| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 1.834916965686968, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.8456, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 0.7821874225568135, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.7682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 0.5025783677051715, | |
| "learning_rate": 4.999827900623038e-05, | |
| "loss": 0.7026, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 0.38259245769258377, | |
| "learning_rate": 4.993807186343243e-05, | |
| "loss": 0.6746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 0.3555510741148015, | |
| "learning_rate": 4.979207812402531e-05, | |
| "loss": 0.6436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 0.2688378444977237, | |
| "learning_rate": 4.956085596012407e-05, | |
| "loss": 0.6363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 0.24209340066643337, | |
| "learning_rate": 4.924528939432311e-05, | |
| "loss": 0.6199, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.23372841521299537, | |
| "learning_rate": 4.884658491984735e-05, | |
| "loss": 0.6106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 0.2050393221438694, | |
| "learning_rate": 4.8366266887814235e-05, | |
| "loss": 0.6112, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 0.22225010943703133, | |
| "learning_rate": 4.780617167924209e-05, | |
| "loss": 0.5938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 0.22817076996103577, | |
| "learning_rate": 4.716844068408693e-05, | |
| "loss": 0.5964, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.24547552141365458, | |
| "learning_rate": 4.6455512114150546e-05, | |
| "loss": 0.5918, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 0.49389185076779596, | |
| "learning_rate": 4.5670111681161296e-05, | |
| "loss": 0.5829, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 0.39410679769547763, | |
| "learning_rate": 4.481524217566783e-05, | |
| "loss": 0.5798, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 0.4326530558641569, | |
| "learning_rate": 4.3894171986588217e-05, | |
| "loss": 0.5786, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.39314639825078235, | |
| "learning_rate": 4.29104226053073e-05, | |
| "loss": 0.5774, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 0.3101300521779392, | |
| "learning_rate": 4.186775516209732e-05, | |
| "loss": 0.5728, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 0.30660811902378926, | |
| "learning_rate": 4.077015604633669e-05, | |
| "loss": 0.5752, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 0.27168731056065015, | |
| "learning_rate": 3.962182166550441e-05, | |
| "loss": 0.5736, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.257673470936219, | |
| "learning_rate": 3.8427142401220634e-05, | |
| "loss": 0.5696, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 0.2462560845245155, | |
| "learning_rate": 3.71906858236735e-05, | |
| "loss": 0.5659, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.21653881090159982, | |
| "learning_rate": 3.591717922860785e-05, | |
| "loss": 0.5731, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 0.20301860022569243, | |
| "learning_rate": 3.46114915636416e-05, | |
| "loss": 0.5639, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.20654293630556758, | |
| "learning_rate": 3.3278614813010034e-05, | |
| "loss": 0.5649, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 0.2077040504228326, | |
| "learning_rate": 3.1923644911909e-05, | |
| "loss": 0.5618, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 0.2074584711617551, | |
| "learning_rate": 3.0551762263406576e-05, | |
| "loss": 0.5605, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 0.2063245253273453, | |
| "learning_rate": 2.9168211932412042e-05, | |
| "loss": 0.5577, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.1884600764661488, | |
| "learning_rate": 2.777828359242567e-05, | |
| "loss": 0.5631, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 0.23858897751140598, | |
| "learning_rate": 2.6387291301738377e-05, | |
| "loss": 0.5558, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 0.19583494956048939, | |
| "learning_rate": 2.50005531864019e-05, | |
| "loss": 0.5536, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 0.1785073485429672, | |
| "learning_rate": 2.362337110764688e-05, | |
| "loss": 0.554, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.19633412962095292, | |
| "learning_rate": 2.226101039148557e-05, | |
| "loss": 0.5521, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 0.20712439231822205, | |
| "learning_rate": 2.0918679697998252e-05, | |
| "loss": 0.551, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 0.19261449151883753, | |
| "learning_rate": 1.9601511107268255e-05, | |
| "loss": 0.5514, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 0.1862092334599903, | |
| "learning_rate": 1.8314540498102216e-05, | |
| "loss": 0.5511, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.164285957599252, | |
| "learning_rate": 1.7062688294552992e-05, | |
| "loss": 0.5431, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 0.1828184120987395, | |
| "learning_rate": 1.5850740653856096e-05, | |
| "loss": 0.5465, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 0.16215375499348011, | |
| "learning_rate": 1.4683331167703218e-05, | |
| "loss": 0.5502, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 0.16594541680443214, | |
| "learning_rate": 1.356492314681356e-05, | |
| "loss": 0.5529, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.15314569577080056, | |
| "learning_rate": 1.2499792556533716e-05, | |
| "loss": 0.5473, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 0.1689661155908787, | |
| "learning_rate": 1.1492011668707753e-05, | |
| "loss": 0.5448, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 0.1638028922208292, | |
| "learning_rate": 1.0545433492320603e-05, | |
| "loss": 0.5499, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 0.15109362703655346, | |
| "learning_rate": 9.663677042440537e-06, | |
| "loss": 0.5443, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.15819129136937093, | |
| "learning_rate": 8.850113503781367e-06, | |
| "loss": 0.5442, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 0.14054281112891112, | |
| "learning_rate": 8.107853341784671e-06, | |
| "loss": 0.5505, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.1587260867222467, | |
| "learning_rate": 7.439734410499752e-06, | |
| "loss": 0.5469, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 0.1725873237416309, | |
| "learning_rate": 6.848311102728011e-06, | |
| "loss": 0.547, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.16764616511872976, | |
| "learning_rate": 6.335844583913515e-06, | |
| "loss": 0.5432, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 0.1385922581664261, | |
| "learning_rate": 5.904294147118193e-06, | |
| "loss": 0.5469, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.14186195400545243, | |
| "learning_rate": 5.555309722133842e-06, | |
| "loss": 0.5434, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 0.1379481281031733, | |
| "learning_rate": 5.290225567370509e-06, | |
| "loss": 0.5395, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.1426541759473039, | |
| "learning_rate": 5.110055168638854e-06, | |
| "loss": 0.5432, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 0.13789293058985388, | |
| "learning_rate": 5.0154873643297575e-06, | |
| "loss": 0.5469, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 268, | |
| "total_flos": 488621249396736.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.0172, | |
| "train_samples_per_second": 33722.532, | |
| "train_steps_per_second": 263.48 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 488621249396736.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |