| { | |
| "best_metric": 0.06023645028471947, | |
| "best_model_checkpoint": "output/bic/checkpoint-1449", | |
| "epoch": 3.0, | |
| "global_step": 1449, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0932, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.06998058408498764, | |
| "eval_runtime": 3.9047, | |
| "eval_samples_per_second": 123.44, | |
| "eval_steps_per_second": 15.622, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0605, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.06084592640399933, | |
| "eval_runtime": 3.902, | |
| "eval_samples_per_second": 123.526, | |
| "eval_steps_per_second": 15.633, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0509, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.06023645028471947, | |
| "eval_runtime": 3.9011, | |
| "eval_samples_per_second": 123.554, | |
| "eval_steps_per_second": 15.636, | |
| "step": 1449 | |
| } | |
| ], | |
| "max_steps": 4830, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.0759219080090624e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |