{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4, "grad_norm": 47.25, "learning_rate": 4.267766952966369e-06, "loss": 10.7132, "step": 20 }, { "epoch": 0.8, "grad_norm": 60.75, "learning_rate": 7.322330470336314e-07, "loss": 9.0428, "step": 40 }, { "epoch": 1.0, "step": 50, "total_flos": 8994587443200.0, "train_loss": 9.614606323242187, "train_runtime": 45.3037, "train_samples_per_second": 4.415, "train_steps_per_second": 1.104 } ], "logging_steps": 20, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8994587443200.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }