| { | |
| "best_metric": 0.25107308099671105, | |
| "best_model_checkpoint": "/opt/ml/checkpoints/checkpoint-14592", | |
| "epoch": 2.666179426274438, | |
| "global_step": 14592, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.045685279187818e-08, | |
| "loss": 2.0931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.8369184916418297e-05, | |
| "loss": 0.2097, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_ANS_f1": 0.1965132827324478, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.28789019516997744, | |
| "eval_ANS_recall": 0.14916729182295574, | |
| "eval_loss": 0.1584259271621704, | |
| "eval_overall_accuracy": 0.9525067851669007, | |
| "eval_overall_f1": 0.1965132827324478, | |
| "eval_overall_precision": 0.28789019516997744, | |
| "eval_overall_recall": 0.14916729182295574, | |
| "eval_runtime": 271.0381, | |
| "eval_samples_per_second": 64.637, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.4823765712064277e-05, | |
| "loss": 0.1427, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_ANS_f1": 0.14480276621268787, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.3350021767522856, | |
| "eval_ANS_recall": 0.09236309077269317, | |
| "eval_loss": 0.1570661962032318, | |
| "eval_overall_accuracy": 0.9537896342872352, | |
| "eval_overall_f1": 0.14480276621268787, | |
| "eval_overall_precision": 0.3350021767522856, | |
| "eval_overall_recall": 0.09236309077269317, | |
| "eval_runtime": 272.0666, | |
| "eval_samples_per_second": 64.392, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.127834650771025e-05, | |
| "loss": 0.1381, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_ANS_f1": 0.18933628222641427, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.34125371267781773, | |
| "eval_ANS_recall": 0.13101275318829708, | |
| "eval_loss": 0.15228605270385742, | |
| "eval_overall_accuracy": 0.954028691761447, | |
| "eval_overall_f1": 0.18933628222641427, | |
| "eval_overall_precision": 0.34125371267781773, | |
| "eval_overall_recall": 0.13101275318829708, | |
| "eval_runtime": 272.4342, | |
| "eval_samples_per_second": 64.305, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.773292730335623e-05, | |
| "loss": 0.1295, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_ANS_f1": 0.18266756939742723, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.36841147018661813, | |
| "eval_ANS_recall": 0.1214403600900225, | |
| "eval_loss": 0.15274310111999512, | |
| "eval_overall_accuracy": 0.9544393980616191, | |
| "eval_overall_f1": 0.18266756939742723, | |
| "eval_overall_precision": 0.36841147018661813, | |
| "eval_overall_recall": 0.1214403600900225, | |
| "eval_runtime": 269.6146, | |
| "eval_samples_per_second": 64.978, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.4187508099002203e-05, | |
| "loss": 0.1275, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_ANS_f1": 0.22205431725643288, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.3693876125968857, | |
| "eval_ANS_recall": 0.1587396849212303, | |
| "eval_loss": 0.15151338279247284, | |
| "eval_overall_accuracy": 0.9544824840017387, | |
| "eval_overall_f1": 0.22205431725643288, | |
| "eval_overall_precision": 0.3693876125968857, | |
| "eval_overall_recall": 0.1587396849212303, | |
| "eval_runtime": 273.5764, | |
| "eval_samples_per_second": 64.037, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.0642088894648179e-05, | |
| "loss": 0.1262, | |
| "step": 10944 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_ANS_f1": 0.22321074285236933, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.3670833905756285, | |
| "eval_ANS_recall": 0.16036009002250562, | |
| "eval_loss": 0.14961716532707214, | |
| "eval_overall_accuracy": 0.9540054114550921, | |
| "eval_overall_f1": 0.22321074285236933, | |
| "eval_overall_precision": 0.3670833905756285, | |
| "eval_overall_recall": 0.16036009002250562, | |
| "eval_runtime": 271.8734, | |
| "eval_samples_per_second": 64.438, | |
| "step": 10944 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.096669690294156e-06, | |
| "loss": 0.1126, | |
| "step": 12768 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_ANS_f1": 0.2386963952765693, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.33832516654737654, | |
| "eval_ANS_recall": 0.18439609902475618, | |
| "eval_loss": 0.15988405048847198, | |
| "eval_overall_accuracy": 0.9519723805225143, | |
| "eval_overall_f1": 0.2386963952765693, | |
| "eval_overall_precision": 0.33832516654737654, | |
| "eval_overall_recall": 0.18439609902475618, | |
| "eval_runtime": 273.7781, | |
| "eval_samples_per_second": 63.99, | |
| "step": 12768 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.551250485940132e-06, | |
| "loss": 0.1109, | |
| "step": 14592 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_ANS_f1": 0.25107308099671105, | |
| "eval_ANS_number": 33325, | |
| "eval_ANS_precision": 0.3296896349795042, | |
| "eval_ANS_recall": 0.20273068267066766, | |
| "eval_loss": 0.16195876896381378, | |
| "eval_overall_accuracy": 0.9512107322907231, | |
| "eval_overall_f1": 0.25107308099671105, | |
| "eval_overall_precision": 0.3296896349795042, | |
| "eval_overall_recall": 0.20273068267066766, | |
| "eval_runtime": 275.1376, | |
| "eval_samples_per_second": 63.674, | |
| "step": 14592 | |
| } | |
| ], | |
| "max_steps": 16419, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.702162559715073e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |