cherry-wizardlm-40-percent-7B / trainer_state.json
Ming Li
Initial commit
5262098
raw
history blame contribute delete
No virus
78.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9978513107004727,
"global_step": 654,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.9831,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.9479,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 3e-06,
"loss": 0.8474,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 0.8862,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 0.8511,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 0.8842,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 7e-06,
"loss": 0.7622,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 0.7532,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 9e-06,
"loss": 0.7864,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 0.7907,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.7628,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 1.2e-05,
"loss": 0.7197,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.7173,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 1.4e-05,
"loss": 0.7939,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.7293,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.7761,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 1.7e-05,
"loss": 0.7265,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 1.8e-05,
"loss": 0.7042,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 1.9e-05,
"loss": 0.6792,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.7203,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 1.9999877230540083e-05,
"loss": 0.7298,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 1.9999508925174792e-05,
"loss": 0.7191,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 1.999889509294746e-05,
"loss": 0.7504,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 1.9998035748930055e-05,
"loss": 0.6989,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 1.999693091422282e-05,
"loss": 0.7237,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 1.9995580615953747e-05,
"loss": 0.6478,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 1.9993984887277917e-05,
"loss": 0.7048,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 1.9992143767376667e-05,
"loss": 0.7172,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 1.999005730145667e-05,
"loss": 0.7182,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 1.998772554074878e-05,
"loss": 0.7409,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 1.99851485425068e-05,
"loss": 0.7484,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 1.9982326370006056e-05,
"loss": 0.7077,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 1.997925909254188e-05,
"loss": 0.7006,
"step": 33
},
{
"epoch": 0.16,
"learning_rate": 1.9975946785427864e-05,
"loss": 0.7109,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 1.9972389529994043e-05,
"loss": 0.6996,
"step": 35
},
{
"epoch": 0.17,
"learning_rate": 1.9968587413584875e-05,
"loss": 0.6881,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 1.996454052955713e-05,
"loss": 0.703,
"step": 37
},
{
"epoch": 0.17,
"learning_rate": 1.9960248977277548e-05,
"loss": 0.6502,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 1.9955712862120443e-05,
"loss": 0.7288,
"step": 39
},
{
"epoch": 0.18,
"learning_rate": 1.9950932295465102e-05,
"loss": 0.7006,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 1.9945907394693034e-05,
"loss": 0.722,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 1.9940638283185118e-05,
"loss": 0.7435,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 1.9935125090318547e-05,
"loss": 0.7045,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 1.9929367951463655e-05,
"loss": 0.6758,
"step": 44
},
{
"epoch": 0.21,
"learning_rate": 1.992336700798062e-05,
"loss": 0.6703,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 1.991712240721595e-05,
"loss": 0.6509,
"step": 46
},
{
"epoch": 0.22,
"learning_rate": 1.9910634302498906e-05,
"loss": 0.6535,
"step": 47
},
{
"epoch": 0.22,
"learning_rate": 1.9903902853137703e-05,
"loss": 0.6871,
"step": 48
},
{
"epoch": 0.22,
"learning_rate": 1.9896928224415622e-05,
"loss": 0.6995,
"step": 49
},
{
"epoch": 0.23,
"learning_rate": 1.9889710587586953e-05,
"loss": 0.7394,
"step": 50
},
{
"epoch": 0.23,
"learning_rate": 1.9882250119872758e-05,
"loss": 0.6726,
"step": 51
},
{
"epoch": 0.24,
"learning_rate": 1.9874547004456565e-05,
"loss": 0.6939,
"step": 52
},
{
"epoch": 0.24,
"learning_rate": 1.986660143047983e-05,
"loss": 0.704,
"step": 53
},
{
"epoch": 0.25,
"learning_rate": 1.9858413593037326e-05,
"loss": 0.7042,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 1.9849983693172324e-05,
"loss": 0.6569,
"step": 55
},
{
"epoch": 0.26,
"learning_rate": 1.9841311937871677e-05,
"loss": 0.6498,
"step": 56
},
{
"epoch": 0.26,
"learning_rate": 1.9832398540060727e-05,
"loss": 0.6551,
"step": 57
},
{
"epoch": 0.27,
"learning_rate": 1.982324371859808e-05,
"loss": 0.6522,
"step": 58
},
{
"epoch": 0.27,
"learning_rate": 1.9813847698270236e-05,
"loss": 0.6868,
"step": 59
},
{
"epoch": 0.28,
"learning_rate": 1.980421070978606e-05,
"loss": 0.635,
"step": 60
},
{
"epoch": 0.28,
"learning_rate": 1.9794332989771133e-05,
"loss": 0.6722,
"step": 61
},
{
"epoch": 0.28,
"learning_rate": 1.9784214780761917e-05,
"loss": 0.6502,
"step": 62
},
{
"epoch": 0.29,
"learning_rate": 1.9773856331199823e-05,
"loss": 0.6862,
"step": 63
},
{
"epoch": 0.29,
"learning_rate": 1.9763257895425112e-05,
"loss": 0.723,
"step": 64
},
{
"epoch": 0.3,
"learning_rate": 1.975241973367062e-05,
"loss": 0.7064,
"step": 65
},
{
"epoch": 0.3,
"learning_rate": 1.974134211205541e-05,
"loss": 0.6093,
"step": 66
},
{
"epoch": 0.31,
"learning_rate": 1.97300253025782e-05,
"loss": 0.6944,
"step": 67
},
{
"epoch": 0.31,
"learning_rate": 1.971846958311071e-05,
"loss": 0.6392,
"step": 68
},
{
"epoch": 0.32,
"learning_rate": 1.9706675237390827e-05,
"loss": 0.657,
"step": 69
},
{
"epoch": 0.32,
"learning_rate": 1.9694642555015643e-05,
"loss": 0.6582,
"step": 70
},
{
"epoch": 0.33,
"learning_rate": 1.9682371831434338e-05,
"loss": 0.6968,
"step": 71
},
{
"epoch": 0.33,
"learning_rate": 1.9669863367940936e-05,
"loss": 0.6958,
"step": 72
},
{
"epoch": 0.33,
"learning_rate": 1.9657117471666897e-05,
"loss": 0.6585,
"step": 73
},
{
"epoch": 0.34,
"learning_rate": 1.9644134455573588e-05,
"loss": 0.6716,
"step": 74
},
{
"epoch": 0.34,
"learning_rate": 1.9630914638444572e-05,
"loss": 0.6753,
"step": 75
},
{
"epoch": 0.35,
"learning_rate": 1.9617458344877818e-05,
"loss": 0.6407,
"step": 76
},
{
"epoch": 0.35,
"learning_rate": 1.9603765905277705e-05,
"loss": 0.6233,
"step": 77
},
{
"epoch": 0.36,
"learning_rate": 1.9589837655846916e-05,
"loss": 0.6693,
"step": 78
},
{
"epoch": 0.36,
"learning_rate": 1.957567393857818e-05,
"loss": 0.6587,
"step": 79
},
{
"epoch": 0.37,
"learning_rate": 1.9561275101245886e-05,
"loss": 0.6806,
"step": 80
},
{
"epoch": 0.37,
"learning_rate": 1.9546641497397522e-05,
"loss": 0.6769,
"step": 81
},
{
"epoch": 0.38,
"learning_rate": 1.9531773486345025e-05,
"loss": 0.6523,
"step": 82
},
{
"epoch": 0.38,
"learning_rate": 1.951667143315593e-05,
"loss": 0.6926,
"step": 83
},
{
"epoch": 0.39,
"learning_rate": 1.9501335708644415e-05,
"loss": 0.6518,
"step": 84
},
{
"epoch": 0.39,
"learning_rate": 1.9485766689362205e-05,
"loss": 0.6683,
"step": 85
},
{
"epoch": 0.39,
"learning_rate": 1.9469964757589324e-05,
"loss": 0.7195,
"step": 86
},
{
"epoch": 0.4,
"learning_rate": 1.9453930301324692e-05,
"loss": 0.6396,
"step": 87
},
{
"epoch": 0.4,
"learning_rate": 1.9437663714276617e-05,
"loss": 0.6797,
"step": 88
},
{
"epoch": 0.41,
"learning_rate": 1.9421165395853124e-05,
"loss": 0.6827,
"step": 89
},
{
"epoch": 0.41,
"learning_rate": 1.9404435751152134e-05,
"loss": 0.6787,
"step": 90
},
{
"epoch": 0.42,
"learning_rate": 1.9387475190951542e-05,
"loss": 0.6523,
"step": 91
},
{
"epoch": 0.42,
"learning_rate": 1.937028413169911e-05,
"loss": 0.6506,
"step": 92
},
{
"epoch": 0.43,
"learning_rate": 1.935286299550225e-05,
"loss": 0.6867,
"step": 93
},
{
"epoch": 0.43,
"learning_rate": 1.9335212210117656e-05,
"loss": 0.6766,
"step": 94
},
{
"epoch": 0.44,
"learning_rate": 1.931733220894081e-05,
"loss": 0.6376,
"step": 95
},
{
"epoch": 0.44,
"learning_rate": 1.9299223430995323e-05,
"loss": 0.6385,
"step": 96
},
{
"epoch": 0.44,
"learning_rate": 1.928088632092218e-05,
"loss": 0.6469,
"step": 97
},
{
"epoch": 0.45,
"learning_rate": 1.9262321328968797e-05,
"loss": 0.688,
"step": 98
},
{
"epoch": 0.45,
"learning_rate": 1.924352891097798e-05,
"loss": 0.6785,
"step": 99
},
{
"epoch": 0.46,
"learning_rate": 1.9224509528376737e-05,
"loss": 0.7346,
"step": 100
},
{
"epoch": 0.46,
"learning_rate": 1.920526364816493e-05,
"loss": 0.6948,
"step": 101
},
{
"epoch": 0.47,
"learning_rate": 1.9185791742903816e-05,
"loss": 0.6711,
"step": 102
},
{
"epoch": 0.47,
"learning_rate": 1.916609429070446e-05,
"loss": 0.6188,
"step": 103
},
{
"epoch": 0.48,
"learning_rate": 1.9146171775215982e-05,
"loss": 0.6117,
"step": 104
},
{
"epoch": 0.48,
"learning_rate": 1.9126024685613664e-05,
"loss": 0.6082,
"step": 105
},
{
"epoch": 0.49,
"learning_rate": 1.9105653516586974e-05,
"loss": 0.6925,
"step": 106
},
{
"epoch": 0.49,
"learning_rate": 1.9085058768327394e-05,
"loss": 0.6782,
"step": 107
},
{
"epoch": 0.5,
"learning_rate": 1.906424094651615e-05,
"loss": 0.7054,
"step": 108
},
{
"epoch": 0.5,
"learning_rate": 1.9043200562311788e-05,
"loss": 0.6751,
"step": 109
},
{
"epoch": 0.5,
"learning_rate": 1.9021938132337628e-05,
"loss": 0.6005,
"step": 110
},
{
"epoch": 0.51,
"learning_rate": 1.9000454178669084e-05,
"loss": 0.6593,
"step": 111
},
{
"epoch": 0.51,
"learning_rate": 1.8978749228820827e-05,
"loss": 0.6555,
"step": 112
},
{
"epoch": 0.52,
"learning_rate": 1.8956823815733858e-05,
"loss": 0.6768,
"step": 113
},
{
"epoch": 0.52,
"learning_rate": 1.8934678477762398e-05,
"loss": 0.7238,
"step": 114
},
{
"epoch": 0.53,
"learning_rate": 1.891231375866068e-05,
"loss": 0.6428,
"step": 115
},
{
"epoch": 0.53,
"learning_rate": 1.8889730207569607e-05,
"loss": 0.6565,
"step": 116
},
{
"epoch": 0.54,
"learning_rate": 1.8866928379003253e-05,
"loss": 0.6442,
"step": 117
},
{
"epoch": 0.54,
"learning_rate": 1.8843908832835248e-05,
"loss": 0.6499,
"step": 118
},
{
"epoch": 0.55,
"learning_rate": 1.882067213428505e-05,
"loss": 0.6379,
"step": 119
},
{
"epoch": 0.55,
"learning_rate": 1.8797218853904037e-05,
"loss": 0.6704,
"step": 120
},
{
"epoch": 0.55,
"learning_rate": 1.8773549567561528e-05,
"loss": 0.6657,
"step": 121
},
{
"epoch": 0.56,
"learning_rate": 1.874966485643062e-05,
"loss": 0.6681,
"step": 122
},
{
"epoch": 0.56,
"learning_rate": 1.8725565306973935e-05,
"loss": 0.6598,
"step": 123
},
{
"epoch": 0.57,
"learning_rate": 1.87012515109292e-05,
"loss": 0.6419,
"step": 124
},
{
"epoch": 0.57,
"learning_rate": 1.8676724065294744e-05,
"loss": 0.683,
"step": 125
},
{
"epoch": 0.58,
"learning_rate": 1.865198357231481e-05,
"loss": 0.6982,
"step": 126
},
{
"epoch": 0.58,
"learning_rate": 1.8627030639464794e-05,
"loss": 0.6285,
"step": 127
},
{
"epoch": 0.59,
"learning_rate": 1.8601865879436318e-05,
"loss": 0.6629,
"step": 128
},
{
"epoch": 0.59,
"learning_rate": 1.857648991012218e-05,
"loss": 0.6572,
"step": 129
},
{
"epoch": 0.6,
"learning_rate": 1.8550903354601182e-05,
"loss": 0.6832,
"step": 130
},
{
"epoch": 0.6,
"learning_rate": 1.8525106841122852e-05,
"loss": 0.6543,
"step": 131
},
{
"epoch": 0.61,
"learning_rate": 1.8499101003091995e-05,
"loss": 0.6509,
"step": 132
},
{
"epoch": 0.61,
"learning_rate": 1.8472886479053147e-05,
"loss": 0.6666,
"step": 133
},
{
"epoch": 0.61,
"learning_rate": 1.84464639126749e-05,
"loss": 0.6756,
"step": 134
},
{
"epoch": 0.62,
"learning_rate": 1.8419833952734094e-05,
"loss": 0.6524,
"step": 135
},
{
"epoch": 0.62,
"learning_rate": 1.839299725309989e-05,
"loss": 0.6862,
"step": 136
},
{
"epoch": 0.63,
"learning_rate": 1.836595447271771e-05,
"loss": 0.657,
"step": 137
},
{
"epoch": 0.63,
"learning_rate": 1.8338706275593066e-05,
"loss": 0.6396,
"step": 138
},
{
"epoch": 0.64,
"learning_rate": 1.831125333077525e-05,
"loss": 0.6946,
"step": 139
},
{
"epoch": 0.64,
"learning_rate": 1.8283596312340893e-05,
"loss": 0.7144,
"step": 140
},
{
"epoch": 0.65,
"learning_rate": 1.8255735899377443e-05,
"loss": 0.7052,
"step": 141
},
{
"epoch": 0.65,
"learning_rate": 1.8227672775966478e-05,
"loss": 0.6792,
"step": 142
},
{
"epoch": 0.66,
"learning_rate": 1.819940763116689e-05,
"loss": 0.6446,
"step": 143
},
{
"epoch": 0.66,
"learning_rate": 1.8170941158997992e-05,
"loss": 0.6499,
"step": 144
},
{
"epoch": 0.66,
"learning_rate": 1.8142274058422467e-05,
"loss": 0.6469,
"step": 145
},
{
"epoch": 0.67,
"learning_rate": 1.8113407033329213e-05,
"loss": 0.6391,
"step": 146
},
{
"epoch": 0.67,
"learning_rate": 1.8084340792516038e-05,
"loss": 0.6411,
"step": 147
},
{
"epoch": 0.68,
"learning_rate": 1.8055076049672286e-05,
"loss": 0.6215,
"step": 148
},
{
"epoch": 0.68,
"learning_rate": 1.8025613523361283e-05,
"loss": 0.6699,
"step": 149
},
{
"epoch": 0.69,
"learning_rate": 1.7995953937002723e-05,
"loss": 0.6861,
"step": 150
},
{
"epoch": 0.69,
"learning_rate": 1.7966098018854888e-05,
"loss": 0.6754,
"step": 151
},
{
"epoch": 0.7,
"learning_rate": 1.793604650199676e-05,
"loss": 0.6583,
"step": 152
},
{
"epoch": 0.7,
"learning_rate": 1.7905800124310048e-05,
"loss": 0.6714,
"step": 153
},
{
"epoch": 0.71,
"learning_rate": 1.7875359628461035e-05,
"loss": 0.6798,
"step": 154
},
{
"epoch": 0.71,
"learning_rate": 1.784472576188237e-05,
"loss": 0.6672,
"step": 155
},
{
"epoch": 0.72,
"learning_rate": 1.7813899276754703e-05,
"loss": 0.6884,
"step": 156
},
{
"epoch": 0.72,
"learning_rate": 1.778288092998822e-05,
"loss": 0.6277,
"step": 157
},
{
"epoch": 0.72,
"learning_rate": 1.7751671483204062e-05,
"loss": 0.6233,
"step": 158
},
{
"epoch": 0.73,
"learning_rate": 1.7720271702715607e-05,
"loss": 0.6577,
"step": 159
},
{
"epoch": 0.73,
"learning_rate": 1.768868235950968e-05,
"loss": 0.6207,
"step": 160
},
{
"epoch": 0.74,
"learning_rate": 1.7656904229227598e-05,
"loss": 0.6266,
"step": 161
},
{
"epoch": 0.74,
"learning_rate": 1.7624938092146138e-05,
"loss": 0.6372,
"step": 162
},
{
"epoch": 0.75,
"learning_rate": 1.7592784733158378e-05,
"loss": 0.696,
"step": 163
},
{
"epoch": 0.75,
"learning_rate": 1.7560444941754425e-05,
"loss": 0.6415,
"step": 164
},
{
"epoch": 0.76,
"learning_rate": 1.7527919512002025e-05,
"loss": 0.6243,
"step": 165
},
{
"epoch": 0.76,
