{ "best_metric": 0.0, "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-5/checkpoint-54", "epoch": 4.0, "eval_steps": 500, "global_step": 216, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_loss": 0.6138535737991333, "eval_matthews_correlation": 0.0, "eval_runtime": 8.6936, "eval_samples_per_second": 119.973, "eval_steps_per_second": 7.592, "step": 54 }, { "epoch": 2.0, "eval_loss": 0.6022257208824158, "eval_matthews_correlation": 0.0, "eval_runtime": 9.1939, "eval_samples_per_second": 113.445, "eval_steps_per_second": 7.179, "step": 108 }, { "epoch": 3.0, "eval_loss": 0.576120138168335, "eval_matthews_correlation": 0.0, "eval_runtime": 9.1717, "eval_samples_per_second": 113.719, "eval_steps_per_second": 7.196, "step": 162 }, { "epoch": 4.0, "eval_loss": 0.5622713565826416, "eval_matthews_correlation": 0.0, "eval_runtime": 9.1866, "eval_samples_per_second": 113.535, "eval_steps_per_second": 7.184, "step": 216 } ], "logging_steps": 500, "max_steps": 216, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 1.1908992105042739e-06, "num_train_epochs": 4, "per_device_train_batch_size": 16, "seed": 32 } }