| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 3950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 4.367088607594937e-05, | |
| "loss": 1.1777, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 3.7341772151898736e-05, | |
| "loss": 0.1233, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 3.10126582278481e-05, | |
| "loss": 0.05, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 2.468354430379747e-05, | |
| "loss": 0.0223, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 31.65, | |
| "learning_rate": 1.8354430379746836e-05, | |
| "loss": 0.0162, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 37.97, | |
| "learning_rate": 1.2025316455696203e-05, | |
| "loss": 0.0166, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 44.3, | |
| "learning_rate": 5.69620253164557e-06, | |
| "loss": 0.0231, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 3950, | |
| "total_flos": 2.4497456256e+16, | |
| "train_loss": 0.18913862856128547, | |
| "train_runtime": 929.4199, | |
| "train_samples_per_second": 268.985, | |
| "train_steps_per_second": 4.25 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3950, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 2.4497456256e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |