{ "best_metric": 0.0, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-27", "epoch": 4.0, "eval_steps": 500, "global_step": 108, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_loss": 0.6132858991622925, "eval_matthews_correlation": 0.0, "eval_runtime": 0.4871, "eval_samples_per_second": 2141.162, "eval_steps_per_second": 135.491, "step": 27 }, { "epoch": 2.0, "eval_loss": 0.6033318638801575, "eval_matthews_correlation": 0.0, "eval_runtime": 0.5208, "eval_samples_per_second": 2002.541, "eval_steps_per_second": 126.719, "step": 54 }, { "epoch": 3.0, "eval_loss": 0.5928357243537903, "eval_matthews_correlation": 0.0, "eval_runtime": 0.5199, "eval_samples_per_second": 2006.182, "eval_steps_per_second": 126.949, "step": 81 }, { "epoch": 4.0, "eval_loss": 0.5839361548423767, "eval_matthews_correlation": 0.0, "eval_runtime": 0.5244, "eval_samples_per_second": 1989.096, "eval_steps_per_second": 125.868, "step": 108 } ], "logging_steps": 500, "max_steps": 135, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "total_flos": 0, "train_batch_size": 32, "trial_name": null, "trial_params": { "learning_rate": 7.921646169086052e-06, "num_train_epochs": 5, "per_device_train_batch_size": 32, "seed": 29 } }