{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9876543209876543, "eval_steps": 500, "global_step": 40, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.6172839506172839, "grad_norm": 1.1812665462493896, "learning_rate": 3.846153846153846e-05, "loss": 1.2185, "step": 25 }, { "epoch": 0.9876543209876543, "step": 40, "total_flos": 7011717989007360.0, "train_loss": 1.1948750972747804, "train_runtime": 1243.0255, "train_samples_per_second": 0.13, "train_steps_per_second": 0.032 } ], "logging_steps": 25, "max_steps": 40, "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": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7011717989007360.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }