| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 26.827210788135588, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 22.093012865206294, | |
| "learning_rate": 1.9957341762950346e-05, | |
| "loss": 1.6838, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 10.857966996633865, | |
| "learning_rate": 1.8502171357296144e-05, | |
| "loss": 1.4792, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 7.826888023024255, | |
| "learning_rate": 1.526432162877356e-05, | |
| "loss": 1.3582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 8.646945817178395, | |
| "learning_rate": 1.092268359463302e-05, | |
| "loss": 1.2374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 8.147122012190973, | |
| "learning_rate": 6.387583338128471e-06, | |
| "loss": 1.1575, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 7.291039136509575, | |
| "learning_rate": 2.6099108277934105e-06, | |
| "loss": 1.0991, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 7.09673355873191, | |
| "learning_rate": 3.817435682718096e-07, | |
| "loss": 1.0781, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0718671083450317, | |
| "eval_runtime": 1.4219, | |
| "eval_samples_per_second": 135.738, | |
| "eval_steps_per_second": 1.407, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 38, | |
| "total_flos": 15808164003840.0, | |
| "train_loss": 1.2820051688896983, | |
| "train_runtime": 418.9516, | |
| "train_samples_per_second": 46.275, | |
| "train_steps_per_second": 0.091 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 15808164003840.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |