| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 3608, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.166923313828149e-06, | |
| "loss": 2.6072, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3964672088623047, | |
| "eval_runtime": 18.2149, | |
| "eval_samples_per_second": 54.9, | |
| "eval_steps_per_second": 0.604, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.777948875885433e-06, | |
| "loss": 2.522, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.383113384246826, | |
| "eval_runtime": 1.6537, | |
| "eval_samples_per_second": 604.697, | |
| "eval_steps_per_second": 6.652, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.3889744379427164e-06, | |
| "loss": 2.485, | |
| "step": 2706 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.3780102729797363, | |
| "eval_runtime": 1.6082, | |
| "eval_samples_per_second": 621.809, | |
| "eval_steps_per_second": 6.84, | |
| "step": 2706 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.4641, | |
| "step": 3608 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.3768954277038574, | |
| "eval_runtime": 1.6566, | |
| "eval_samples_per_second": 603.647, | |
| "eval_steps_per_second": 6.64, | |
| "step": 3608 | |
| } | |
| ], | |
| "max_steps": 3608, | |
| "num_train_epochs": 4, | |
| "total_flos": 1.1301011030016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |