{ "best_metric": 0.777171458678308, "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-100", "epoch": 22.22222222222222, "eval_steps": 100, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 11.11111111111111, "grad_norm": 3.375645875930786, "learning_rate": 0.0004483383350728088, "loss": 0.8989, "step": 50 }, { "epoch": 22.22222222222222, "grad_norm": 2.6706221103668213, "learning_rate": 0.00020658795558326743, "loss": 0.4221, "step": 100 }, { "epoch": 22.22222222222222, "eval_accuracy": 0.7912087912087912, "eval_confusion_matrix": [ [ 59, 1, 1, 2 ], [ 20, 35, 22, 0 ], [ 2, 7, 68, 0 ], [ 2, 0, 0, 54 ] ], "eval_f1": 0.777171458678308, "eval_loss": 0.8805518746376038, "eval_precision": 0.8021831966052498, "eval_recall": 0.7912087912087912, "eval_runtime": 2.8496, "eval_samples_per_second": 95.803, "eval_steps_per_second": 1.053, "step": 100 } ], "logging_steps": 50, "max_steps": 160, "num_input_tokens_seen": 0, "num_train_epochs": 40, "save_steps": 100, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.001 }, "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": 5.511815490816e+16, "train_batch_size": 128, "trial_name": null, "trial_params": null }