{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.013745704467353952, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006872852233676976, "grad_norm": 20.37238311767578, "learning_rate": 1e-05, "loss": 13.6308, "step": 1 }, { "epoch": 0.006872852233676976, "eval_loss": 13.368016242980957, "eval_runtime": 111.4088, "eval_samples_per_second": 2.199, "eval_steps_per_second": 1.104, "step": 1 }, { "epoch": 0.013745704467353952, "grad_norm": 20.47346305847168, "learning_rate": 2e-05, "loss": 13.2721, "step": 2 }, { "epoch": 0.013745704467353952, "eval_loss": 12.771807670593262, "eval_runtime": 12.4302, "eval_samples_per_second": 19.71, "eval_steps_per_second": 9.895, "step": 2 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1479677168320512.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }