{ "best_metric": 0.0, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.6176753640174866, "eval_matthews_correlation": 0.0, "eval_runtime": 0.4943, "eval_samples_per_second": 2110.017, "eval_steps_per_second": 133.52, "step": 54 }, { "epoch": 2.0, "eval_loss": 0.6119449734687805, "eval_matthews_correlation": 0.0, "eval_runtime": 0.4986, "eval_samples_per_second": 2091.885, "eval_steps_per_second": 132.372, "step": 108 }, { "epoch": 3.0, "eval_loss": 0.608396589756012, "eval_matthews_correlation": 0.0, "eval_runtime": 0.5, "eval_samples_per_second": 2086.175, "eval_steps_per_second": 132.011, "step": 162 }, { "epoch": 4.0, "eval_loss": 0.6073262691497803, "eval_matthews_correlation": 0.0, "eval_runtime": 0.4975, "eval_samples_per_second": 2096.331, "eval_steps_per_second": 132.654, "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": 4.417181244756343e-06, "num_train_epochs": 4, "per_device_train_batch_size": 16, "seed": 2 } }