"learning_rate": 1.749520924252706e-05,
"loss": 0.5833,
"step": 166
},
{
"epoch": 0.77,
"learning_rate": 1.7462314936493957e-05,
"loss": 0.6248,
"step": 167
},
{
"epoch": 0.77,
"learning_rate": 1.742923740158595e-05,
"loss": 0.6502,
"step": 168
},
{
"epoch": 0.77,
"learning_rate": 1.7395977449985265e-05,
"loss": 0.6422,
"step": 169
},
{
"epoch": 0.78,
"learning_rate": 1.736253589835316e-05,
"loss": 0.6289,
"step": 170
},
{
"epoch": 0.78,
"learning_rate": 1.7328913567809876e-05,
"loss": 0.6313,
"step": 171
},
{
"epoch": 0.79,
"learning_rate": 1.7295111283914487e-05,
"loss": 0.6308,
"step": 172
},
{
"epoch": 0.79,
"learning_rate": 1.7261129876644625e-05,
"loss": 0.6308,
"step": 173
},
{
"epoch": 0.8,
"learning_rate": 1.7226970180376087e-05,
"loss": 0.6308,
"step": 174
},
{
"epoch": 0.8,
"learning_rate": 1.719263303386237e-05,
"loss": 0.6516,
"step": 175
},
{
"epoch": 0.81,
"learning_rate": 1.715811928021406e-05,
"loss": 0.6368,
"step": 176
},
{
"epoch": 0.81,
"learning_rate": 1.7123429766878133e-05,
"loss": 0.63,
"step": 177
},
{
"epoch": 0.82,
"learning_rate": 1.708856534561716e-05,
"loss": 0.6369,
"step": 178
},
{
"epoch": 0.82,
"learning_rate": 1.7053526872488367e-05,
"loss": 0.6373,
"step": 179
},
{
"epoch": 0.83,
"learning_rate": 1.701831520782264e-05,
"loss": 0.6417,
"step": 180
},
{
"epoch": 0.83,
"learning_rate": 1.6982931216203392e-05,
"loss": 0.6458,
"step": 181
},
{
"epoch": 0.83,
"learning_rate": 1.694737576644533e-05,
"loss": 0.6879,
"step": 182
},
{
"epoch": 0.84,
"learning_rate": 1.6911649731573127e-05,
"loss": 0.6547,
"step": 183
},
{
"epoch": 0.84,
"learning_rate": 1.6875753988799984e-05,
"loss": 0.6253,
"step": 184
},
{
"epoch": 0.85,
"learning_rate": 1.6839689419506092e-05,
"loss": 0.6941,
"step": 185
},
{
"epoch": 0.85,
"learning_rate": 1.680345690921699e-05,
"loss": 0.6663,
"step": 186
},
{
"epoch": 0.86,
"learning_rate": 1.676705734758182e-05,
"loss": 0.6244,
"step": 187
},
{
"epoch": 0.86,
"learning_rate": 1.6730491628351487e-05,
"loss": 0.6623,
"step": 188
},
{
"epoch": 0.87,
"learning_rate": 1.6693760649356718e-05,
"loss": 0.6453,
"step": 189
},
{
"epoch": 0.87,
"learning_rate": 1.6656865312485996e-05,
"loss": 0.6387,
"step": 190
},
{
"epoch": 0.88,
"learning_rate": 1.6619806523663435e-05,
"loss": 0.6073,
"step": 191
},
{
"epoch": 0.88,
"learning_rate": 1.6582585192826544e-05,
"loss": 0.6048,
"step": 192
},
{
"epoch": 0.88,
"learning_rate": 1.6545202233903846e-05,
"loss": 0.592,
"step": 193
},
{
"epoch": 0.89,
"learning_rate": 1.6507658564792492e-05,
"loss": 0.6529,
"step": 194
},
{
"epoch": 0.89,
"learning_rate": 1.6469955107335666e-05,
"loss": 0.6008,
"step": 195
},
{
"epoch": 0.9,
"learning_rate": 1.6432092787299994e-05,
"loss": 0.6669,
"step": 196
},
{
"epoch": 0.9,
"learning_rate": 1.639407253435279e-05,
"loss": 0.632,
"step": 197
},
{
"epoch": 0.91,
"learning_rate": 1.6355895282039244e-05,
"loss": 0.6474,
"step": 198
},
{
"epoch": 0.91,
"learning_rate": 1.6317561967759474e-05,
"loss": 0.6479,
"step": 199
},
{
"epoch": 0.92,
"learning_rate": 1.627907353274555e-05,
"loss": 0.63,
"step": 200
},
{
"epoch": 0.92,
"learning_rate": 1.6240430922038348e-05,
"loss": 0.6037,
"step": 201
},
{
"epoch": 0.93,
"learning_rate": 1.620163508446435e-05,
"loss": 0.7098,
"step": 202
},
{
"epoch": 0.93,
"learning_rate": 1.6162686972612363e-05,
"loss": 0.6597,
"step": 203
},
{
"epoch": 0.94,
"learning_rate": 1.612358754281012e-05,
"loss": 0.6891,
"step": 204
},
{
"epoch": 0.94,
"learning_rate": 1.6084337755100795e-05,
"loss": 0.6422,
"step": 205
},
{
"epoch": 0.94,
"learning_rate": 1.604493857321944e-05,
"loss": 0.6662,
"step": 206
},
{
"epoch": 0.95,
"learning_rate": 1.600539096456931e-05,
"loss": 0.6403,
"step": 207
},
{
"epoch": 0.95,
"learning_rate": 1.596569590019811e-05,
"loss": 0.6195,
"step": 208
},
{
"epoch": 0.96,
"learning_rate": 1.592585435477417e-05,
"loss": 0.6007,
"step": 209
},
{
"epoch": 0.96,
"learning_rate": 1.588586730656249e-05,
"loss": 0.6068,
"step": 210
},
{
"epoch": 0.97,
"learning_rate": 1.5845735737400733e-05,
"loss": 0.6343,
"step": 211
},
{
"epoch": 0.97,
"learning_rate": 1.5805460632675112e-05,
"loss": 0.6197,
"step": 212
},
{
"epoch": 0.98,
"learning_rate": 1.57650429812962e-05,
"loss": 0.636,
"step": 213
},
{
"epoch": 0.98,
"learning_rate": 1.5724483775674645e-05,
"loss": 0.6304,
"step": 214
},
{
"epoch": 0.99,
"learning_rate": 1.56837840116968e-05,
"loss": 0.6489,
"step": 215
},
{
"epoch": 0.99,
"learning_rate": 1.5642944688700263e-05,
"loss": 0.6021,
"step": 216
},
{
"epoch": 0.99,
"learning_rate": 1.5601966809449375e-05,
"loss": 0.6537,
"step": 217
},
{
"epoch": 1.0,
"learning_rate": 1.556085138011055e-05,
"loss": 0.6562,
"step": 218
},
{
"epoch": 1.0,
"learning_rate": 1.5519599410227594e-05,
"loss": 0.4769,
"step": 219
},
{
"epoch": 1.01,
"learning_rate": 1.547821191269693e-05,
"loss": 0.4262,
"step": 220
},
{
"epoch": 1.01,
"learning_rate": 1.5436689903742695e-05,
"loss": 0.4012,
"step": 221
},
{
"epoch": 1.02,
"learning_rate": 1.539503440289181e-05,
"loss": 0.4177,
"step": 222
},
{
"epoch": 1.02,
"learning_rate": 1.5353246432948954e-05,
"loss": 0.4107,
"step": 223
},
{
"epoch": 1.03,
"learning_rate": 1.5311327019971415e-05,
"loss": 0.4058,
"step": 224
},
{
"epoch": 1.03,
"learning_rate": 1.5269277193243936e-05,
"loss": 0.4185,
"step": 225
},
{
"epoch": 1.04,
"learning_rate": 1.5227097985253422e-05,
"loss": 0.3996,
"step": 226
},
{
"epoch": 1.04,
"learning_rate": 1.5184790431663586e-05,
"loss": 0.4187,
"step": 227
},
{
"epoch": 1.05,
"learning_rate": 1.5142355571289533e-05,
"loss": 0.38,
"step": 228
},
{
"epoch": 1.05,
"learning_rate": 1.509979444607224e-05,
"loss": 0.4095,
"step": 229
},
{
"epoch": 1.05,
"learning_rate": 1.5057108101052978e-05,
"loss": 0.4075,
"step": 230
},
{
"epoch": 1.06,
"learning_rate": 1.5014297584347652e-05,
"loss": 0.3781,
"step": 231
},
{
"epoch": 1.06,
"learning_rate": 1.4971363947121065e-05,
"loss": 0.3877,
"step": 232
},
{
"epoch": 1.07,
"learning_rate": 1.4928308243561108e-05,
"loss": 0.3934,
"step": 233
},
{
"epoch": 1.07,
"learning_rate": 1.4885131530852872e-05,
"loss": 0.372,
"step": 234
},
{
"epoch": 1.08,
"learning_rate": 1.4841834869152703e-05,
"loss": 0.3963,
"step": 235
},
{
"epoch": 1.08,
"learning_rate": 1.479841932156215e-05,
"loss": 0.3955,
"step": 236
},
{
"epoch": 1.09,
"learning_rate": 1.4754885954101883e-05,
"loss": 0.3849,
"step": 237
},
{
"epoch": 1.09,
"learning_rate": 1.4711235835685502e-05,
"loss": 0.4244,
"step": 238
},
{
"epoch": 1.1,
"learning_rate": 1.46674700380933e-05,
"loss": 0.3684,
"step": 239
},
{
"epoch": 1.1,
"learning_rate": 1.462358963594595e-05,
"loss": 0.4202,
"step": 240
},
{
"epoch": 1.1,
"learning_rate": 1.4579595706678095e-05,
"loss": 0.398,
"step": 241
},
{
"epoch": 1.11,
"learning_rate": 1.4535489330511932e-05,
"loss": 0.4082,
"step": 242
},
{
"epoch": 1.11,
"learning_rate": 1.449127159043065e-05,
"loss": 0.3744,
"step": 243
},
{
"epoch": 1.12,
"learning_rate": 1.4446943572151869e-05,
"loss": 0.3965,
"step": 244
},
{
"epoch": 1.12,
"learning_rate": 1.4402506364100957e-05,
"loss": 0.413,
"step": 245
},
{
"epoch": 1.13,
"learning_rate": 1.4357961057384323e-05,
"loss": 0.4195,
"step": 246
},
{
"epoch": 1.13,
"learning_rate": 1.4313308745762616e-05,
"loss": 0.4148,
"step": 247
},
{
"epoch": 1.14,
"learning_rate": 1.426855052562387e-05,
"loss": 0.3986,
"step": 248
},
{
"epoch": 1.14,
"learning_rate": 1.4223687495956592e-05,
"loss": 0.4128,
"step": 249
},
{
"epoch": 1.15,
"learning_rate": 1.4178720758322761e-05,
"loss": 0.3874,
"step": 250
},
{
"epoch": 1.15,
"learning_rate": 1.4133651416830803e-05,
"loss": 0.3938,
"step": 251
},
{
"epoch": 1.16,
"learning_rate": 1.4088480578108454e-05,
"loss": 0.4315,
"step": 252
},
{
"epoch": 1.16,
"learning_rate": 1.4043209351275615e-05,
"loss": 0.4098,
"step": 253
},
{
"epoch": 1.16,
"learning_rate": 1.3997838847917096e-05,
"loss": 0.3793,
"step": 254
},
{
"epoch": 1.17,
"learning_rate": 1.3952370182055332e-05,
"loss": 0.4081,
"step": 255
},
{
"epoch": 1.17,
"learning_rate": 1.3906804470123038e-05,
"loss": 0.4026,
"step": 256
},
{
"epoch": 1.18,
"learning_rate": 1.3861142830935786e-05,
"loss": 0.4051,
"step": 257
},
{
"epoch": 1.18,
"learning_rate": 1.3815386385664526e-05,
"loss": 0.3842,
"step": 258
},
{
"epoch": 1.19,
"learning_rate": 1.3769536257808077e-05,
"loss": 0.406,
"step": 259
},
{
"epoch": 1.19,
"learning_rate": 1.3723593573165523e-05,
"loss": 0.3914,
"step": 260
},
{
"epoch": 1.2,
"learning_rate": 1.367755945980858e-05,
"loss": 0.4159,
"step": 261
},
{
"epoch": 1.2,
"learning_rate": 1.3631435048053899e-05,
"loss": 0.3933,
"step": 262
},
{
"epoch": 1.21,
"learning_rate": 1.3585221470435301e-05,
"loss": 0.3735,
"step": 263
},
{
"epoch": 1.21,
"learning_rate": 1.3538919861675979e-05,
"loss": 0.3933,
"step": 264
},
{
"epoch": 1.21,
"learning_rate": 1.3492531358660634e-05,
"loss": 0.382,
"step": 265
},
{
"epoch": 1.22,
"learning_rate": 1.3446057100407557e-05,
"loss": 0.3773,
"step": 266
},
{
"epoch": 1.22,
"learning_rate": 1.3399498228040664e-05,
"loss": 0.3935,
"step": 267
},
{
"epoch": 1.23,
"learning_rate": 1.3352855884761483e-05,
"loss": 0.4454,
"step": 268
},
{
"epoch": 1.23,
"learning_rate": 1.330613121582107e-05,
"loss": 0.3683,
"step": 269
},
{
"epoch": 1.24,
"learning_rate": 1.3259325368491897e-05,
"loss": 0.3848,
"step": 270
},
{
"epoch": 1.24,
"learning_rate": 1.3212439492039688e-05,
"loss": 0.3962,
"step": 271
},
{
"epoch": 1.25,
"learning_rate": 1.3165474737695185e-05,
"loss": 0.4087,
"step": 272
},
{
"epoch": 1.25,
"learning_rate": 1.3118432258625895e-05,
"loss": 0.3904,
"step": 273
},
{
"epoch": 1.26,
"learning_rate": 1.3071313209907768e-05,
"loss": 0.4293,
"step": 274
},
{
"epoch": 1.26,
"learning_rate": 1.3024118748496834e-05,
"loss": 0.3833,
"step": 275
},
{
"epoch": 1.27,
"learning_rate": 1.2976850033200806e-05,
"loss": 0.3931,
"step": 276
},
{
"epoch": 1.27,
"learning_rate": 1.292950822465061e-05,
"loss": 0.41,
"step": 277
},
{
"epoch": 1.27,
"learning_rate": 1.2882094485271894e-05,
"loss": 0.3931,
"step": 278
},
{
"epoch": 1.28,
"learning_rate": 1.2834609979256505e-05,
"loss": 0.4066,
"step": 279
},
{
"epoch": 1.28,
"learning_rate": 1.2787055872533867e-05,
"loss": 0.3927,
"step": 280
},
{
"epoch": 1.29,
"learning_rate": 1.2739433332742381e-05,
"loss": 0.4068,
"step": 281
},
{
"epoch": 1.29,
"learning_rate": 1.2691743529200749e-05,
"loss": 0.3804,
"step": 282
},
{
"epoch": 1.3,
"learning_rate": 1.264398763287925e-05,
"loss": 0.4001,
"step": 283
},
{
"epoch": 1.3,
"learning_rate": 1.2596166816371005e-05,
"loss": 0.3805,
"step": 284
},
{
"epoch": 1.31,
"learning_rate": 1.2548282253863181e-05,
"loss": 0.3817,
"step": 285
},
{
"epoch": 1.31,
"learning_rate": 1.2500335121108151e-05,
"loss": 0.3835,
"step": 286
},
{
"epoch": 1.32,
"learning_rate": 1.2452326595394633e-05,
"loss": 0.417,
"step": 287
},
{
"epoch": 1.32,
"learning_rate": 1.2404257855518782e-05,
"loss": 0.3878,
"step": 288
},
{
"epoch": 1.32,
"learning_rate": 1.2356130081755243e-05,
"loss": 0.3937,
"step": 289
},
{
"epoch": 1.33,
"learning_rate": 1.2307944455828178e-05,
"loss": 0.3955,
"step": 290
},
{
"epoch": 1.33,
"learning_rate": 1.225970216088224e-05,
"loss": 0.391,
"step": 291
},
{
"epoch": 1.34,
"learning_rate": 1.221140438145353e-05,
"loss": 0.4032,
"step": 292
},
{
"epoch": 1.34,
"learning_rate": 1.2163052303440503e-05,
"loss": 0.3866,
"step": 293
},
{
"epoch": 1.35,
"learning_rate": 1.2114647114074863e-05,
"loss": 0.4002,
"step": 294
},
{
"epoch": 1.35,
"learning_rate": 1.2066190001892398e-05,
"loss": 0.387,
"step": 295
},
{
"epoch": 1.36,
"learning_rate": 1.2017682156703807e-05,
"loss": 0.3885,
"step": 296
},
{
"epoch": 1.36,
"learning_rate": 1.1969124769565485e-05,
"loss": 0.4031,
"step": 297
},
{
"epoch": 1.37,
"learning_rate": 1.1920519032750269e-05,
"loss": 0.3797,
"step": 298
},
{
"epoch": 1.37,
"learning_rate": 1.1871866139718167e-05,
"loss": 0.3705,
"step": 299
},
{
"epoch": 1.38,
"learning_rate": 1.1823167285087064e-05,
"loss": 0.3996,
"step": 300
},
{
"epoch": 1.38,
"learning_rate": 1.177442366460337e-05,
"loss": 0.3883,
"step": 301
},
{
"epoch": 1.38,
"learning_rate": 1.1725636475112688e-05,
"loss": 0.3968,
"step": 302
},
{
"epoch": 1.39,
"learning_rate": 1.167680691453039e-05,
"loss": 0.3762,
"step": 303
},
{
"epoch": 1.39,
"learning_rate": 1.1627936181812233e-05,
"loss": 0.4023,
"step": 304
},
{
"epoch": 1.4,
"learning_rate": 1.1579025476924912e-05,
"loss": 0.3884,
"step": 305
},
{
"epoch": 1.4,
"learning_rate": 1.153007600081659e-05,
"loss": 0.4205,
"step": 306
},
{
"epoch": 1.41,
"learning_rate": 1.1481088955387418e-05,
"loss": 0.4153,
"step": 307
},
{
"epoch": 1.41,
"learning_rate": 1.1432065543460016e-05,
"loss": 0.3908,
"step": 308
},
{
"epoch": 1.42,
"learning_rate": 1.1383006968749948e-05,
"loss": 0.4012,
"step": 309
},
{
"epoch": 1.42,
"learning_rate": 1.1333914435836153e-05,
"loss": 0.3788,
"step": 310
},
{
"epoch": 1.43,
"learning_rate": 1.1284789150131388e-05,
"loss": 0.39,
"step": 311
},
{
"epoch": 1.43,
"learning_rate": 1.1235632317852605e-05,
"loss": 0.3781,
"step": 312
},
{
"epoch": 1.43,
"learning_rate": 1.118644514599136e-05,
"loss": 0.3866,
"step": 313
},
{
"epoch": 1.44,
"learning_rate": 1.1137228842284156e-05,
"loss": 0.3831,
"step": 314
},
{
"epoch": 1.44,
"learning_rate": 1.1087984615182797e-05,
"loss": 0.4087,
"step": 315
},
{
"epoch": 1.45,
"learning_rate": 1.1038713673824715e-05,
"loss": 0.3871,
"step": 316
},
{
"epoch": 1.45,
"learning_rate": 1.0989417228003285e-05,
"loss": 0.3844,
"step": 317
},
{
"epoch": 1.46,
"learning_rate": 1.094009648813811e-05,
"loss": 0.3787,
"step": 318
},
{
"epoch": 1.46,
"learning_rate": 1.0890752665245312e-05,
"loss": 0.3753,
"step": 319
},
{
"epoch": 1.47,
"learning_rate": 1.0841386970907786e-05,
"loss": 0.3917,
"step": 320
},
{
"epoch": 1.47,
"learning_rate": 1.0792000617245461e-05,
"loss": 0.3836,
"step": 321
},
{
"epoch": 1.48,
"learning_rate": 1.074259481688553e-05,
"loss": 0.3996,
"step": 322
},
{
"epoch": 1.48,
"learning_rate": 1.0693170782932676e-05,
"loss": 0.3912,
"step": 323
},
{
"epoch": 1.49,
"learning_rate": 1.0643729728939292e-05,
"loss": 0.4158,
"step": 324
},
{
"epoch": 1.49,
"learning_rate": 1.0594272868875677e-05,
"loss": 0.365,
"step": 325
},
{
"epoch": 1.49,
"learning_rate": 1.0544801417100228e-05,
"loss": 0.3951,
"step": 326
},
{
"epoch": 1.5,
"learning_rate": 1.0495316588329634e-05,
"loss": 0.4068,
"step": 327
},
{
"epoch": 1.5,
"learning_rate": 1.044581959760903e-05,
"loss": 0.3909,
"step": 328
},
{
"epoch": 1.51,
"learning_rate": 1.0396311660282182e-05,
"loss": 0.4009,
"step": 329
},
{
"epoch": 1.51,
"learning_rate": 1.0346793991961636e-05,
"loss": 0.4002,
"step": 330
},
{
"epoch": 1.52,
"learning_rate": 1.0297267808498873e-05,
"loss": 0.3741,
"step": 331
},
{
"epoch": 1.52,
"learning_rate": 1.0247734325954448e-05,
"loss": 0.398,
"step": 332
},
{
"epoch": 1.53,
"learning_rate": 1.0198194760568144e-05,
"loss": 0.3939,
"step": 333
},
{
"epoch": 1.53,
"learning_rate": 1.0148650328729097e-05,
"loss": 0.3897,
"step": 334
},
{
"epoch": 1.54,
"learning_rate": 1.009910224694593e-05,
"loss": 0.3933,
"step": 335
},
{
"epoch": 1.54,
"learning_rate": 1.0049551731816902e-05,
"loss": 0.3876,
"step": 336
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 0.3875,
"step": 337
},
{
"epoch": 1.55,
"learning_rate": 9.950448268183101e-06,
"loss": 0.4196,
"step": 338
},
{
"epoch": 1.55,
"learning_rate": 9.900897753054071e-06,
"loss": 0.4326,
"step": 339
},
{
"epoch": 1.56,
"learning_rate": 9.85134967127091e-06,
"loss": 0.4109,
"step": 340
},
{
"epoch": 1.56,
"learning_rate": 9.80180523943186e-06,
"loss": 0.3766,
"step": 341
},
{
"epoch": 1.57,
"learning_rate": 9.752265674045556e-06,
"loss": 0.4007,
"step": 342
},
{
"epoch": 1.57,
"learning_rate": 9.702732191501129e-06,
"loss": 0.3804,
"step": 343
},
{
"epoch": 1.58,
"learning_rate": 9.653206008038364e-06,
"loss": 0.3891,
"step": 344
},
{
"epoch": 1.58,
"learning_rate": 9.603688339717818e-06,
"loss": 0.4009,
"step": 345
},
{
"epoch": 1.59,
"learning_rate": 9.554180402390972e-06,
"loss": 0.3607,
"step": 346
},
{
"epoch": 1.59,
"learning_rate": 9.50468341167037e-06,
"loss": 0.405,
"step": 347
},
{
"epoch": 1.6,
"learning_rate": 9.455198582899773e-06,
"loss": 0.3946,
"step": 348
},
{
"epoch": 1.6,
"learning_rate": 9.405727131124326e-06,
"loss": 0.3944,
"step": 349
},
{
"epoch": 1.6,
"learning_rate": 9.356270271060711e-06,
"loss": 0.4035,
"step": 350
},
{
"epoch": 1.61,
"learning_rate": 9.306829217067327e-06,
"loss": 0.3789,
"step": 351
},
{
"epoch": 1.61,
"learning_rate": 9.257405183114473e-06,
"loss": 0.39,
"step": 352
},
{
"epoch": 1.62,
"learning_rate": 9.20799938275454e-06,
"loss": 0.4013,
"step": 353
},
{
"epoch": 1.62,
"learning_rate": 9.158613029092214e-06,
"loss": 0.3797,
"step": 354
},
{
"epoch": 1.63,
"learning_rate": 9.10924733475469e-06,
"loss": 0.3827,
"step": 355
},
{
"epoch": 1.63,
"learning_rate": 9.059903511861892e-06,
"loss": 0.3887,
"step": 356
},
{
"epoch": 1.64,
"learning_rate": 9.010582771996718e-06,
"loss": 0.3955,
"step": 357
},
{
"epoch": 1.64,
"learning_rate": 8.961286326175288e-06,
"loss": 0.3779,
"step": 358
},
{
"epoch": 1.65,
"learning_rate": 8.912015384817207e-06,
"loss": 0.402,
"step": 359
},
{
"epoch": 1.65,
"learning_rate": 8.862771157715847e-06,
"loss": 0.4148,
"step": 360
},
{
"epoch": 1.65,
"learning_rate": 8.813554854008642e-06,
"loss": 0.3745,
"step": 361
},
{
"epoch": 1.66,
"learning_rate": 8.764367682147396e-06,
"loss": 0.3848,
"step": 362
},
{
"epoch": 1.66,
"learning_rate": 8.715210849868617e-06,
"loss": 0.4093,
"step": 363
},
{
"epoch": 1.67,
"learning_rate": 8.666085564163852e-06,
"loss": 0.4238,
"step": 364
},
{
"epoch": 1.67,
"learning_rate": 8.616993031250059e-06,
"loss": 0.3783,
"step": 365
},
{
"epoch": 1.68,
"learning_rate": 8.567934456539985e-06,
"loss": 0.3886,
"step": 366
},
{
"epoch": 1.68,
"learning_rate": 8.518911044612584e-06,
"loss": 0.41,
"step": 367
},
{
"epoch": 1.69,
"learning_rate": 8.469923999183412e-06,
"loss": 0.3998,
"step": 368
},
{
"epoch": 1.69,
"learning_rate": 8.42097452307509e-06,
"loss": 0.3921,
"step": 369
},
{
"epoch": 1.7,
"learning_rate": 8.372063818187768e-06,
"loss": 0.3969,
"step": 370
},
{
"epoch": 1.7,
"learning_rate": 8.323193085469615e-06,
"loss": 0.4243,
"step": 371
},
{
"epoch": 1.71,
"learning_rate": 8.274363524887315e-06,
"loss": 0.3838,
"step": 372
},
{
"epoch": 1.71,
"learning_rate": 8.225576335396632e-06,
"loss": 0.4145,
"step": 373
},
{
"epoch": 1.71,
"learning_rate": 8.176832714912942e-06,
"loss": 0.3778,
"step": 374
},
{
"epoch": 1.72,
"learning_rate": 8.128133860281838e-06,
"loss": 0.4341,
"step": 375
},
{
"epoch": 1.72,
"learning_rate": 8.079480967249738e-06,
"loss": 0.4378,
"step": 376
},
{
"epoch": 1.73,
"learning_rate": 8.030875230434517e-06,
"loss": 0.4016,
"step": 377
},
{
"epoch": 1.73,
"learning_rate": 7.982317843296192e-06,
"loss": 0.4061,
"step": 378
},
{
"epoch": 1.74,
"learning_rate": 7.933809998107604e-06,
"loss": 0.398,
"step": 379
},
{
"epoch": 1.74,
"learning_rate": 7.885352885925139e-06,
"loss": 0.3965,
"step": 380
},
{
"epoch": 1.75,
"learning_rate": 7.836947696559499e-06,
"loss": 0.3726,
"step": 381
},
{
"epoch": 1.75,
"learning_rate": 7.788595618546474e-06,
"loss": 0.3898,
"step": 382
},
{
"epoch": 1.76,
"learning_rate": 7.740297839117763e-06,
"loss": 0.3583,
"step": 383
},
{
"epoch": 1.76,
"learning_rate": 7.692055544171823e-06,
"loss": 0.3738,
"step": 384
},
{
"epoch": 1.76,
"learning_rate": 7.643869918244759e-06,
"loss": 0.3947,
"step": 385
},
{
"epoch": 1.77,
"learning_rate": 7.595742144481223e-06,
"loss": 0.4034,
"step": 386
},
{
"epoch": 1.77,
"learning_rate": 7.547673404605372e-06,
"loss": 0.384,
"step": 387
},
{
"epoch": 1.78,
"learning_rate": 7.4996648788918505e-06,
"loss": 0.4198,
"step": 388
},
{
"epoch": 1.78,
"learning_rate": 7.4517177461368195e-06,
"loss": 0.4072,
"step": 389
},
{
"epoch": 1.79,
"learning_rate": 7.403833183628995e-06,
"loss": 0.3998,
"step": 390
},
{
"epoch": 1.79,
"learning_rate": 7.356012367120753e-06,
"loss": 0.4055,
"step": 391
},
{
"epoch": 1.8,
"learning_rate": 7.308256470799255e-06,
"loss": 0.4153,
"step": 392
},
{
"epoch": 1.8,
"learning_rate": 7.26056666725762e-06,
"loss": 0.3925,
"step": 393
},
{
"epoch": 1.81,
"learning_rate": 7.212944127466135e-06,
"loss": 0.4064,
"step": 394
},
{
"epoch": 1.81,
"learning_rate": 7.165390020743498e-06,
"loss": 0.4028,
"step": 395
},
{
"epoch": 1.82,
"learning_rate": 7.117905514728107e-06,
"loss": 0.3929,
"step": 396
},
{
"epoch": 1.82,
"learning_rate": 7.070491775349396e-06,
"loss": 0.4253,
"step": 397
},
{
"epoch": 1.82,
"learning_rate": 7.023149966799198e-06,
"loss": 0.4012,
"step": 398
},
{
"epoch": 1.83,
"learning_rate": 6.975881251503169e-06,
"loss": 0.3896,
"step": 399
},
{
"epoch": 1.83,
"learning_rate": 6.928686790092235e-06,
"loss": 0.3987,
"step": 400
},
{
"epoch": 1.84,
"learning_rate": 6.8815677413741074e-06,
"loss": 0.3999,
"step": 401
},
{
"epoch": 1.84,
"learning_rate": 6.834525262304818e-06,
"loss": 0.4174,
"step": 402
},
{
"epoch": 1.85,
"learning_rate": 6.787560507960316e-06,
"loss": 0.3844,
"step": 403
},
{
"epoch": 1.85,
"learning_rate": 6.740674631508105e-06,
"loss": 0.3798,
"step": 404
},
{
"epoch": 1.86,
"learning_rate": 6.693868784178934e-06,
"loss": 0.3733,
"step": 405
},
{
"epoch": 1.86,
"learning_rate": 6.64714411523852e-06,
"loss": 0.3948,
"step": 406
},
{
"epoch": 1.87,
"learning_rate": 6.600501771959338e-06,
"loss": 0.3931,
"step": 407
},
{
"epoch": 1.87,
"learning_rate": 6.553942899592447e-06,
"loss": 0.3851,
"step": 408
},
{
"epoch": 1.87,
"learning_rate": 6.507468641339371e-06,
"loss": 0.3872,
"step": 409
},
{
"epoch": 1.88,
"learning_rate": 6.461080138324025e-06,
"loss": 0.3883,
"step": 410
},
{
"epoch": 1.88,
"learning_rate": 6.414778529564701e-06,
"loss": 0.4104,
"step": 411
},
{
"epoch": 1.89,
"learning_rate": 6.3685649519461035e-06,
"loss": 0.3942,
"step": 412
},
{
"epoch": 1.89,
"learning_rate": 6.322440540191421e-06,
"loss": 0.3965,
"step": 413
},
{
"epoch": 1.9,
"learning_rate": 6.276406426834479e-06,
"loss": 0.393,
"step": 414
},
{
"epoch": 1.9,
"learning_rate": 6.230463742191926e-06,
"loss": 0.3936,
"step": 415
},
{
"epoch": 1.91,
"learning_rate": 6.184613614335476e-06,
"loss": 0.3762,
"step": 416
},
{
"epoch": 1.91,
"learning_rate": 6.138857169064216e-06,
"loss": 0.3824,
"step": 417
},
{
"epoch": 1.92,
"learning_rate": 6.093195529876963e-06,
"loss": 0.3739,
"step": 418
},
{
"epoch": 1.92,
"learning_rate": 6.047629817944672e-06,
"loss": 0.3943,
"step": 419
},
{
"epoch": 1.93,
"learning_rate": 6.002161152082909e-06,
"loss": 0.3796,
"step": 420
},
{
"epoch": 1.93,
"learning_rate": 5.956790648724389e-06,
"loss": 0.4059,
"step": 421
},
{
"epoch": 1.93,
"learning_rate": 5.911519421891546e-06,
"loss": 0.4164,
"step": 422
},
{
"epoch": 1.94,
"learning_rate": 5.866348583169199e-06,
"loss": 0.4223,
"step": 423
},
{
"epoch": 1.94,
"learning_rate": 5.821279241677238e-06,
"loss": 0.3837,
"step": 424
},
{
"epoch": 1.95,
"learning_rate": 5.7763125040434084e-06,
"loss": 0.39,
"step": 425
},
{
"epoch": 1.95,
"learning_rate": 5.731449474376134e-06,
"loss": 0.4024,
"step": 426
},
{
"epoch": 1.96,
"learning_rate": 5.686691254237391e-06,
"loss": 0.3991,
"step": 427
},
{
"epoch": 1.96,
"learning_rate": 5.6420389426156815e-06,
"loss": 0.3815,
"step": 428
},
{
"epoch": 1.97,
"learning_rate": 5.597493635899048e-06,
"loss": 0.3908,
"step": 429
},
{
"epoch": 1.97,
"learning_rate": 5.553056427848136e-06,
"loss": 0.3969,
"step": 430
},
{
"epoch": 1.98,
"learning_rate": 5.508728409569354e-06,
"loss": 0.3771,
"step": 431
},
{
"epoch": 1.98,
"learning_rate": 5.4645106694880735e-06,
"loss": 0.3837,
"step": 432
},
{
"epoch": 1.98,
"learning_rate": 5.420404293321909e-06,
"loss": 0.3788,
"step": 433
},
{
"epoch": 1.99,
"learning_rate": 5.376410364054052e-06,
"loss": 0.4118,
"step": 434
},
{
"epoch": 1.99,
"learning_rate": 5.332529961906699e-06,
"loss": 0.3804,
"step": 435
},
{
"epoch": 2.0,
"learning_rate": 5.288764164314499e-06,
"loss": 0.4005,
"step": 436
},
{
"epoch": 2.0,
"learning_rate": 5.245114045898118e-06,
"loss": 0.308,
"step": 437
},
{
"epoch": 2.01,
"learning_rate": 5.201580678437852e-06,
"loss": 0.2691,
"step": 438
},
{
"epoch": 2.01,
"learning_rate": 5.158165130847301e-06,
"loss": 0.2466,
"step": 439
},
{
"epoch": 2.02,
"learning_rate": 5.11486846914713e-06,
"loss": 0.2611,
"step": 440
},
{
"epoch": 2.02,
"learning_rate": 5.071691756438897e-06,
"loss": 0.2371,
"step": 441
},
{
"epoch": 2.03,
"learning_rate": 5.028636052878938e-06,
"loss": 0.2318,
"step": 442
},
{
"epoch": 2.03,
"learning_rate": 4.98570241565235e-06,
"loss": 0.2635,
"step": 443
},
{
"epoch": 2.04,
"learning_rate": 4.942891898947024e-06,
"loss": 0.2503,
"step": 444
},
{
"epoch": 2.04,
"learning_rate": 4.900205553927761e-06,
"loss": 0.2528,
"step": 445
},
{
"epoch": 2.04,
"learning_rate": 4.85764442871047e-06,
"loss": 0.2505,
"step": 446
},
{
"epoch": 2.05,
"learning_rate": 4.815209568336416e-06,
"loss": 0.2666,
"step": 447
},
{
"epoch": 2.05,
"learning_rate": 4.772902014746583e-06,
"loss": 0.2561,
"step": 448
},
{
"epoch": 2.06,
"learning_rate": 4.730722806756069e-06,
"loss": 0.2466,
"step": 449
},
{
"epoch": 2.06,
"learning_rate": 4.68867298002859e-06,
"loss": 0.249,
"step": 450
},
{
"epoch": 2.07,
"learning_rate": 4.646753567051052e-06,
"loss": 0.2375,
"step": 451
},
{
"epoch": 2.07,
"learning_rate": 4.604965597108192e-06,
"loss": 0.2388,
"step": 452
},
{
"epoch": 2.08,
"learning_rate": 4.563310096257309e-06,
"loss": 0.2624,
"step": 453
},
{
"epoch": 2.08,
"learning_rate": 4.521788087303074e-06,
"loss": 0.2565,
"step": 454
},
{
"epoch": 2.09,
"learning_rate": 4.480400589772409e-06,
"loss": 0.2565,
"step": 455
},
{
"epoch": 2.09,
"learning_rate": 4.439148619889451e-06,
"loss": 0.271,
"step": 456
},
{
"epoch": 2.09,
"learning_rate": 4.398033190550626e-06,
"loss": 0.2154,
"step": 457
},
{
"epoch": 2.1,
"learning_rate": 4.357055311299736e-06,
"loss": 0.2548,
"step": 458
},
{
"epoch": 2.1,
"learning_rate": 4.316215988303204e-06,
"loss": 0.2664,
"step": 459
},
{
"epoch": 2.11,
"learning_rate": 4.275516224325356e-06,
"loss": 0.2496,
"step": 460
},
{
"epoch": 2.11,
"learning_rate": 4.2349570187037995e-06,
"loss": 0.2491,
"step": 461
},
{
"epoch": 2.12,
"learning_rate": 4.194539367324888e-06,
"loss": 0.2364,
"step": 462
},
{
"epoch": 2.12,
"learning_rate": 4.154264262599268e-06,
"loss": 0.2337,
"step": 463
},
{
"epoch": 2.13,
"learning_rate": 4.114132693437511e-06,
"loss": 0.2436,
"step": 464
},
{
"epoch": 2.13,
"learning_rate": 4.074145645225831e-06,
"loss": 0.214,
"step": 465
},
{
"epoch": 2.14,
"learning_rate": 4.034304099801891e-06,
"loss": 0.2546,
"step": 466
},
{
"epoch": 2.14,
"learning_rate": 3.994609035430695e-06,
"loss": 0.2525,
"step": 467
},
{
"epoch": 2.15,
"learning_rate": 3.955061426780562e-06,
"loss": 0.2376,
"step": 468
},
{
"epoch": 2.15,
"learning_rate": 3.915662244899206e-06,
"loss": 0.2485,
"step": 469
},
{
"epoch": 2.15,
"learning_rate": 3.876412457189883e-06,
"loss": 0.2488,
"step": 470
},
{
"epoch": 2.16,
"learning_rate": 3.83731302738764e-06,
"loss": 0.2323,
"step": 471
},
{
"epoch": 2.16,
"learning_rate": 3.7983649155356537e-06,
"loss": 0.2256,
"step": 472
},
{
"epoch": 2.17,
"learning_rate": 3.7595690779616555e-06,
"loss": 0.2402,
"step": 473
},
{
"epoch": 2.17,
"learning_rate": 3.7209264672544498e-06,
"loss": 0.2299,
"step": 474
},
{
"epoch": 2.18,
"learning_rate": 3.6824380322405273e-06,
"loss": 0.2454,
"step": 475
},
{
"epoch": 2.18,
"learning_rate": 3.6441047179607616e-06,
"loss": 0.2483,
"step": 476
},
{
"epoch": 2.19,
"learning_rate": 3.6059274656472133e-06,
"loss": 0.2586,
"step": 477
},
{
"epoch": 2.19,
"learning_rate": 3.56790721270001e-06,
"loss": 0.245,
"step": 478
},
{
"epoch": 2.2,
"learning_rate": 3.530044892664335e-06,
"loss": 0.2452,
"step": 479
},
{
"epoch": 2.2,
"learning_rate": 3.492341435207509e-06,
"loss": 0.2273,
"step": 480
},
{
"epoch": 2.2,
"learning_rate": 3.4547977660961506e-06,
"loss": 0.2676,
"step": 481
},
{
"epoch": 2.21,
"learning_rate": 3.417414807173457e-06,
"loss": 0.2862,
"step": 482
},
{
"epoch": 2.21,
"learning_rate": 3.380193476336564e-06,
"loss": 0.2408,
"step": 483
},
{
"epoch": 2.22,
"learning_rate": 3.343134687514007e-06,
"loss": 0.2524,
"step": 484
},
{
"epoch": 2.22,
"learning_rate": 3.3062393506432843e-06,
"loss": 0.2409,
"step": 485
},
{
"epoch": 2.23,
"learning_rate": 3.269508371648512e-06,
"loss": 0.2479,
"step": 486
},
{
"epoch": 2.23,
"learning_rate": 3.232942652418185e-06,
"loss": 0.2586,
"step": 487
},
{
"epoch": 2.24,
"learning_rate": 3.1965430907830164e-06,
"loss": 0.243,
"step": 488
},
{
"epoch": 2.24,
"learning_rate": 3.1603105804939137e-06,
"loss": 0.2356,
"step": 489
},
{
"epoch": 2.25,
"learning_rate": 3.124246011200018e-06,
"loss": 0.2501,
"step": 490
},
{
"epoch": 2.25,
"learning_rate": 3.0883502684268753e-06,
"loss": 0.2669,
"step": 491
},
{
"epoch": 2.26,
"learning_rate": 3.052624233554672e-06,
"loss": 0.2252,
"step": 492
},
{
"epoch": 2.26,
"learning_rate": 3.0170687837966093e-06,
"loss": 0.2598,
"step": 493
},
{
"epoch": 2.26,
"learning_rate": 2.9816847921773616e-06,
"loss": 0.2389,
"step": 494
},
{
"epoch": 2.27,
"learning_rate": 2.9464731275116355e-06,
"loss": 0.2464,
"step": 495
},
{
"epoch": 2.27,
"learning_rate": 2.911434654382843e-06,
"loss": 0.2476,
"step": 496
},
{
"epoch": 2.28,
"learning_rate": 2.876570233121867e-06,
"loss": 0.2375,
"step": 497
},
{
"epoch": 2.28,
"learning_rate": 2.8418807197859423e-06,
"loss": 0.2472,
"step": 498
},
{
"epoch": 2.29,
"learning_rate": 2.8073669661376325e-06,
"loss": 0.2643,
"step": 499
},
{
"epoch": 2.29,
"learning_rate": 2.773029819623916e-06,
"loss": 0.2446,
"step": 500
},
{
"epoch": 2.3,
"learning_rate": 2.7388701233553806e-06,
"loss": 0.2544,
"step": 501
},
{
"epoch": 2.3,
"learning_rate": 2.704888716085513e-06,
"loss": 0.2338,
"step": 502
},
{
"epoch": 2.31,
"learning_rate": 2.6710864321901255e-06,
"loss": 0.2452,
"step": 503
},
{
"epoch": 2.31,
"learning_rate": 2.6374641016468416e-06,
"loss": 0.2544,
"step": 504
},
{
"epoch": 2.31,
"learning_rate": 2.6040225500147365e-06,
"loss": 0.2386,
"step": 505
},
{
"epoch": 2.32,
"learning_rate": 2.570762598414052e-06,
"loss": 0.2386,
"step": 506
},
{
"epoch": 2.32,
"learning_rate": 2.537685063506048e-06,
"loss": 0.2498,
"step": 507
},
{
"epoch": 2.33,
"learning_rate": 2.5047907574729446e-06,
"loss": 0.2294,
"step": 508
},
{
"epoch": 2.33,
"learning_rate": 2.47208048799798e-06,
"loss": 0.2408,
"step": 509
},
{
"epoch": 2.34,
"learning_rate": 2.4395550582455774e-06,
"loss": 0.268,
"step": 510
},
{
"epoch": 2.34,
"learning_rate": 2.407215266841624e-06,
"loss": 0.2575,
"step": 511
},
{
"epoch": 2.35,
"learning_rate": 2.3750619078538663e-06,
"loss": 0.244,
"step": 512
},
{
"epoch": 2.35,
"learning_rate": 2.3430957707724057e-06,
"loss": 0.2641,
"step": 513
},
{
"epoch": 2.36,
"learning_rate": 2.3113176404903226e-06,
"loss": 0.2429,
"step": 514
},
{
"epoch": 2.36,
"learning_rate": 2.279728297284394e-06,
"loss": 0.2208,
"step": 515
},
{
"epoch": 2.37,
"learning_rate": 2.24832851679594e-06,
"loss": 0.2324,
"step": 516
},
{
"epoch": 2.37,
"learning_rate": 2.217119070011781e-06,
"loss": 0.2445,
"step": 517
},
{
"epoch": 2.37,
"learning_rate": 2.186100723245299e-06,
"loss": 0.2358,
"step": 518
},
{
"epoch": 2.38,
"learning_rate": 2.155274238117633e-06,
"loss": 0.2515,
"step": 519
},
{
"epoch": 2.38,
"learning_rate": 2.1246403715389675e-06,
"loss": 0.2297,
"step": 520
},
{
"epoch": 2.39,
"learning_rate": 2.094199875689954e-06,
"loss": 0.2435,
"step": 521
},
{
"epoch": 2.39,
"learning_rate": 2.063953498003239e-06,
"loss": 0.2678,
"step": 522
},
{
"epoch": 2.4,
"learning_rate": 2.0339019811451154e-06,
"loss": 0.2391,
"step": 523
},
{
"epoch": 2.4,
"learning_rate": 2.004046062997279e-06,
"loss": 0.2507,
"step": 524
},
{
"epoch": 2.41,
"learning_rate": 1.9743864766387198e-06,
"loss": 0.2638,
"step": 525
},
{
"epoch": 2.41,
"learning_rate": 1.9449239503277197e-06,
"loss": 0.2337,
"step": 526
},
{
"epoch": 2.42,
"learning_rate": 1.915659207483964e-06,
"loss": 0.2499,
"step": 527
},
{
"epoch": 2.42,
"learning_rate": 1.8865929666707895e-06,
"loss": 0.2398,
"step": 528
},
{
"epoch": 2.42,
"learning_rate": 1.857725941577534e-06,
"loss": 0.2344,
"step": 529
},
{
"epoch": 2.43,
"learning_rate": 1.8290588410020116e-06,
"loss": 0.242,
"step": 530
},
{
"epoch": 2.43,
"learning_rate": 1.8005923688331152e-06,
"loss": 0.2239,
"step": 531
},
{
"epoch": 2.44,
"learning_rate": 1.7723272240335264e-06,
"loss": 0.2541,
"step": 532
},
{
"epoch": 2.44,
"learning_rate": 1.744264100622558e-06,
"loss": 0.2569,
"step": 533
},
{
"epoch": 2.45,
"learning_rate": 1.7164036876591106e-06,
"loss": 0.2348,
"step": 534
},
{
"epoch": 2.45,
"learning_rate": 1.6887466692247556e-06,
"loss": 0.2576,
"step": 535
},
{
"epoch": 2.46,
"learning_rate": 1.6612937244069326e-06,
"loss": 0.249,
"step": 536
},
{
"epoch": 2.46,
"learning_rate": 1.6340455272822896e-06,
"loss": 0.2381,
"step": 537
},
{
"epoch": 2.47,
"learning_rate": 1.6070027469001115e-06,
"loss": 0.2363,
"step": 538
},
{
"epoch": 2.47,
"learning_rate": 1.5801660472659075e-06,
"loss": 0.2388,
"step": 539
},
{
"epoch": 2.48,
"learning_rate": 1.5535360873251026e-06,
"loss": 0.2289,
"step": 540
},
{
"epoch": 2.48,
"learning_rate": 1.5271135209468546e-06,
"loss": 0.2513,
"step": 541
},
{
"epoch": 2.48,
"learning_rate": 1.5008989969080067e-06,
"loss": 0.259,
"step": 542
},
{
"epoch": 2.49,
"learning_rate": 1.4748931588771486e-06,
"loss": 0.2364,
"step": 543
},
{
"epoch": 2.49,
"learning_rate": 1.4490966453988187e-06,
"loss": 0.2582,
"step": 544
},
{
"epoch": 2.5,
"learning_rate": 1.423510089877823e-06,
"loss": 0.2357,
"step": 545
},
{
"epoch": 2.5,
"learning_rate": 1.3981341205636823e-06,
"loss": 0.2291,
"step": 546
},
{
"epoch": 2.51,
"learning_rate": 1.3729693605352057e-06,
"loss": 0.252,
"step": 547
},
{
"epoch": 2.51,
"learning_rate": 1.3480164276851925e-06,
"loss": 0.2429,
"step": 548
},
{
"epoch": 2.52,
"learning_rate": 1.3232759347052604e-06,
"loss": 0.2409,
"step": 549
},
{
"epoch": 2.52,
"learning_rate": 1.2987484890708024e-06,
"loss": 0.2284,
"step": 550
},
{
"epoch": 2.53,
"learning_rate": 1.2744346930260687e-06,
"loss": 0.2263,
"step": 551
},
{
"epoch": 2.53,
"learning_rate": 1.250335143569381e-06,
"loss": 0.2392,
"step": 552
},
{
"epoch": 2.53,
"learning_rate": 1.226450432438474e-06,
"loss": 0.2473,
"step": 553
},
{
"epoch": 2.54,
"learning_rate": 1.2027811460959648e-06,
"loss": 0.2601,
"step": 554
},
{
"epoch": 2.54,
"learning_rate": 1.1793278657149532e-06,
"loss": 0.255,
"step": 555
},
{
"epoch": 2.55,
"learning_rate": 1.1560911671647535e-06,
"loss": 0.2579,
"step": 556
},
{
"epoch": 2.55,
"learning_rate": 1.1330716209967506e-06,
"loss": 0.2317,
"step": 557
},
{
"epoch": 2.56,
"learning_rate": 1.110269792430393e-06,
"loss": 0.2527,
"step": 558
},
{
"epoch": 2.56,
"learning_rate": 1.0876862413393196e-06,
"loss": 0.2591,
"step": 559
},
{
"epoch": 2.57,
"learning_rate": 1.0653215222376045e-06,
"loss": 0.2243,
"step": 560
},
{
"epoch": 2.57,
"learning_rate": 1.0431761842661437e-06,
"loss": 0.2433,
"step": 561
},
{
"epoch": 2.58,
"learning_rate": 1.021250771179173e-06,
"loss": 0.2438,
"step": 562
},
{
"epoch": 2.58,
"learning_rate": 9.995458213309184e-07,
"loss": 0.2494,
"step": 563
},
{
"epoch": 2.59,
"learning_rate": 9.780618676623722e-07,
"loss": 0.2426,
"step": 564
},
{
"epoch": 2.59,
"learning_rate": 9.56799437688214e-07,
"loss": 0.2514,
"step": 565
},
{
"epoch": 2.59,
"learning_rate": 9.357590534838534e-07,
"loss": 0.2477,
"step": 566
},
{
"epoch": 2.6,
"learning_rate": 9.149412316726081e-07,
"loss": 0.2353,
"step": 567
},
{
"epoch": 2.6,
"learning_rate": 8.943464834130288e-07,
"loss": 0.249,
"step": 568
},
{
"epoch": 2.61,
"learning_rate": 8.739753143863383e-07,
"loss": 0.2286,
"step": 569
},
{
"epoch": 2.61,
"learning_rate": 8.538282247840201e-07,
"loss": 0.2453,
"step": 570
},
{
"epoch": 2.62,
"learning_rate": 8.339057092955383e-07,
"loss": 0.2489,
"step": 571
},
{
"epoch": 2.62,
"learning_rate": 8.142082570961851e-07,
"loss": 0.2373,
"step": 572
},
{
"epoch": 2.63,
"learning_rate": 7.947363518350748e-07,
"loss": 0.2366,
"step": 573
},
{
"epoch": 2.63,
"learning_rate": 7.754904716232647e-07,
"loss": 0.2285,
"step": 574
},
{
"epoch": 2.64,
"learning_rate": 7.564710890220183e-07,
"loss": 0.2732,
"step": 575
},
{
"epoch": 2.64,
"learning_rate": 7.376786710312045e-07,
"loss": 0.245,
"step": 576
},
{
"epoch": 2.64,
"learning_rate": 7.191136790778208e-07,
"loss": 0.2544,
"step": 577
},
{
"epoch": 2.65,
"learning_rate": 7.007765690046775e-07,
"loss": 0.2482,
"step": 578
},
{
"epoch": 2.65,
"learning_rate": 6.826677910591928e-07,
"loss": 0.2538,
"step": 579
},
{
"epoch": 2.66,
"learning_rate": 6.647877898823463e-07,
"loss": 0.2493,
"step": 580
},
{
"epoch": 2.66,
"learning_rate": 6.47137004497751e-07,
"loss": 0.2654,
"step": 581
},
{
"epoch": 2.67,
"learning_rate": 6.297158683008897e-07,
"loss": 0.2262,
"step": 582
},
{
"epoch": 2.67,
"learning_rate": 6.125248090484581e-07,
"loss": 0.2535,
"step": 583
},
{
"epoch": 2.68,
"learning_rate": 5.955642488478675e-07,
"loss": 0.2478,
"step": 584
},
{
"epoch": 2.68,
"learning_rate": 5.788346041468796e-07,
"loss": 0.251,
"step": 585
},
{
"epoch": 2.69,
"learning_rate": 5.623362857233838e-07,
"loss": 0.2515,
"step": 586
},
{
"epoch": 2.69,
"learning_rate": 5.4606969867531e-07,
"loss": 0.2181,
"step": 587
},
{
"epoch": 2.7,
"learning_rate": 5.30035242410678e-07,
"loss": 0.2642,
"step": 588
},
{
"epoch": 2.7,
"learning_rate": 5.142333106377961e-07,
"loss": 0.237,
"step": 589
},
{
"epoch": 2.7,
"learning_rate": 4.986642913555895e-07,
"loss": 0.2331,
"step": 590
},
{
"epoch": 2.71,
"learning_rate": 4.833285668440757e-07,
"loss": 0.2404,
"step": 591
},
{
"epoch": 2.71,
"learning_rate": 4.6822651365497686e-07,
"loss": 0.2496,
"step": 592
},
{
"epoch": 2.72,
"learning_rate": 4.533585026024789e-07,
"loss": 0.2408,
"step": 593
},
{
"epoch": 2.72,
"learning_rate": 4.387248987541182e-07,
"loss": 0.2638,
"step": 594
},
{
"epoch": 2.73,
"learning_rate": 4.2432606142182145e-07,
"loss": 0.2188,
"step": 595
},
{
"epoch": 2.73,
"learning_rate": 4.1016234415308553e-07,
"loss": 0.2401,
"step": 596
},
{
"epoch": 2.74,
"learning_rate": 3.9623409472229535e-07,
"loss": 0.26,
"step": 597
},
{
"epoch": 2.74,
"learning_rate": 3.8254165512218276e-07,
"loss": 0.2457,
"step": 598
},
{
"epoch": 2.75,
"learning_rate": 3.690853615554302e-07,
"loss": 0.2252,
"step": 599
},
{
"epoch": 2.75,
"learning_rate": 3.5586554442641587e-07,
"loss": 0.2324,
"step": 600
},
{
"epoch": 2.75,
"learning_rate": 3.4288252833310277e-07,
"loss": 0.2325,
"step": 601
},
{
"epoch": 2.76,
"learning_rate": 3.3013663205906597e-07,
"loss": 0.2282,
"step": 602
},
{
"epoch": 2.76,
"learning_rate": 3.176281685656646e-07,
"loss": 0.2429,
"step": 603
},
{
"epoch": 2.77,
"learning_rate": 3.0535744498435993e-07,
"loss": 0.2343,
"step": 604
},
{
"epoch": 2.77,
"learning_rate": 2.933247626091751e-07,
"loss": 0.2384,
"step": 605
},
{
"epoch": 2.78,
"learning_rate": 2.815304168892918e-07,
"loss": 0.2244,
"step": 606
},
{
"epoch": 2.78,
"learning_rate": 2.6997469742180093e-07,
"loss": 0.2234,
"step": 607
},
{
"epoch": 2.79,
"learning_rate": 2.586578879445922e-07,
"loss": 0.2492,
"step": 608
},
{
"epoch": 2.79,
"learning_rate": 2.4758026632938026e-07,
"loss": 0.2465,
"step": 609
},
{
"epoch": 2.8,
"learning_rate": 2.367421045748908e-07,
"loss": 0.2211,
"step": 610
},
{
"epoch": 2.8,
"learning_rate": 2.2614366880017723e-07,
"loss": 0.236,
"step": 611
},
{
"epoch": 2.81,
"learning_rate": 2.1578521923808714e-07,
"loss": 0.2437,
"step": 612
},
{
"epoch": 2.81,
"learning_rate": 2.0566701022887047e-07,
"loss": 0.2728,
"step": 613
},
{
"epoch": 2.81,
"learning_rate": 1.9578929021394022e-07,
"loss": 0.2821,
"step": 614
},
{
"epoch": 2.82,
"learning_rate": 1.8615230172976507e-07,
"loss": 0.2479,
"step": 615
},
{
"epoch": 2.82,
"learning_rate": 1.767562814019208e-07,
"loss": 0.2439,
"step": 616
},
{
"epoch": 2.83,
"learning_rate": 1.67601459939275e-07,
"loss": 0.2389,
"step": 617
},
{
"epoch": 2.83,
"learning_rate": 1.586880621283249e-07,
"loss": 0.2518,
"step": 618
},
{
"epoch": 2.84,
"learning_rate": 1.500163068276772e-07,
"loss": 0.2242,
"step": 619
},
{
"epoch": 2.84,
"learning_rate": 1.41586406962676e-07,
"loss": 0.2334,
"step": 620
},
{
"epoch": 2.85,
"learning_rate": 1.3339856952017115e-07,
"loss": 0.2491,
"step": 621
},
{
"epoch": 2.85,
"learning_rate": 1.2545299554343804e-07,
"loss": 0.2298,
"step": 622
},
{
"epoch": 2.86,
"learning_rate": 1.1774988012724364e-07,
"loss": 0.2422,
"step": 623
},
{
"epoch": 2.86,
"learning_rate": 1.1028941241305047e-07,
"loss": 0.2355,
"step": 624
},
{
"epoch": 2.86,
"learning_rate": 1.0307177558437686e-07,
"loss": 0.2346,
"step": 625
},
{
"epoch": 2.87,
"learning_rate": 9.609714686229954e-08,
"loss": 0.2243,
"step": 626
},
{
"epoch": 2.87,
"learning_rate": 8.936569750109702e-08,
"loss": 0.2341,
"step": 627
},
{
"epoch": 2.88,
"learning_rate": 8.287759278405083e-08,
"loss": 0.2421,
"step": 628
},
{
"epoch": 2.88,
"learning_rate": 7.663299201938201e-08,
"loss": 0.2465,
"step": 629
},
{
"epoch": 2.89,
"learning_rate": 7.063204853634543e-08,
"loss": 0.2627,
"step": 630
},
{
"epoch": 2.89,
"learning_rate": 6.487490968145715e-08,
"loss": 0.2439,
"step": 631
},
{
"epoch": 2.9,
"learning_rate": 5.9361716814883006e-08,
"loss": 0.2243,
"step": 632
},
{
"epoch": 2.9,
"learning_rate": 5.409260530696681e-08,
"loss": 0.2365,
"step": 633
},
{
"epoch": 2.91,
"learning_rate": 4.906770453490195e-08,
"loss": 0.2489,
"step": 634
},
{
"epoch": 2.91,
"learning_rate": 4.428713787955841e-08,
"loss": 0.215,
"step": 635
},
{
"epoch": 2.92,
"learning_rate": 3.9751022722455123e-08,
"loss": 0.2372,
"step": 636
},
{
"epoch": 2.92,
"learning_rate": 3.545947044287346e-08,
"loss": 0.2491,
"step": 637
},
{
"epoch": 2.92,
"learning_rate": 3.141258641512379e-08,
"loss": 0.2172,
"step": 638
},
{
"epoch": 2.93,
"learning_rate": 2.7610470005959844e-08,
"loss": 0.2363,
"step": 639
},
{
"epoch": 2.93,
"learning_rate": 2.4053214572137274e-08,
"loss": 0.2522,
"step": 640
},
{
"epoch": 2.94,
"learning_rate": 2.0740907458122184e-08,
"loss": 0.2435,
"step": 641
},
{
"epoch": 2.94,
"learning_rate": 1.7673629993943954e-08,
"loss": 0.2528,
"step": 642
},
{
"epoch": 2.95,
"learning_rate": 1.4851457493204602e-08,
"loss": 0.2396,
"step": 643
},
{
"epoch": 2.95,
"learning_rate": 1.2274459251220283e-08,
"loss": 0.2462,
"step": 644
},
{
"epoch": 2.96,
"learning_rate": 9.942698543330409e-09,
"loss": 0.2371,
"step": 645
},
{
"epoch": 2.96,
"learning_rate": 7.856232623332238e-09,
"loss": 0.2588,
"step": 646
},
{
"epoch": 2.97,
"learning_rate": 6.015112722087546e-09,
"loss": 0.2434,
"step": 647
},
{
"epoch": 2.97,
"learning_rate": 4.419384046253638e-09,
"loss": 0.2185,
"step": 648
},
{
"epoch": 2.97,
"learning_rate": 3.0690857771809023e-09,
"loss": 0.2563,
"step": 649
},
{
"epoch": 2.98,
"learning_rate": 1.9642510699469096e-09,
"loss": 0.2227,
"step": 650
},
{
"epoch": 2.98,
"learning_rate": 1.1049070525426254e-09,
"loss": 0.2365,
"step": 651
},
{
"epoch": 2.99,
"learning_rate": 4.910748252107133e-10,
"loss": 0.2518,
"step": 652
},
{
"epoch": 2.99,
"learning_rate": 1.227694599192919e-10,
"loss": 0.2351,
"step": 653
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.2667,
"step": 654
},
{
"epoch": 3.0,
"step": 654,
"total_flos": 4.514766325578465e+17,
"train_loss": 0.43864560537382,
"train_runtime": 55082.109,
"train_samples_per_second": 1.521,
"train_steps_per_second": 0.012
}
],
"max_steps": 654,
"num_train_epochs": 3,
"total_flos": 4.514766325578465e+17,
"trial_name": null,
"trial_params": null
}