| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017394329448599756, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017394329448599757, | |
| "eval_loss": 31.39523696899414, | |
| "eval_runtime": 15.6242, | |
| "eval_samples_per_second": 154.952, | |
| "eval_steps_per_second": 77.508, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005218298834579927, | |
| "grad_norm": 1378.8846435546875, | |
| "learning_rate": 6e-05, | |
| "loss": 101.6594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010436597669159853, | |
| "grad_norm": 2315.408935546875, | |
| "learning_rate": 0.00012, | |
| "loss": 139.6225, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013915463558879806, | |
| "eval_loss": 31.306568145751953, | |
| "eval_runtime": 14.1121, | |
| "eval_samples_per_second": 171.555, | |
| "eval_steps_per_second": 85.813, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015654896503739782, | |
| "grad_norm": 1939.8433837890625, | |
| "learning_rate": 0.00018, | |
| "loss": 125.2086, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 22343225180160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |