{ "best_global_step": 300, "best_metric": 0.8175438596491228, "best_model_checkpoint": "outputs/distilbert-lora-multilabel/checkpoint-300", "epoch": 9.375, "eval_steps": 150, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.125, "grad_norm": 0.41905462741851807, "learning_rate": 0.0002817708333333333, "loss": 0.6864, "step": 100 }, { "epoch": 4.6875, "eval_f1_macro": 0.7462122292280096, "eval_f1_micro": 0.7950963222416813, "eval_loss": 0.47137245535850525, "eval_precision_micro": 0.7773972602739726, "eval_recall_micro": 0.8136200716845878, "eval_runtime": 1.1588, "eval_samples_per_second": 144.974, "eval_steps_per_second": 3.452, "step": 150 }, { "epoch": 6.25, "grad_norm": 0.30065807700157166, "learning_rate": 0.0002296875, "loss": 0.4746, "step": 200 }, { "epoch": 9.375, "grad_norm": 0.2939732074737549, "learning_rate": 0.00017760416666666665, "loss": 0.4416, "step": 300 }, { "epoch": 9.375, "eval_f1_macro": 0.7699460773144984, "eval_f1_micro": 0.8175438596491228, "eval_loss": 0.4503212869167328, "eval_precision_micro": 0.8006872852233677, "eval_recall_micro": 0.8351254480286738, "eval_runtime": 1.1768, "eval_samples_per_second": 142.759, "eval_steps_per_second": 3.399, "step": 300 } ], "logging_steps": 100, "max_steps": 640, "num_input_tokens_seen": 0, "num_train_epochs": 20, "save_steps": 150, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 417105484050000.0, "train_batch_size": 24, "trial_name": null, "trial_params": null }