| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9697275479313827, | |
| "eval_steps": 500, | |
| "global_step": 3844, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.974811083123427e-05, | |
| "loss": 1.0444, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019949622166246853, | |
| "loss": 1.002, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018895430333613683, | |
| "loss": 0.9986, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00017785253714606113, | |
| "loss": 0.9637, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00016675077095598543, | |
| "loss": 0.9805, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00015564900476590973, | |
| "loss": 0.9943, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00014454723857583403, | |
| "loss": 0.9564, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013344547238575835, | |
| "loss": 0.9335, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00012234370619568265, | |
| "loss": 0.9133, | |
| "step": 1782 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00011124194000560695, | |
| "loss": 0.9323, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00010014017381553126, | |
| "loss": 0.9367, | |
| "step": 2178 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.903840762545556e-05, | |
| "loss": 0.9114, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.793664143537988e-05, | |
| "loss": 0.8827, | |
| "step": 2574 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.683487524530419e-05, | |
| "loss": 0.8703, | |
| "step": 2772 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 5.573310905522848e-05, | |
| "loss": 0.9036, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 4.4631342865152794e-05, | |
| "loss": 0.9028, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.352957667507709e-05, | |
| "loss": 0.8646, | |
| "step": 3366 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2.2427810485001402e-05, | |
| "loss": 0.8536, | |
| "step": 3564 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.1382113821138211e-05, | |
| "loss": 0.849, | |
| "step": 3762 | |
| } | |
| ], | |
| "logging_steps": 198, | |
| "max_steps": 3964, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 2.6878066792228454e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |