{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5, "grad_norm": 23.098186492919922, "learning_rate": 4e-05, "loss": 20.3615234375, "step": 5 }, { "epoch": 1.0, "grad_norm": 20.22834014892578, "learning_rate": 4.555555555555556e-05, "loss": 18.719927978515624, "step": 10 }, { "epoch": 1.5, "grad_norm": 26.030532836914062, "learning_rate": 4e-05, "loss": 15.761956787109375, "step": 15 }, { "epoch": 2.0, "grad_norm": 18.831279754638672, "learning_rate": 3.444444444444445e-05, "loss": 12.686418151855468, "step": 20 }, { "epoch": 2.5, "grad_norm": 11.36743450164795, "learning_rate": 2.8888888888888888e-05, "loss": 10.551300811767579, "step": 25 }, { "epoch": 3.0, "grad_norm": 11.401389122009277, "learning_rate": 2.3333333333333336e-05, "loss": 9.241132354736328, "step": 30 }, { "epoch": 3.5, "grad_norm": 9.021888732910156, "learning_rate": 1.777777777777778e-05, "loss": 8.222637939453126, "step": 35 }, { "epoch": 4.0, "grad_norm": 8.384751319885254, "learning_rate": 1.2222222222222222e-05, "loss": 7.461705017089844, "step": 40 }, { "epoch": 4.5, "grad_norm": 7.771845817565918, "learning_rate": 6.666666666666667e-06, "loss": 7.064363098144531, "step": 45 }, { "epoch": 5.0, "grad_norm": 7.118314743041992, "learning_rate": 1.1111111111111112e-06, "loss": 6.785512542724609, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 583136829726720.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }