{ "best_metric": 0.3174082040786743, "best_model_checkpoint": "gal_sp_mBERT/checkpoint-750", "epoch": 4.0, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.8976631501472031, "eval_f1": 0.6289719626168223, "eval_loss": 0.36869561672210693, "eval_precision": 0.682786608048698, "eval_recall": 0.5830205024545192, "eval_runtime": 5.5033, "eval_samples_per_second": 181.163, "eval_steps_per_second": 11.448, "step": 250 }, { "epoch": 2.0, "learning_rate": 1.9600000000000002e-05, "loss": 0.4367, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.914622178606477, "eval_f1": 0.7035446539049421, "eval_loss": 0.3205152750015259, "eval_precision": 0.7093791281373845, "eval_recall": 0.6978053710655501, "eval_runtime": 5.8377, "eval_samples_per_second": 170.785, "eval_steps_per_second": 10.792, "step": 500 }, { "epoch": 3.0, "eval_accuracy": 0.9163702158979392, "eval_f1": 0.7188652482269503, "eval_loss": 0.3174082040786743, "eval_precision": 0.7064399219403401, "eval_recall": 0.7317354894600058, "eval_runtime": 5.6206, "eval_samples_per_second": 177.384, "eval_steps_per_second": 11.209, "step": 750 }, { "epoch": 4.0, "learning_rate": 1.9200000000000003e-05, "loss": 0.2325, "step": 1000 }, { "epoch": 4.0, "eval_accuracy": 0.9164315505397449, "eval_f1": 0.709383145091225, "eval_loss": 0.32722988724708557, "eval_precision": 0.7114435085681092, "eval_recall": 0.7073346809125036, "eval_runtime": 5.4618, "eval_samples_per_second": 182.541, "eval_steps_per_second": 11.535, "step": 1000 } ], "max_steps": 25000, "num_train_epochs": 100, "total_flos": 623488737039000.0, "trial_name": null, "trial_params": null }