{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 804, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 6.508703708648682, "learning_rate": 1.3333333333333333e-05, "loss": 0.6101, "step": 268 }, { "epoch": 1.0, "eval_loss": 0.6032158732414246, "eval_matthews_correlation": 0.1345503796973939, "eval_runtime": 8.5318, "eval_samples_per_second": 122.249, "eval_steps_per_second": 7.736, "step": 268 }, { "epoch": 2.0, "grad_norm": 11.809653282165527, "learning_rate": 6.666666666666667e-06, "loss": 0.5325, "step": 536 }, { "epoch": 2.0, "eval_loss": 0.5451133251190186, "eval_matthews_correlation": 0.3134805838230471, "eval_runtime": 8.5009, "eval_samples_per_second": 122.693, "eval_steps_per_second": 7.764, "step": 536 }, { "epoch": 3.0, "grad_norm": 9.861120223999023, "learning_rate": 0.0, "loss": 0.428, "step": 804 }, { "epoch": 3.0, "eval_loss": 0.5648320913314819, "eval_matthews_correlation": 0.3262988329908328, "eval_runtime": 8.5202, "eval_samples_per_second": 122.414, "eval_steps_per_second": 7.746, "step": 804 }, { "epoch": 3.0, "step": 804, "total_flos": 4562104380880896.0, "train_loss": 0.5235365682573461, "train_runtime": 487.6856, "train_samples_per_second": 52.602, "train_steps_per_second": 1.649 } ], "logging_steps": 500, "max_steps": 804, "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": true }, "attributes": {} } }, "total_flos": 4562104380880896.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }