{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.3684210526315788, "eval_steps": 25, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.42105263157894735, "grad_norm": 0.0, "learning_rate": 9.657457896300791e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.42105263157894735, "eval_loss": NaN, "eval_runtime": 4.4524, "eval_samples_per_second": 11.23, "eval_steps_per_second": 2.92, "step": 1 }, { "epoch": 0.8421052631578947, "grad_norm": 0.0, "learning_rate": 8.681980515339464e-05, "loss": 0.0, "step": 2 }, { "epoch": 1.263157894736842, "grad_norm": 0.0, "learning_rate": 7.222075445642904e-05, "loss": 0.0, "step": 3 }, { "epoch": 1.6842105263157894, "grad_norm": 0.0, "learning_rate": 5.500000000000001e-05, "loss": 0.0, "step": 4 }, { "epoch": 2.1052631578947367, "grad_norm": 0.0, "learning_rate": 3.777924554357096e-05, "loss": 0.0, "step": 5 }, { "epoch": 2.526315789473684, "grad_norm": 0.0, "learning_rate": 2.3180194846605367e-05, "loss": 0.0, "step": 6 }, { "epoch": 2.9473684210526314, "grad_norm": 0.0, "learning_rate": 1.3425421036992098e-05, "loss": 0.0, "step": 7 }, { "epoch": 3.3684210526315788, "grad_norm": 0.0, "learning_rate": 1e-05, "loss": 0.0, "step": 8 } ], "logging_steps": 1, "max_steps": 8, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.548933787706982e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }