| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.975609756097561, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 40.474364127833894, | |
| "learning_rate": 4e-07, | |
| "loss": 2.8277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 39.80986919634387, | |
| "learning_rate": 8e-07, | |
| "loss": 2.7894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 37.613931575844546, | |
| "learning_rate": 1.2e-06, | |
| "loss": 2.7705, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 34.058960023767305, | |
| "learning_rate": 1.6e-06, | |
| "loss": 2.6445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 27.17276921169534, | |
| "learning_rate": 2e-06, | |
| "loss": 2.6669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 15.411738818229358, | |
| "learning_rate": 1.9996268812619105e-06, | |
| "loss": 2.449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22764227642276422, | |
| "grad_norm": 9.722583741958005, | |
| "learning_rate": 1.998507803482828e-06, | |
| "loss": 2.492, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 5.002874583844784, | |
| "learning_rate": 1.9966436017605294e-06, | |
| "loss": 2.3573, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 4.38783321163898, | |
| "learning_rate": 1.9940356672322033e-06, | |
| "loss": 2.2742, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 4.050625126869575, | |
| "learning_rate": 1.9906859460363304e-06, | |
| "loss": 2.3301, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35772357723577236, | |
| "grad_norm": 3.6789133162460774, | |
| "learning_rate": 1.986596937860402e-06, | |
| "loss": 2.2729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 2.613575263087869, | |
| "learning_rate": 1.9817716940755586e-06, | |
| "loss": 2.3178, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.42276422764227645, | |
| "grad_norm": 2.83098515959453, | |
| "learning_rate": 1.9762138154595447e-06, | |
| "loss": 2.3486, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45528455284552843, | |
| "grad_norm": 2.5132095083333734, | |
| "learning_rate": 1.969927449509671e-06, | |
| "loss": 2.273, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 2.137375987210218, | |
| "learning_rate": 1.9629172873477994e-06, | |
| "loss": 2.224, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 1.7542766611994582, | |
| "learning_rate": 1.955188560219648e-06, | |
| "loss": 2.3732, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5528455284552846, | |
| "grad_norm": 1.490783000173608, | |
| "learning_rate": 1.9467470355910435e-06, | |
| "loss": 2.2965, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 1.6159290325764584, | |
| "learning_rate": 1.93759901284402e-06, | |
| "loss": 2.2234, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6178861788617886, | |
| "grad_norm": 1.805845446790275, | |
| "learning_rate": 1.9277513185759843e-06, | |
| "loss": 2.2912, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 1.4604974196739857, | |
| "learning_rate": 1.9172113015054528e-06, | |
| "loss": 2.2642, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 1.324880967104045, | |
| "learning_rate": 1.9059868269881636e-06, | |
| "loss": 2.2243, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7154471544715447, | |
| "grad_norm": 1.1866315224263582, | |
| "learning_rate": 1.894086271147651e-06, | |
| "loss": 2.1637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7479674796747967, | |
| "grad_norm": 1.2828999422781817, | |
| "learning_rate": 1.8815185146246715e-06, | |
| "loss": 2.3203, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 1.1737064917540987, | |
| "learning_rate": 1.8682929359501337e-06, | |
| "loss": 2.2612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": 1.2633649535555074, | |
| "learning_rate": 1.8544194045464886e-06, | |
| "loss": 2.2641, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8455284552845529, | |
| "grad_norm": 1.214313162130321, | |
| "learning_rate": 1.8399082733627965e-06, | |
| "loss": 2.1903, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 1.1791856518491939, | |
| "learning_rate": 1.8247703711489684e-06, | |
| "loss": 2.2214, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": 1.0774382245713374, | |
| "learning_rate": 1.8090169943749474e-06, | |
| "loss": 2.2613, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.943089430894309, | |
| "grad_norm": 1.5312368454111793, | |
| "learning_rate": 1.792659898800858e-06, | |
| "loss": 2.2658, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 1.1478826076751814, | |
| "learning_rate": 1.7757112907044198e-06, | |
| "loss": 2.3472, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 30, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.86038253256704e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |