{ "best_metric": null, "best_model_checkpoint": null, "epoch": 18.06451612903226, "global_step": 140, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9, "eval_accuracy": 0.7506493506493507, "eval_f1": 0.0, "eval_loss": 1.2528471946716309, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.2089, "eval_samples_per_second": 38.296, "eval_steps_per_second": 4.787, "step": 7 }, { "epoch": 1.94, "eval_accuracy": 0.7688311688311689, "eval_f1": 0.04819277108433734, "eval_loss": 0.8142604827880859, "eval_precision": 0.18181818181818182, "eval_recall": 0.027777777777777776, "eval_runtime": 0.1224, "eval_samples_per_second": 65.373, "eval_steps_per_second": 8.172, "step": 15 }, { "epoch": 2.97, "eval_accuracy": 0.8701298701298701, "eval_f1": 0.4864864864864865, "eval_loss": 0.5706822276115417, "eval_precision": 0.47368421052631576, "eval_recall": 0.5, "eval_runtime": 0.1206, "eval_samples_per_second": 66.316, "eval_steps_per_second": 8.289, "step": 23 }, { "epoch": 4.0, "eval_accuracy": 0.8909090909090909, "eval_f1": 0.5379310344827586, "eval_loss": 0.4967877268791199, "eval_precision": 0.5342465753424658, "eval_recall": 0.5416666666666666, "eval_runtime": 0.121, "eval_samples_per_second": 66.117, "eval_steps_per_second": 8.265, "step": 31 }, { "epoch": 4.9, "eval_accuracy": 0.9025974025974026, "eval_f1": 0.5419354838709678, "eval_loss": 0.4114609658718109, "eval_precision": 0.5060240963855421, "eval_recall": 0.5833333333333334, "eval_runtime": 0.1266, "eval_samples_per_second": 63.18, "eval_steps_per_second": 7.897, "step": 38 }, { "epoch": 5.94, "eval_accuracy": 0.9051948051948052, "eval_f1": 0.5806451612903225, "eval_loss": 0.37950557470321655, "eval_precision": 0.5421686746987951, "eval_recall": 0.625, "eval_runtime": 0.1236, "eval_samples_per_second": 64.708, "eval_steps_per_second": 8.088, "step": 46 }, { "epoch": 6.97, "eval_accuracy": 0.9077922077922078, "eval_f1": 0.5359477124183006, "eval_loss": 0.3877827525138855, "eval_precision": 0.5061728395061729, "eval_recall": 0.5694444444444444, "eval_runtime": 0.1224, "eval_samples_per_second": 65.385, "eval_steps_per_second": 8.173, "step": 54 }, { "epoch": 8.0, "eval_accuracy": 0.912987012987013, "eval_f1": 0.6064516129032258, "eval_loss": 0.4006221294403076, "eval_precision": 0.5662650602409639, "eval_recall": 0.6527777777777778, "eval_runtime": 0.1196, "eval_samples_per_second": 66.868, "eval_steps_per_second": 8.358, "step": 62 }, { "epoch": 8.9, "eval_accuracy": 0.9116883116883117, "eval_f1": 0.6103896103896104, "eval_loss": 0.3754499554634094, "eval_precision": 0.573170731707317, "eval_recall": 0.6527777777777778, "eval_runtime": 0.124, "eval_samples_per_second": 64.536, "eval_steps_per_second": 8.067, "step": 69 }, { "epoch": 9.94, "eval_accuracy": 0.9142857142857143, "eval_f1": 0.5987261146496815, "eval_loss": 0.3780848979949951, "eval_precision": 0.5529411764705883, "eval_recall": 0.6527777777777778, "eval_runtime": 0.1879, "eval_samples_per_second": 42.581, "eval_steps_per_second": 5.323, "step": 77 }, { "epoch": 10.97, "eval_accuracy": 0.912987012987013, "eval_f1": 0.6075949367088608, "eval_loss": 0.395553857088089, "eval_precision": 0.5581395348837209, "eval_recall": 0.6666666666666666, "eval_runtime": 0.1224, "eval_samples_per_second": 65.381, "eval_steps_per_second": 8.173, "step": 85 }, { "epoch": 12.0, "eval_accuracy": 0.9155844155844156, "eval_f1": 0.6075949367088608, "eval_loss": 0.387939453125, "eval_precision": 0.5581395348837209, "eval_recall": 0.6666666666666666, "eval_runtime": 0.3171, "eval_samples_per_second": 25.232, "eval_steps_per_second": 3.154, "step": 93 }, { "epoch": 12.9, "eval_accuracy": 0.9142857142857143, "eval_f1": 0.6134969325153374, "eval_loss": 0.3951228857040405, "eval_precision": 0.5494505494505495, "eval_recall": 0.6944444444444444, "eval_runtime": 0.452, "eval_samples_per_second": 17.699, "eval_steps_per_second": 2.212, "step": 100 }, { "epoch": 13.94, "eval_accuracy": 0.9168831168831169, "eval_f1": 0.6211180124223603, "eval_loss": 0.39693745970726013, "eval_precision": 0.5617977528089888, "eval_recall": 0.6944444444444444, "eval_runtime": 0.431, "eval_samples_per_second": 18.56, "eval_steps_per_second": 2.32, "step": 108 }, { "epoch": 14.97, "eval_accuracy": 0.912987012987013, "eval_f1": 0.5962732919254659, "eval_loss": 0.3942334055900574, "eval_precision": 0.5393258426966292, "eval_recall": 0.6666666666666666, "eval_runtime": 0.1222, "eval_samples_per_second": 65.44, "eval_steps_per_second": 8.18, "step": 116 }, { "epoch": 16.0, "eval_accuracy": 0.9155844155844156, "eval_f1": 0.608695652173913, "eval_loss": 0.3981378674507141, "eval_precision": 0.550561797752809, "eval_recall": 0.6805555555555556, "eval_runtime": 0.5596, "eval_samples_per_second": 14.297, "eval_steps_per_second": 1.787, "step": 124 }, { "epoch": 16.9, "eval_accuracy": 0.9168831168831169, "eval_f1": 0.625, "eval_loss": 0.39964303374290466, "eval_precision": 0.5681818181818182, "eval_recall": 0.6944444444444444, "eval_runtime": 0.1224, "eval_samples_per_second": 65.348, "eval_steps_per_second": 8.169, "step": 131 }, { "epoch": 17.94, "eval_accuracy": 0.9168831168831169, "eval_f1": 0.625, "eval_loss": 0.39898383617401123, "eval_precision": 0.5681818181818182, "eval_recall": 0.6944444444444444, "eval_runtime": 0.1264, "eval_samples_per_second": 63.289, "eval_steps_per_second": 7.911, "step": 139 }, { "epoch": 18.06, "eval_accuracy": 0.9168831168831169, "eval_f1": 0.625, "eval_loss": 0.39904916286468506, "eval_precision": 0.5681818181818182, "eval_recall": 0.6944444444444444, "eval_runtime": 0.1186, "eval_samples_per_second": 67.465, "eval_steps_per_second": 8.433, "step": 140 }, { "epoch": 18.06, "step": 140, "total_flos": 507367899021024.0, "train_loss": 0.25862868172781805, "train_runtime": 1414.9426, "train_samples_per_second": 1.71, "train_steps_per_second": 0.099 } ], "max_steps": 140, "num_train_epochs": 20, "total_flos": 507367899021024.0, "trial_name": null, "trial_params": null }