| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 234.01170349121094, | |
| "eval_runtime": 0.658, | |
| "eval_samples_per_second": 85.108, | |
| "eval_steps_per_second": 10.639, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 190.9105987548828, | |
| "eval_runtime": 0.627, | |
| "eval_samples_per_second": 89.321, | |
| "eval_steps_per_second": 11.165, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 151.1154022216797, | |
| "eval_runtime": 0.6673, | |
| "eval_samples_per_second": 83.926, | |
| "eval_steps_per_second": 10.491, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 106.11787414550781, | |
| "eval_runtime": 0.625, | |
| "eval_samples_per_second": 89.596, | |
| "eval_steps_per_second": 11.199, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 96.85845184326172, | |
| "eval_runtime": 0.6443, | |
| "eval_samples_per_second": 86.921, | |
| "eval_steps_per_second": 10.865, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 77.78966522216797, | |
| "eval_runtime": 0.6498, | |
| "eval_samples_per_second": 86.181, | |
| "eval_steps_per_second": 10.773, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 84.43614196777344, | |
| "eval_runtime": 0.6744, | |
| "eval_samples_per_second": 83.034, | |
| "eval_steps_per_second": 10.379, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 75.44404602050781, | |
| "eval_runtime": 0.6298, | |
| "eval_samples_per_second": 88.912, | |
| "eval_steps_per_second": 11.114, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.928571428571429, | |
| "grad_norm": 88.87016296386719, | |
| "learning_rate": 1.1904761904761906e-06, | |
| "loss": 6.5619, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 68.6030044555664, | |
| "eval_runtime": 1.2208, | |
| "eval_samples_per_second": 45.873, | |
| "eval_steps_per_second": 5.734, | |
| "step": 504 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |