{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 102, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.19950124688279303, "grad_norm": 2.516839958843775e-05, "learning_rate": 0.00016363636363636366, "loss": 3.0967, "step": 10 }, { "epoch": 0.39900249376558605, "grad_norm": 2.9362299756030552e-05, "learning_rate": 0.00019621030198436006, "loss": 2.2956, "step": 20 }, { "epoch": 0.5985037406483791, "grad_norm": 1.008875642583007e-05, "learning_rate": 0.00018130560994785325, "loss": 2.0889, "step": 30 }, { "epoch": 0.7980049875311721, "grad_norm": 1.1583351806621067e-05, "learning_rate": 0.00015680647467311557, "loss": 1.9784, "step": 40 }, { "epoch": 0.9975062344139651, "grad_norm": 1.18182670121314e-05, "learning_rate": 0.0001256039090057547, "loss": 1.8224, "step": 50 }, { "epoch": 1.1795511221945136, "grad_norm": 1.2619072549568955e-05, "learning_rate": 9.137996201193805e-05, "loss": 1.6893, "step": 60 }, { "epoch": 1.3790523690773067, "grad_norm": 1.5141326912271325e-05, "learning_rate": 5.817321992244351e-05, "loss": 1.7017, "step": 70 }, { "epoch": 1.5785536159600997, "grad_norm": 1.3717271031055134e-05, "learning_rate": 2.9902234019385057e-05, "loss": 1.7029, "step": 80 }, { "epoch": 1.7780548628428927, "grad_norm": 1.1637918760243338e-05, "learning_rate": 9.903113209758096e-06, "loss": 1.6202, "step": 90 }, { "epoch": 1.9775561097256857, "grad_norm": 1.4227169231162407e-05, "learning_rate": 5.358475304807375e-07, "loss": 1.693, "step": 100 } ], "logging_steps": 10, "max_steps": 102, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 1.4162734662392218e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }