{ "best_metric": 0.5002057401338981, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070", "epoch": 2.0, "eval_steps": 500, "global_step": 1070, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.93, "learning_rate": 1.8206261895616947e-05, "loss": 0.5254, "step": 500 }, { "epoch": 1.0, "eval_loss": 0.4812505543231964, "eval_matthews_correlation": 0.4559278202620904, "eval_runtime": 0.73, "eval_samples_per_second": 1428.785, "eval_steps_per_second": 90.412, "step": 535 }, { "epoch": 1.87, "learning_rate": 2.2358567240231335e-06, "loss": 0.3218, "step": 1000 }, { "epoch": 2.0, "eval_loss": 0.5361687541007996, "eval_matthews_correlation": 0.5002057401338981, "eval_runtime": 0.7925, "eval_samples_per_second": 1316.068, "eval_steps_per_second": 83.28, "step": 1070 } ], "logging_steps": 500, "max_steps": 1070, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "total_flos": 86032659644700.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 3.417666706721076e-05, "num_train_epochs": 2, "per_device_train_batch_size": 16, "seed": 19 } }