{ "best_metric": 0.7027027027027026, "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-luo/checkpoint-1000", "epoch": 95.23809523809524, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 9.52, "eval_accuracy_score": 0.9252045188936502, "eval_f1": 0.6073298429319371, "eval_loss": 0.4060324430465698, "eval_precision": 0.6270270270270271, "eval_recall": 0.5888324873096447, "eval_runtime": 1.2904, "eval_samples_per_second": 71.298, "eval_steps_per_second": 9.3, "step": 200 }, { "epoch": 19.05, "eval_accuracy_score": 0.9349435138293728, "eval_f1": 0.6757493188010899, "eval_loss": 0.47699496150016785, "eval_precision": 0.7294117647058823, "eval_recall": 0.6294416243654822, "eval_runtime": 1.2894, "eval_samples_per_second": 71.351, "eval_steps_per_second": 9.307, "step": 400 }, { "epoch": 23.81, "learning_rate": 4.865771812080537e-05, "loss": 0.1354, "step": 500 }, { "epoch": 28.57, "eval_accuracy_score": 0.9287105570705103, "eval_f1": 0.6315789473684211, "eval_loss": 0.4870217740535736, "eval_precision": 0.6557377049180327, "eval_recall": 0.6091370558375635, "eval_runtime": 1.2888, "eval_samples_per_second": 71.385, "eval_steps_per_second": 9.311, "step": 600 }, { "epoch": 38.1, "eval_accuracy_score": 0.9291001168679393, "eval_f1": 0.6631853785900784, "eval_loss": 0.5066892504692078, "eval_precision": 0.6827956989247311, "eval_recall": 0.6446700507614214, "eval_runtime": 1.2903, "eval_samples_per_second": 71.303, "eval_steps_per_second": 9.3, "step": 800 }, { "epoch": 47.62, "learning_rate": 4.697986577181208e-05, "loss": 0.0036, "step": 1000 }, { "epoch": 47.62, "eval_accuracy_score": 0.9368913128165174, "eval_f1": 0.7027027027027026, "eval_loss": 0.5251720547676086, "eval_precision": 0.7514450867052023, "eval_recall": 0.6598984771573604, "eval_runtime": 1.2868, "eval_samples_per_second": 71.496, "eval_steps_per_second": 9.326, "step": 1000 }, { "epoch": 57.14, "eval_accuracy_score": 0.9333852746396571, "eval_f1": 0.6702997275204359, "eval_loss": 0.49117618799209595, "eval_precision": 0.7235294117647059, "eval_recall": 0.6243654822335025, "eval_runtime": 1.2889, "eval_samples_per_second": 71.38, "eval_steps_per_second": 9.31, "step": 1200 }, { "epoch": 66.67, "eval_accuracy_score": 0.925983638488508, "eval_f1": 0.6702412868632708, "eval_loss": 0.5857591032981873, "eval_precision": 0.7102272727272727, "eval_recall": 0.6345177664974619, "eval_runtime": 1.2888, "eval_samples_per_second": 71.384, "eval_steps_per_second": 9.311, "step": 1400 }, { "epoch": 71.43, "learning_rate": 4.530201342281879e-05, "loss": 0.0041, "step": 1500 }, { "epoch": 76.19, "eval_accuracy_score": 0.9306583560576549, "eval_f1": 0.6776859504132232, "eval_loss": 0.5567479729652405, "eval_precision": 0.7409638554216867, "eval_recall": 0.6243654822335025, "eval_runtime": 1.2907, "eval_samples_per_second": 71.28, "eval_steps_per_second": 9.297, "step": 1600 }, { "epoch": 85.71, "eval_accuracy_score": 0.9306583560576549, "eval_f1": 0.6614987080103358, "eval_loss": 0.5476430654525757, "eval_precision": 0.6736842105263158, "eval_recall": 0.649746192893401, "eval_runtime": 1.2879, "eval_samples_per_second": 71.432, "eval_steps_per_second": 9.317, "step": 1800 }, { "epoch": 95.24, "learning_rate": 4.36241610738255e-05, "loss": 0.002, "step": 2000 }, { "epoch": 95.24, "eval_accuracy_score": 0.9326061550447994, "eval_f1": 0.6772486772486772, "eval_loss": 0.5742465257644653, "eval_precision": 0.7071823204419889, "eval_recall": 0.649746192893401, "eval_runtime": 1.2841, "eval_samples_per_second": 71.646, "eval_steps_per_second": 9.345, "step": 2000 }, { "epoch": 95.24, "step": 2000, "total_flos": 8014478705879040.0, "train_loss": 0.03629368221759796, "train_runtime": 2156.3708, "train_samples_per_second": 222.596, "train_steps_per_second": 6.956 } ], "max_steps": 15000, "num_train_epochs": 715, "total_flos": 8014478705879040.0, "trial_name": null, "trial_params": null }