| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.279112754158966, | |
| "eval_steps": 500, | |
| "global_step": 990, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 1356770.7575, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "step": 990, | |
| "total_flos": 6.487477354443571e+17, | |
| "train_loss": 683867.2831603315, | |
| "train_runtime": 12592.8457, | |
| "train_samples_per_second": 1.289, | |
| "train_steps_per_second": 0.079 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 990, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 6.487477354443571e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |