| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2226, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.5628, | |
| "eval_samples_per_second": 472.357, | |
| "eval_steps_per_second": 9.904, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 98073.078125, | |
| "learning_rate": 1.550763701707098e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4917, | |
| "eval_samples_per_second": 564.492, | |
| "eval_steps_per_second": 11.836, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.7325, | |
| "eval_samples_per_second": 540.78, | |
| "eval_steps_per_second": 11.339, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 376953.0, | |
| "learning_rate": 1.101527403414196e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0124, | |
| "eval_samples_per_second": 515.601, | |
| "eval_steps_per_second": 10.811, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 884346.875, | |
| "learning_rate": 6.522911051212939e-06, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0086, | |
| "eval_samples_per_second": 515.925, | |
| "eval_steps_per_second": 10.818, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.3978, | |
| "eval_samples_per_second": 574.31, | |
| "eval_steps_per_second": 12.042, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 6.289308176100629, | |
| "grad_norm": 1115746.75, | |
| "learning_rate": 2.0305480682839176e-06, | |
| "loss": 0.0, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2226, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 520991326672152.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.8432205176909278, | |
| "num_train_epochs": 7, | |
| "temperature": 11 | |
| } | |
| } | |