| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8888888888888888, | |
| "eval_steps": 500, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 19.76939582824707, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 9.5977, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 23.03803062438965, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 8.8963, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 19.974302291870117, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 8.297, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.126984126984127, | |
| "grad_norm": 51.25042724609375, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 9.9734, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 21.681840896606445, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 7.6149, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6349206349206349, | |
| "grad_norm": 17.052457809448242, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 7.5471, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 11.491819381713867, | |
| "learning_rate": 0.0, | |
| "loss": 7.4192, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "step": 14, | |
| "total_flos": 180166080636000.0, | |
| "train_loss": 8.477952480316162, | |
| "train_runtime": 453.3902, | |
| "train_samples_per_second": 2.206, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 14, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 180166080636000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |