| { | |
| "best_metric": 3.4386398792266846, | |
| "best_model_checkpoint": "output/the-notorious-big/checkpoint-48", | |
| "epoch": 1.0, | |
| "global_step": 48, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013355940688336427, | |
| "loss": 3.0338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012302403914397873, | |
| "loss": 3.0668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 2.9281, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 2.8865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.411334533481218e-05, | |
| "loss": 2.8148, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 2.8586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.3368877084135277e-05, | |
| "loss": 2.8945, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 2.876, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 2.8567, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.4386398792266846, | |
| "eval_runtime": 0.9158, | |
| "eval_samples_per_second": 76.439, | |
| "eval_steps_per_second": 9.828, | |
| "step": 48 | |
| } | |
| ], | |
| "max_steps": 4800, | |
| "num_train_epochs": 100, | |
| "total_flos": 49776132096000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |