| { | |
| "best_metric": 0.8346361517906189, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.19061234214915415, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003812246842983083, | |
| "grad_norm": 0.2967394292354584, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003812246842983083, | |
| "eval_loss": 0.934563934803009, | |
| "eval_runtime": 12.3785, | |
| "eval_samples_per_second": 142.828, | |
| "eval_steps_per_second": 17.854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007624493685966166, | |
| "grad_norm": 0.33949005603790283, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9268, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01143674052894925, | |
| "grad_norm": 0.29785802960395813, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015248987371932332, | |
| "grad_norm": 0.26380258798599243, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.922, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019061234214915415, | |
| "grad_norm": 0.313311368227005, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0228734810578985, | |
| "grad_norm": 0.3013531565666199, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9275, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02668572790088158, | |
| "grad_norm": 0.29245325922966003, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8662, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.030497974743864665, | |
| "grad_norm": 0.26414409279823303, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.034310221586847746, | |
| "grad_norm": 0.2993530035018921, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9113, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03812246842983083, | |
| "grad_norm": 0.27474743127822876, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041934715272813915, | |
| "grad_norm": 0.27231356501579285, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8842, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.045746962115797, | |
| "grad_norm": 0.2848631739616394, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8936, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.049559208958780084, | |
| "grad_norm": 0.21465671062469482, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9129, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05337145580176316, | |
| "grad_norm": 0.1949559450149536, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8329, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.057183702644746245, | |
| "grad_norm": 0.2053157389163971, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9376, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06099594948772933, | |
| "grad_norm": 0.19364218413829803, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06480819633071241, | |
| "grad_norm": 0.1981198489665985, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06862044317369549, | |
| "grad_norm": 0.2124132364988327, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07243269001667858, | |
| "grad_norm": 0.21935242414474487, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8403, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07624493685966166, | |
| "grad_norm": 0.22234244644641876, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8335, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08005718370264475, | |
| "grad_norm": 0.22361911833286285, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8508, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08386943054562783, | |
| "grad_norm": 0.2258802205324173, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7993, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0876816773886109, | |
| "grad_norm": 0.24764667451381683, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8078, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.091493924231594, | |
| "grad_norm": 0.25130197405815125, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7911, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09530617107457708, | |
| "grad_norm": 0.2888367772102356, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09530617107457708, | |
| "eval_loss": 0.8428515195846558, | |
| "eval_runtime": 12.3144, | |
| "eval_samples_per_second": 143.571, | |
| "eval_steps_per_second": 17.946, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09911841791756017, | |
| "grad_norm": 0.1759335994720459, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8758, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10293066476054324, | |
| "grad_norm": 0.19624562561511993, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9195, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10674291160352632, | |
| "grad_norm": 0.19254527986049652, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8493, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11055515844650941, | |
| "grad_norm": 0.20061329007148743, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.908, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11436740528949249, | |
| "grad_norm": 0.19461949169635773, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8234, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11817965213247558, | |
| "grad_norm": 0.1995747834444046, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8731, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12199189897545866, | |
| "grad_norm": 0.20301039516925812, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8031, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12580414581844174, | |
| "grad_norm": 0.20862935483455658, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.838, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12961639266142483, | |
| "grad_norm": 0.22189174592494965, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8665, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13342863950440792, | |
| "grad_norm": 0.23263895511627197, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8503, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13724088634739098, | |
| "grad_norm": 0.23706233501434326, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7954, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14105313319037407, | |
| "grad_norm": 0.27249541878700256, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8025, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14486538003335717, | |
| "grad_norm": 0.1823560893535614, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9405, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14867762687634023, | |
| "grad_norm": 0.16355444490909576, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8379, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15248987371932332, | |
| "grad_norm": 0.16927115619182587, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1563021205623064, | |
| "grad_norm": 0.18029265105724335, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8458, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1601143674052895, | |
| "grad_norm": 0.18312260508537292, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8675, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16392661424827257, | |
| "grad_norm": 0.19348792731761932, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8466, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16773886109125566, | |
| "grad_norm": 0.1927310675382614, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7973, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17155110793423875, | |
| "grad_norm": 0.20133088529109955, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8522, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1753633547772218, | |
| "grad_norm": 0.20981720089912415, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8388, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1791756016202049, | |
| "grad_norm": 0.21205788850784302, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7974, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.182987848463188, | |
| "grad_norm": 0.23205319046974182, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1868000953061711, | |
| "grad_norm": 0.24879471957683563, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.848, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "grad_norm": 0.29144957661628723, | |
| "learning_rate": 0.0, | |
| "loss": 0.8512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "eval_loss": 0.8346361517906189, | |
| "eval_runtime": 12.391, | |
| "eval_samples_per_second": 142.684, | |
| "eval_steps_per_second": 17.836, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.9585460372176896e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |