| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.7268993854522705, | |
| "eval_runtime": 0.7029, | |
| "eval_samples_per_second": 142.272, | |
| "eval_steps_per_second": 18.495, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8854426741600037, | |
| "eval_runtime": 0.6981, | |
| "eval_samples_per_second": 143.238, | |
| "eval_steps_per_second": 18.621, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.9036551117897034, | |
| "eval_runtime": 0.705, | |
| "eval_samples_per_second": 141.842, | |
| "eval_steps_per_second": 18.44, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 39, | |
| "total_flos": 648728419500032.0, | |
| "train_loss": 0.4328929705497546, | |
| "train_runtime": 171.6645, | |
| "train_samples_per_second": 1.748, | |
| "train_steps_per_second": 0.227 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 648728419500032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |