| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 139704, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.359719978459882e-05, | |
| "loss": 0.6809, | |
| "step": 46568 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3213633894920349, | |
| "eval_runtime": 420.6563, | |
| "eval_samples_per_second": 2182.138, | |
| "eval_steps_per_second": 11.366, | |
| "step": 46568 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.270866989768444e-05, | |
| "loss": 0.4706, | |
| "step": 93136 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.2747191786766052, | |
| "eval_runtime": 418.1806, | |
| "eval_samples_per_second": 2195.056, | |
| "eval_steps_per_second": 11.433, | |
| "step": 93136 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.1818793753365646e-05, | |
| "loss": 0.4215, | |
| "step": 139704 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.2559063732624054, | |
| "eval_runtime": 418.7155, | |
| "eval_samples_per_second": 2192.252, | |
| "eval_steps_per_second": 11.418, | |
| "step": 139704 | |
| } | |
| ], | |
| "max_steps": 232840, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.1227226187002455e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |