{ "best_metric": 0.0020041936077177525, "best_model_checkpoint": "./model_irony/checkpoint-900", "epoch": 2.0, "global_step": 900, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 1.866666666666667e-05, "loss": 0.0022, "step": 450 }, { "epoch": 1.0, "eval_accuracy": 0.730349344978166, "eval_f1": 0.7263157894736844, "eval_loss": 0.002291674492880702, "eval_precision": 0.7373453318335208, "eval_recall": 0.7156113537117904, "eval_runtime": 5.5801, "eval_samples_per_second": 656.615, "eval_steps_per_second": 41.038, "step": 450 }, { "epoch": 2.0, "learning_rate": 1.7333333333333336e-05, "loss": 0.0004, "step": 900 }, { "epoch": 2.0, "eval_accuracy": 0.7516375545851528, "eval_f1": 0.7462353597322923, "eval_loss": 0.0020041936077177525, "eval_precision": 0.7628278221208666, "eval_recall": 0.730349344978166, "eval_runtime": 5.635, "eval_samples_per_second": 650.223, "eval_steps_per_second": 40.639, "step": 900 } ], "max_steps": 6750, "num_train_epochs": 15, "total_flos": 738972065640000.0, "trial_name": null, "trial_params": null }