{ "best_metric": 0.2816326530612245, "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-4\\checkpoint-276", "epoch": 2.0, "eval_steps": 500, "global_step": 276, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.27346938775510204, "eval_loss": 2.3406941890716553, "eval_runtime": 1.1, "eval_samples_per_second": 222.719, "eval_steps_per_second": 14.545, "step": 138 }, { "epoch": 2.0, "eval_accuracy": 0.2816326530612245, "eval_loss": 2.316737174987793, "eval_runtime": 1.269, "eval_samples_per_second": 193.066, "eval_steps_per_second": 12.608, "step": 276 } ], "logging_steps": 500, "max_steps": 276, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "total_flos": 0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 3.631800261031757e-06, "num_train_epochs": 2, "per_device_train_batch_size": 16, "seed": 19 } }