{ "best_metric": 0.48193970397464586, "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1070", "epoch": 2.0, "eval_steps": 500, "global_step": 1070, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9345794392523364, "grad_norm": 7.622775554656982, "learning_rate": 9.778478536884857e-06, "loss": 0.5241, "step": 500 }, { "epoch": 1.0, "eval_loss": 0.4830199182033539, "eval_matthews_correlation": 0.46026235307744706, "eval_runtime": 0.8066, "eval_samples_per_second": 1293.029, "eval_steps_per_second": 81.822, "step": 535 }, { "epoch": 1.8691588785046729, "grad_norm": 4.373930931091309, "learning_rate": 1.2008657852314734e-06, "loss": 0.3568, "step": 1000 }, { "epoch": 2.0, "eval_loss": 0.5022780895233154, "eval_matthews_correlation": 0.48193970397464586, "eval_runtime": 0.992, "eval_samples_per_second": 1051.423, "eval_steps_per_second": 66.533, "step": 1070 } ], "logging_steps": 500, "max_steps": 1070, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 85536683075904.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 1.835609128853824e-05, "num_train_epochs": 2, "per_device_train_batch_size": 16, "seed": 15 } }