{ "best_metric": 0.7583892617449665, "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-18", "epoch": 0.9664429530201343, "eval_steps": 500, "global_step": 18, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9664429530201343, "eval_accuracy": 0.7583892617449665, "eval_loss": 0.686046838760376, "eval_runtime": 3.2219, "eval_samples_per_second": 92.493, "eval_steps_per_second": 11.794, "step": 18 } ], "logging_steps": 500, "max_steps": 126, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2706329606400000.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }