| { | |
| "best_metric": 1.0933258533477783, | |
| "best_model_checkpoint": "bygpt5_quatags/base/en/checkpoint-79485", | |
| "epoch": 7.0, | |
| "global_step": 79485, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.948826997701317e-05, | |
| "loss": 1.2528, | |
| "step": 11355 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1518468856811523, | |
| "eval_runtime": 238.8558, | |
| "eval_samples_per_second": 84.511, | |
| "eval_steps_per_second": 10.567, | |
| "step": 11355 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.704445954688097e-05, | |
| "loss": 1.1543, | |
| "step": 22710 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1252901554107666, | |
| "eval_runtime": 237.7799, | |
| "eval_samples_per_second": 84.894, | |
| "eval_steps_per_second": 10.615, | |
| "step": 22710 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.282832230852865e-05, | |
| "loss": 1.1219, | |
| "step": 34065 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1092721223831177, | |
| "eval_runtime": 236.9998, | |
| "eval_samples_per_second": 85.173, | |
| "eval_steps_per_second": 10.65, | |
| "step": 34065 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.7278263072276784e-05, | |
| "loss": 1.0991, | |
| "step": 45420 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.1006560325622559, | |
| "eval_runtime": 236.7452, | |
| "eval_samples_per_second": 85.265, | |
| "eval_steps_per_second": 10.661, | |
| "step": 45420 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.0971391293814688e-05, | |
| "loss": 1.0814, | |
| "step": 56775 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0954959392547607, | |
| "eval_runtime": 239.1383, | |
| "eval_samples_per_second": 84.411, | |
| "eval_steps_per_second": 10.555, | |
| "step": 56775 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.4563511746431305e-05, | |
| "loss": 1.0674, | |
| "step": 68130 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.0942013263702393, | |
| "eval_runtime": 238.8829, | |
| "eval_samples_per_second": 84.502, | |
| "eval_steps_per_second": 10.566, | |
| "step": 68130 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 8.72093225141226e-06, | |
| "loss": 1.0567, | |
| "step": 79485 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.0933258533477783, | |
| "eval_runtime": 238.8392, | |
| "eval_samples_per_second": 84.517, | |
| "eval_steps_per_second": 10.568, | |
| "step": 79485 | |
| } | |
| ], | |
| "max_steps": 113550, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.183225275809792e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |