| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.11111111111111, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.62962962962963e-05, | |
| "loss": 0.0119, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 3.259259259259259e-05, | |
| "loss": 0.0015, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 2.888888888888889e-05, | |
| "loss": 0.0007, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 2.5185185185185187e-05, | |
| "loss": 0.0003, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 5400, | |
| "num_train_epochs": 30, | |
| "total_flos": 4162821591225600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |