| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 65, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 0.801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 0.4026, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001076923076923077, | |
| "loss": 0.309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.3093, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.2294, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.1809, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 65, | |
| "total_flos": 0.0, | |
| "train_loss": 0.35707517037024866, | |
| "train_runtime": 242.8167, | |
| "train_samples_per_second": 4.258, | |
| "train_steps_per_second": 0.268 | |
| } | |
| ], | |
| "max_steps": 65, | |
| "num_train_epochs": 1, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |