| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 689, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05805515239477504, | |
| "grad_norm": 0.600770890712738, | |
| "learning_rate": 2.9999908009303982e-05, | |
| "loss": 2.8908, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11611030478955008, | |
| "grad_norm": 0.3810243308544159, | |
| "learning_rate": 2.998887064264453e-05, | |
| "loss": 2.6786, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1741654571843251, | |
| "grad_norm": 0.2603137493133545, | |
| "learning_rate": 2.9959452370912904e-05, | |
| "loss": 2.5845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23222060957910015, | |
| "grad_norm": 0.2289140671491623, | |
| "learning_rate": 2.9911693281561532e-05, | |
| "loss": 2.4006, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29027576197387517, | |
| "grad_norm": 0.18332642316818237, | |
| "learning_rate": 2.9845658454559736e-05, | |
| "loss": 2.2503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3483309143686502, | |
| "grad_norm": 0.21847300231456757, | |
| "learning_rate": 2.9761437873711118e-05, | |
| "loss": 2.0564, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40638606676342526, | |
| "grad_norm": 0.2699638307094574, | |
| "learning_rate": 2.9659146304035112e-05, | |
| "loss": 1.8541, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4644412191582003, | |
| "grad_norm": 0.17481808364391327, | |
| "learning_rate": 2.953892313537998e-05, | |
| "loss": 1.5994, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5224963715529753, | |
| "grad_norm": 0.12553584575653076, | |
| "learning_rate": 2.9400932192480125e-05, | |
| "loss": 1.4072, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5805515239477503, | |
| "grad_norm": 0.12803253531455994, | |
| "learning_rate": 2.9245361511716764e-05, | |
| "loss": 1.3509, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6386066763425254, | |
| "grad_norm": 0.0883030965924263, | |
| "learning_rate": 2.907242308488601e-05, | |
| "loss": 1.3609, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6966618287373004, | |
| "grad_norm": 0.08672440052032471, | |
| "learning_rate": 2.8882352570323616e-05, | |
| "loss": 1.3838, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 0.08096282929182053, | |
| "learning_rate": 2.8675408971779997e-05, | |
| "loss": 1.3488, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8127721335268505, | |
| "grad_norm": 0.08677352964878082, | |
| "learning_rate": 2.8451874285483073e-05, | |
| "loss": 1.3902, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8708272859216255, | |
| "grad_norm": 0.06741151958703995, | |
| "learning_rate": 2.8212053115869935e-05, | |
| "loss": 1.319, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9288824383164006, | |
| "grad_norm": 0.0820663794875145, | |
| "learning_rate": 2.7956272260510948e-05, | |
| "loss": 1.3725, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9869375907111756, | |
| "grad_norm": 0.06830213963985443, | |
| "learning_rate": 2.768488026479187e-05, | |
| "loss": 1.3809, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0449927431059507, | |
| "grad_norm": 0.08063437789678574, | |
| "learning_rate": 2.7398246946960864e-05, | |
| "loss": 1.286, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1030478955007257, | |
| "grad_norm": 0.07576021552085876, | |
| "learning_rate": 2.7096762894187533e-05, | |
| "loss": 1.3281, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1611030478955007, | |
| "grad_norm": 0.06808394193649292, | |
| "learning_rate": 2.678083893032079e-05, | |
| "loss": 1.3432, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2191582002902757, | |
| "grad_norm": 0.06429944187402725, | |
| "learning_rate": 2.6450905556070718e-05, | |
| "loss": 1.3108, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2772133526850509, | |
| "grad_norm": 0.07570013403892517, | |
| "learning_rate": 2.610741236237734e-05, | |
| "loss": 1.2846, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.3352685050798259, | |
| "grad_norm": 0.0730566531419754, | |
| "learning_rate": 2.5750827417765714e-05, | |
| "loss": 1.2743, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3933236574746009, | |
| "grad_norm": 0.07746976613998413, | |
| "learning_rate": 2.5381636630522056e-05, | |
| "loss": 1.2424, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.4513788098693758, | |
| "grad_norm": 0.063927061855793, | |
| "learning_rate": 2.50003430865602e-05, | |
| "loss": 1.3057, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.509433962264151, | |
| "grad_norm": 0.06818998605012894, | |
| "learning_rate": 2.4607466363880555e-05, | |
| "loss": 1.2931, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.567489114658926, | |
| "grad_norm": 0.07596269994974136, | |
| "learning_rate": 2.4203541824555744e-05, | |
| "loss": 1.3029, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.625544267053701, | |
| "grad_norm": 0.07179366797208786, | |
| "learning_rate": 2.378911988520776e-05, | |
| "loss": 1.2844, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.683599419448476, | |
| "grad_norm": 0.06046036258339882, | |
| "learning_rate": 2.33647652669707e-05, | |
| "loss": 1.3078, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.741654571843251, | |
| "grad_norm": 0.07098483294248581, | |
| "learning_rate": 2.2931056225961137e-05, | |
| "loss": 1.3307, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.799709724238026, | |
| "grad_norm": 0.07308895885944366, | |
| "learning_rate": 2.2488583765304748e-05, | |
| "loss": 1.2819, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.8577648766328012, | |
| "grad_norm": 0.06851565092802048, | |
| "learning_rate": 2.203795082979298e-05, | |
| "loss": 1.267, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.9158200290275762, | |
| "grad_norm": 0.07384185492992401, | |
| "learning_rate": 2.1579771484267097e-05, | |
| "loss": 1.2629, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.9738751814223512, | |
| "grad_norm": 0.0664062350988388, | |
| "learning_rate": 2.111467007684928e-05, | |
| "loss": 1.2841, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0319303338171264, | |
| "grad_norm": 0.07113119959831238, | |
| "learning_rate": 2.0643280388160994e-05, | |
| "loss": 1.2779, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0899854862119014, | |
| "grad_norm": 0.07706930488348007, | |
| "learning_rate": 2.0166244767687922e-05, | |
| "loss": 1.2854, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.1480406386066764, | |
| "grad_norm": 0.06886892020702362, | |
| "learning_rate": 1.968421325846838e-05, | |
| "loss": 1.2983, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.2060957910014514, | |
| "grad_norm": 0.07846487313508987, | |
| "learning_rate": 1.919784271129792e-05, | |
| "loss": 1.286, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.2641509433962264, | |
| "grad_norm": 0.09121862053871155, | |
| "learning_rate": 1.8707795889657207e-05, | |
| "loss": 1.2774, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.3222060957910013, | |
| "grad_norm": 0.07675393670797348, | |
| "learning_rate": 1.8214740566582862e-05, | |
| "loss": 1.2635, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.3802612481857763, | |
| "grad_norm": 0.06239638477563858, | |
| "learning_rate": 1.7719348614711877e-05, | |
| "loss": 1.2833, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.4383164005805513, | |
| "grad_norm": 0.0633472129702568, | |
| "learning_rate": 1.7222295090739667e-05, | |
| "loss": 1.2657, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.4963715529753268, | |
| "grad_norm": 0.0839238315820694, | |
| "learning_rate": 1.672425731553926e-05, | |
| "loss": 1.2424, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.5544267053701017, | |
| "grad_norm": 0.061606671661138535, | |
| "learning_rate": 1.6225913951195186e-05, | |
| "loss": 1.2802, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.6124818577648767, | |
| "grad_norm": 0.07224655896425247, | |
| "learning_rate": 1.5727944076209725e-05, | |
| "loss": 1.2556, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.6705370101596517, | |
| "grad_norm": 0.07351450622081757, | |
| "learning_rate": 1.5231026260141692e-05, | |
| "loss": 1.292, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.7285921625544267, | |
| "grad_norm": 0.06462671607732773, | |
| "learning_rate": 1.4735837638938767e-05, | |
| "loss": 1.2588, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.7866473149492017, | |
| "grad_norm": 0.0673007071018219, | |
| "learning_rate": 1.4243052992223376e-05, | |
| "loss": 1.2889, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.8447024673439767, | |
| "grad_norm": 0.06969607621431351, | |
| "learning_rate": 1.3753343823789447e-05, | |
| "loss": 1.2591, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.9027576197387517, | |
| "grad_norm": 0.07535108923912048, | |
| "learning_rate": 1.3267377446563042e-05, | |
| "loss": 1.3026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9608127721335267, | |
| "grad_norm": 0.06275378167629242, | |
| "learning_rate": 1.2785816073273818e-05, | |
| "loss": 1.2005, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.018867924528302, | |
| "grad_norm": 0.05750374495983124, | |
| "learning_rate": 1.2309315914076298e-05, | |
| "loss": 1.1945, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.06437436491250992, | |
| "learning_rate": 1.1838526282350759e-05, | |
| "loss": 1.2601, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.134978229317852, | |
| "grad_norm": 0.05980416387319565, | |
| "learning_rate": 1.1374088709902117e-05, | |
| "loss": 1.2469, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.193033381712627, | |
| "grad_norm": 0.0727262794971466, | |
| "learning_rate": 1.0916636072762575e-05, | |
| "loss": 1.2763, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.251088534107402, | |
| "grad_norm": 0.0568414144217968, | |
| "learning_rate": 1.0466791728789216e-05, | |
| "loss": 1.2867, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.309143686502177, | |
| "grad_norm": 0.062224190682172775, | |
| "learning_rate": 1.0025168668231769e-05, | |
| "loss": 1.2627, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.367198838896952, | |
| "grad_norm": 0.05727972835302353, | |
| "learning_rate": 9.592368678428012e-06, | |
| "loss": 1.265, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.425253991291727, | |
| "grad_norm": 0.06459406763315201, | |
| "learning_rate": 9.168981523765108e-06, | |
| "loss": 1.2674, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.483309143686502, | |
| "grad_norm": 0.06641963869333267, | |
| "learning_rate": 8.755584142024184e-06, | |
| "loss": 1.271, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.5413642960812775, | |
| "grad_norm": 0.06708668172359467, | |
| "learning_rate": 8.352739858203466e-06, | |
| "loss": 1.2262, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.599419448476052, | |
| "grad_norm": 0.0688287690281868, | |
| "learning_rate": 7.960997616891126e-06, | |
| "loss": 1.2368, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.6574746008708274, | |
| "grad_norm": 0.07018615305423737, | |
| "learning_rate": 7.580891234233905e-06, | |
| "loss": 1.2569, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.7155297532656024, | |
| "grad_norm": 0.07098717987537384, | |
| "learning_rate": 7.212938670520841e-06, | |
| "loss": 1.2335, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.7735849056603774, | |
| "grad_norm": 0.062128230929374695, | |
| "learning_rate": 6.857641324373356e-06, | |
| "loss": 1.2773, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.8316400580551524, | |
| "grad_norm": 0.07041653245687485, | |
| "learning_rate": 6.515483349503413e-06, | |
| "loss": 1.2542, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.8896952104499274, | |
| "grad_norm": 0.06907247006893158, | |
| "learning_rate": 6.186930994970886e-06, | |
| "loss": 1.2725, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.9477503628447024, | |
| "grad_norm": 0.07188240438699722, | |
| "learning_rate": 5.872431969839034e-06, | |
| "loss": 1.2734, | |
| "step": 680 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.849187788931891e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |