| { |
| "best_global_step": 400, |
| "best_metric": 81.91199737367272, |
| "best_model_checkpoint": null, |
| "epoch": 0.13245033112582782, |
| "eval_steps": 100, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.013245033112582781, |
| "grad_norm": 7.202547550201416, |
| "learning_rate": 9.998701986754968e-06, |
| "loss": 0.7094, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.026490066225165563, |
| "grad_norm": 9.662558555603027, |
| "learning_rate": 9.99737748344371e-06, |
| "loss": 0.68, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.026490066225165563, |
| "eval_HasAns_exact": 75.14792899408285, |
| "eval_HasAns_f1": 81.01957227969451, |
| "eval_HasAns_total": 15041, |
| "eval_best_exact": 75.14792899408285, |
| "eval_best_exact_thresh": 0.0, |
| "eval_best_f1": 81.01957227969451, |
| "eval_best_f1_thresh": 0.0, |
| "eval_exact": 75.14792899408285, |
| "eval_f1": 81.01957227969451, |
| "eval_loss": 0.5824803113937378, |
| "eval_runtime": 120.1578, |
| "eval_samples_per_second": 125.177, |
| "eval_steps_per_second": 7.831, |
| "eval_total": 15041, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.039735099337748346, |
| "grad_norm": 7.527211666107178, |
| "learning_rate": 9.996052980132451e-06, |
| "loss": 0.586, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.052980132450331126, |
| "grad_norm": 5.419323921203613, |
| "learning_rate": 9.994728476821193e-06, |
| "loss": 0.6035, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.052980132450331126, |
| "eval_HasAns_exact": 75.56013562927997, |
| "eval_HasAns_f1": 81.46153699536843, |
| "eval_HasAns_total": 15041, |
| "eval_best_exact": 75.56013562927997, |
| "eval_best_exact_thresh": 0.0, |
| "eval_best_f1": 81.46153699536843, |
| "eval_best_f1_thresh": 0.0, |
| "eval_exact": 75.56013562927997, |
| "eval_f1": 81.46153699536843, |
| "eval_loss": 0.5453085899353027, |
| "eval_runtime": 118.3719, |
| "eval_samples_per_second": 127.066, |
| "eval_steps_per_second": 7.95, |
| "eval_total": 15041, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.06622516556291391, |
| "grad_norm": 9.9099760055542, |
| "learning_rate": 9.993403973509935e-06, |
| "loss": 0.5616, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.07947019867549669, |
| "grad_norm": 3.5184719562530518, |
| "learning_rate": 9.992079470198677e-06, |
| "loss": 0.5286, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.07947019867549669, |
| "eval_HasAns_exact": 75.8526693703876, |
| "eval_HasAns_f1": 81.45745729278944, |
| "eval_HasAns_total": 15041, |
| "eval_best_exact": 75.8526693703876, |
| "eval_best_exact_thresh": 0.0, |
| "eval_best_f1": 81.45745729278944, |
| "eval_best_f1_thresh": 0.0, |
| "eval_exact": 75.8526693703876, |
| "eval_f1": 81.45745729278944, |
| "eval_loss": 0.5200360417366028, |
| "eval_runtime": 118.7441, |
| "eval_samples_per_second": 126.667, |
| "eval_steps_per_second": 7.925, |
| "eval_total": 15041, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.09271523178807947, |
| "grad_norm": 4.889588832855225, |
| "learning_rate": 9.990754966887418e-06, |
| "loss": 0.4943, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.10596026490066225, |
| "grad_norm": 6.106881141662598, |
| "learning_rate": 9.98943046357616e-06, |
| "loss": 0.5957, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.10596026490066225, |
| "eval_HasAns_exact": 76.39784588790639, |
| "eval_HasAns_f1": 81.91199737367272, |
| "eval_HasAns_total": 15041, |
| "eval_best_exact": 76.39784588790639, |
| "eval_best_exact_thresh": 0.0, |
| "eval_best_f1": 81.91199737367272, |
| "eval_best_f1_thresh": 0.0, |
| "eval_exact": 76.39784588790639, |
| "eval_f1": 81.91199737367272, |
| "eval_loss": 0.49782633781433105, |
| "eval_runtime": 118.2655, |
| "eval_samples_per_second": 127.18, |
| "eval_steps_per_second": 7.957, |
| "eval_total": 15041, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.11920529801324503, |
| "grad_norm": 6.963775634765625, |
| "learning_rate": 9.988105960264902e-06, |
| "loss": 0.5675, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.13245033112582782, |
| "grad_norm": 7.559121608734131, |
| "learning_rate": 9.986781456953643e-06, |
| "loss": 0.5173, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.13245033112582782, |
| "eval_HasAns_exact": 75.94574828801277, |
| "eval_HasAns_f1": 81.43615773338746, |
| "eval_HasAns_total": 15041, |
| "eval_best_exact": 75.94574828801277, |
| "eval_best_exact_thresh": 0.0, |
| "eval_best_f1": 81.43615773338746, |
| "eval_best_f1_thresh": 0.0, |
| "eval_exact": 75.94574828801277, |
| "eval_f1": 81.43615773338746, |
| "eval_loss": 0.4918788969516754, |
| "eval_runtime": 118.4997, |
| "eval_samples_per_second": 126.929, |
| "eval_steps_per_second": 7.941, |
| "eval_total": 15041, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 377500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 10, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4180748107776000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
