{ "epoch": 0.07407407407407407, "global_step": 10, "max_steps": 12, "logging_steps": 10, "eval_steps": 10, "save_steps": 5, "train_batch_size": 8, "num_train_epochs": 1, "num_input_tokens_seen": 0, "total_flos": 5313378151366656.0, "log_history": [ { "loss": 0.688, "grad_norm": 0.5886830687522888, "learning_rate": 0.0001, "epoch": 0.07407407407407407, "step": 10 }, { "eval_loss": 0.31789010763168335, "eval_runtime": 428.825, "eval_samples_per_second": 0.529, "eval_steps_per_second": 0.133, "epoch": 0.07407407407407407, "step": 10 } ], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": { "TrainerControl": { "args": { "should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false }, "attributes": {} } } }