| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04, | |
| "eval_steps": 10, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.366393566131592, | |
| "eval_runtime": 3175.9898, | |
| "eval_samples_per_second": 0.315, | |
| "eval_steps_per_second": 0.039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.2631593942642212, | |
| "eval_runtime": 3164.028, | |
| "eval_samples_per_second": 0.316, | |
| "eval_steps_per_second": 0.04, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "total_flos": 3505481507143680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |