| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 6062, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.25e-07, | |
| "loss": 0.5208, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.5e-07, | |
| "loss": 0.583, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.411691981631932e-07, | |
| "loss": 0.4802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.3233839632638644e-07, | |
| "loss": 0.5088, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.2350759448957965e-07, | |
| "loss": 0.4887, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.1467679265277285e-07, | |
| "loss": 0.4407, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.0584599081596607e-07, | |
| "loss": 0.4351, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.970151889791593e-07, | |
| "loss": 0.4326, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.8818438714235253e-07, | |
| "loss": 0.4043, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.7935358530554573e-07, | |
| "loss": 0.4158, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.7052278346873893e-07, | |
| "loss": 0.427, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.6169198163193219e-07, | |
| "loss": 0.425, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15155, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |