{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0476190476190474, "eval_steps": 25, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.38095238095238093, "grad_norm": 0.0, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.38095238095238093, "eval_loss": NaN, "eval_runtime": 0.7227, "eval_samples_per_second": 24.908, "eval_steps_per_second": 4.151, "step": 1 }, { "epoch": 0.7619047619047619, "grad_norm": 0.0, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 2 }, { "epoch": 1.1428571428571428, "grad_norm": 0.0, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 3 }, { "epoch": 1.5238095238095237, "grad_norm": 0.0, "learning_rate": 5e-05, "loss": 0.0, "step": 4 }, { "epoch": 1.9047619047619047, "grad_norm": 0.0, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 5 }, { "epoch": 2.2857142857142856, "grad_norm": 0.0, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 6 }, { "epoch": 2.6666666666666665, "grad_norm": 0.0, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 7 }, { "epoch": 3.0476190476190474, "grad_norm": 0.0, "learning_rate": 0.0, "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": 2, "trial_name": null, "trial_params": null }