| { | |
| "best_metric": 0.06587601453065872, | |
| "best_model_checkpoint": "test-ner/checkpoint-2636", | |
| "epoch": 4.0, | |
| "global_step": 5272, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.241274658573596e-06, | |
| "loss": 0.2967, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.482549317147192e-06, | |
| "loss": 0.0903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9800172512938471, | |
| "eval_f1": 0.8510216941218831, | |
| "eval_loss": 0.07860440760850906, | |
| "eval_precision": 0.8489583333333334, | |
| "eval_recall": 0.8530951091860675, | |
| "eval_runtime": 11.6301, | |
| "eval_samples_per_second": 249.008, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.72382397572079e-06, | |
| "loss": 0.0695, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 6.965098634294386e-06, | |
| "loss": 0.0487, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.206373292867982e-06, | |
| "loss": 0.0521, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9845816561242093, | |
| "eval_f1": 0.8887689955939214, | |
| "eval_loss": 0.06587601453065872, | |
| "eval_precision": 0.885663082437276, | |
| "eval_recall": 0.8918967695361848, | |
| "eval_runtime": 11.691, | |
| "eval_samples_per_second": 247.711, | |
| "step": 2636 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 5.447647951441578e-06, | |
| "loss": 0.0388, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4.688922610015174e-06, | |
| "loss": 0.0344, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9849949683726279, | |
| "eval_f1": 0.8925949424453912, | |
| "eval_loss": 0.06827788800001144, | |
| "eval_precision": 0.8965768390386016, | |
| "eval_recall": 0.8886482584371053, | |
| "eval_runtime": 11.7404, | |
| "eval_samples_per_second": 246.67, | |
| "step": 3954 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.930197268588772e-06, | |
| "loss": 0.0297, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.1714719271623673e-06, | |
| "loss": 0.0255, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2.4127465857359637e-06, | |
| "loss": 0.0235, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9865943070730305, | |
| "eval_f1": 0.904637078550122, | |
| "eval_loss": 0.06835205852985382, | |
| "eval_precision": 0.90619340818544, | |
| "eval_recall": 0.9030860855441256, | |
| "eval_runtime": 11.7952, | |
| "eval_samples_per_second": 245.524, | |
| "step": 5272 | |
| } | |
| ], | |
| "max_steps": 6590, | |
| "num_train_epochs": 5, | |
| "total_flos": 1452761017373610.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |