| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 2.8146, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.0222, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.7161, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1800, | |
| "total_flos": 512626054053888.0, | |
| "train_loss": 2.0816353352864585, | |
| "train_runtime": 329.7867, | |
| "train_samples_per_second": 21.805, | |
| "train_steps_per_second": 5.458 | |
| } | |
| ], | |
| "max_steps": 1800, | |
| "num_train_epochs": 3, | |
| "total_flos": 512626054053888.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |