{ "best_metric": 0.16614657640457153, "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_f89a5abe/checkpoint-3744", "epoch": 2.0, "eval_steps": 500, "global_step": 3744, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.27, "learning_rate": 9.109686609686609e-07, "loss": 0.4669, "step": 500 }, { "epoch": 0.53, "learning_rate": 8.219373219373219e-07, "loss": 0.2923, "step": 1000 }, { "epoch": 0.8, "learning_rate": 7.329059829059828e-07, "loss": 0.2644, "step": 1500 }, { "epoch": 1.0, "eval_accuracy": 0.9365846057961982, "eval_f1": 0.9374518233030922, "eval_loss": 0.20392829179763794, "eval_precision": 0.9391690915156866, "eval_recall": 0.9365846057961982, "eval_runtime": 9.474, "eval_samples_per_second": 677.432, "eval_steps_per_second": 42.432, "step": 1872 }, { "epoch": 1.07, "learning_rate": 6.438746438746438e-07, "loss": 0.2187, "step": 2000 }, { "epoch": 1.34, "learning_rate": 5.548433048433048e-07, "loss": 0.207, "step": 2500 }, { "epoch": 1.6, "learning_rate": 4.658119658119658e-07, "loss": 0.2034, "step": 3000 }, { "epoch": 1.87, "learning_rate": 3.767806267806268e-07, "loss": 0.1867, "step": 3500 }, { "epoch": 2.0, "eval_accuracy": 0.946712371455282, "eval_f1": 0.9475582315535889, "eval_loss": 0.16614657640457153, "eval_precision": 0.9495886957118708, "eval_recall": 0.946712371455282, "eval_runtime": 9.3971, "eval_samples_per_second": 682.974, "eval_steps_per_second": 42.779, "step": 3744 } ], "logging_steps": 500, "max_steps": 5616, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2005789101411648.0, "trial_name": null, "trial_params": null }