{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 330, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.779943585395813, "learning_rate": 9.95071753514617e-05, "loss": 2.6508, "step": 33 }, { "epoch": 2.0, "grad_norm": 1.3855775594711304, "learning_rate": 9.453892880090696e-05, "loss": 0.9286, "step": 66 }, { "epoch": 3.0, "grad_norm": 1.2113683223724365, "learning_rate": 8.472890717343391e-05, "loss": 0.5889, "step": 99 }, { "epoch": 4.0, "grad_norm": 1.3740702867507935, "learning_rate": 7.114354649475499e-05, "loss": 0.3735, "step": 132 }, { "epoch": 5.0, "grad_norm": 0.7858107089996338, "learning_rate": 5.525969550182577e-05, "loss": 0.2275, "step": 165 }, { "epoch": 6.0, "grad_norm": 1.551007866859436, "learning_rate": 3.880406913668777e-05, "loss": 0.1282, "step": 198 }, { "epoch": 7.0, "grad_norm": 0.5927512645721436, "learning_rate": 2.3565539376167295e-05, "loss": 0.0817, "step": 231 }, { "epoch": 8.0, "grad_norm": 0.3906025290489197, "learning_rate": 1.1200669042715161e-05, "loss": 0.0569, "step": 264 }, { "epoch": 9.0, "grad_norm": 0.464603453874588, "learning_rate": 3.0536287893223604e-06, "loss": 0.0416, "step": 297 }, { "epoch": 10.0, "grad_norm": 0.2005661427974701, "learning_rate": 1.0073873344895735e-08, "loss": 0.0386, "step": 330 } ], "logging_steps": 500, "max_steps": 330, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 928975928739840.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }