{ "best_metric": 0.44455763518973207, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138", "epoch": 2.0, "eval_steps": 500, "global_step": 2138, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4677268475210477, "grad_norm": 8.62888240814209, "learning_rate": 5.373752855939329e-06, "loss": 0.5755, "step": 500 }, { "epoch": 0.9354536950420954, "grad_norm": 20.624385833740234, "learning_rate": 4.381186757686775e-06, "loss": 0.5165, "step": 1000 }, { "epoch": 1.0, "eval_loss": 0.5140782594680786, "eval_matthews_correlation": 0.4102877158206736, "eval_runtime": 2.0196, "eval_samples_per_second": 516.439, "eval_steps_per_second": 32.68, "step": 1069 }, { "epoch": 1.4031805425631432, "grad_norm": 10.336002349853516, "learning_rate": 3.38862065943422e-06, "loss": 0.4425, "step": 1500 }, { "epoch": 1.8709073900841908, "grad_norm": 11.466729164123535, "learning_rate": 2.396054561181666e-06, "loss": 0.4078, "step": 2000 }, { "epoch": 2.0, "eval_loss": 0.5298678874969482, "eval_matthews_correlation": 0.44455763518973207, "eval_runtime": 2.0041, "eval_samples_per_second": 520.439, "eval_steps_per_second": 32.933, "step": 2138 } ], "logging_steps": 500, "max_steps": 3207, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 75003196354260.0, "train_batch_size": 8, "trial_name": null, "trial_params": { "learning_rate": 6.366318954191884e-06, "num_train_epochs": 3, "per_device_train_batch_size": 8, "seed": 21 } }