| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 2100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 1.1447, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.9021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.7221, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.563, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2100, | |
| "total_flos": 2817064347303936.0, | |
| "train_loss": 0.8206888725644066, | |
| "train_runtime": 649.5749, | |
| "train_samples_per_second": 32.32, | |
| "train_steps_per_second": 3.233 | |
| } | |
| ], | |
| "max_steps": 2100, | |
| "num_train_epochs": 3, | |
| "total_flos": 2817064347303936.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |