{ "best_metric": null, "best_model_checkpoint": null, "epoch": 6.666666666666667, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.666666666666667, "grad_norm": 0.6133930087089539, "learning_rate": 0.0, "loss": 0.9894, "step": 10 }, { "epoch": 6.666666666666667, "step": 10, "total_flos": 77551836020736.0, "train_loss": 0.9893854141235352, "train_runtime": 10.295, "train_samples_per_second": 5.828, "train_steps_per_second": 0.971 } ], "logging_steps": 10, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 77551836020736.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }