { + "epoch": 0.9990038614360065, + "grad_norm": 0.9966890196757293, + "learning_rate": 5.089058567664396e-11, + "loss": 0.8125, + "step": 11157 + }, + { + "epoch": 0.9990934019810845, + "grad_norm": 0.9710463795168044, + "learning_rate": 4.205834146064902e-11, + "loss": 0.7746, + "step": 11158 + }, + { + "epoch": 0.9991829425261626, + "grad_norm": 1.0802563022335718, + "learning_rate": 3.4067261120984684e-11, + "loss": 0.795, + "step": 11159 + }, + { + "epoch": 0.9992724830712407, + "grad_norm": 1.0067298497614499, + "learning_rate": 2.6917345328225653e-11, + "loss": 0.8149, + "step": 11160 + }, + { + "epoch": 0.9993620236163188, + "grad_norm": 1.089581608273436, + "learning_rate": 2.060859468300258e-11, + "loss": 0.8233, + "step": 11161 + }, + { + "epoch": 0.9994515641613968, + "grad_norm": 1.1516062666467761, + "learning_rate": 1.514100971822252e-11, + "loss": 0.7471, + "step": 11162 + }, + { + "epoch": 0.999541104706475, + "grad_norm": 0.9880798501695719, + "learning_rate": 1.0514590893517807e-11, + "loss": 0.817, + "step": 11163 + }, + { + "epoch": 0.999630645251553, + "grad_norm": 1.0438818650034132, + "learning_rate": 6.729338596356272e-12, + "loss": 0.7806, + "step": 11164 + }, + { + "epoch": 0.999720185796631, + "grad_norm": 1.057060240229699, + "learning_rate": 3.785253146482148e-12, + "loss": 0.8326, + "step": 11165 + }, + { + "epoch": 0.9998097263417091, + "grad_norm": 0.9140718394821942, + "learning_rate": 1.6823347903649478e-12, + "loss": 0.7493, + "step": 11166 + }, + { + "epoch": 0.9998992668867872, + "grad_norm": 1.0844146151998872, + "learning_rate": 4.2058370675057693e-13, + "loss": 0.7957, + "step": 11167 + }, + { + "epoch": 0.9999888074318652, + "grad_norm": 0.9303737122818287, + "learning_rate": 0.0, + "loss": 0.8216, + "step": 11168 + }, + { + "epoch": 0.9999888074318652, + "step": 11168, + "total_flos": 2.6264864681754624e+16, + "train_loss": 0.2994103609800424, + "train_runtime": 169468.3256, + "train_samples_per_second": 8.435, + "train_steps_per_second": 0.066 + } + ], + "logging_steps": 1.0, + "max_steps": 11168, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.6264864681754624e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +}