{ "best_metric": 0.0, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-14", "epoch": 4.0, "eval_steps": 500, "global_step": 56, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_loss": 0.6364148259162903, "eval_matthews_correlation": 0.0, "eval_runtime": 0.7423, "eval_samples_per_second": 1405.066, "eval_steps_per_second": 88.911, "step": 14 }, { "epoch": 2.0, "eval_loss": 0.6171813011169434, "eval_matthews_correlation": 0.0, "eval_runtime": 0.7892, "eval_samples_per_second": 1321.514, "eval_steps_per_second": 83.624, "step": 28 }, { "epoch": 3.0, "eval_loss": 0.6131183505058289, "eval_matthews_correlation": 0.0, "eval_runtime": 0.8107, "eval_samples_per_second": 1286.518, "eval_steps_per_second": 81.41, "step": 42 }, { "epoch": 4.0, "eval_loss": 0.6122009754180908, "eval_matthews_correlation": 0.0, "eval_runtime": 0.8211, "eval_samples_per_second": 1270.242, "eval_steps_per_second": 80.38, "step": 56 } ], "logging_steps": 500, "max_steps": 56, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 0, "train_batch_size": 64, "trial_name": null, "trial_params": { "learning_rate": 5.296109483200084e-06, "num_train_epochs": 4, "per_device_train_batch_size": 64, "seed": 4 } }