{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016129032258064516, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005376344086021505, "grad_norm": 0.2367846965789795, "learning_rate": 2e-05, "loss": 1.1054, "step": 1 }, { "epoch": 0.0005376344086021505, "eval_loss": 1.1771646738052368, "eval_runtime": 50.2759, "eval_samples_per_second": 15.594, "eval_steps_per_second": 7.797, "step": 1 }, { "epoch": 0.001075268817204301, "grad_norm": 0.2534483075141907, "learning_rate": 4e-05, "loss": 1.0431, "step": 2 }, { "epoch": 0.0016129032258064516, "grad_norm": 0.2641952931880951, "learning_rate": 6e-05, "loss": 1.1042, "step": 3 }, { "epoch": 0.0016129032258064516, "eval_loss": 1.1709295511245728, "eval_runtime": 51.3001, "eval_samples_per_second": 15.283, "eval_steps_per_second": 7.641, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 977249545224192.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }