| { | |
| "best_metric": 2.8949737548828125, | |
| "best_model_checkpoint": "output/green-day/checkpoint-51", | |
| "epoch": 1.0, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013397182122930294, | |
| "loss": 3.1093, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00012459110818763681, | |
| "loss": 3.1106, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000109940736055617, | |
| "loss": 2.9044, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.139953924430466e-05, | |
| "loss": 2.8391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.071254101695329e-05, | |
| "loss": 2.9691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.982671888105512e-05, | |
| "loss": 2.8602, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0707762854909304e-05, | |
| "loss": 2.7604, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5155072587539005e-05, | |
| "loss": 2.9872, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6324050628611986e-06, | |
| "loss": 2.636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3011164863877445e-07, | |
| "loss": 2.785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.8949737548828125, | |
| "eval_runtime": 3.4558, | |
| "eval_samples_per_second": 22.86, | |
| "eval_steps_per_second": 2.894, | |
| "step": 51 | |
| } | |
| ], | |
| "max_steps": 51, | |
| "num_train_epochs": 1, | |
| "total_flos": 53042282496000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |