| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 279, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0, | |
| "step": 279, | |
| "total_flos": 1032696881888364.0, | |
| "train_loss": 0.5050160397765457, | |
| "train_runtime": 177.9329, | |
| "train_samples_per_second": 99.779, | |
| "train_steps_per_second": 1.568 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 279, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1032696881888364.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |