{ "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": 0.5333333333333333, "grad_norm": 0.21942713856697083, "learning_rate": 0.000199107748815478, "loss": 0.7714, "step": 5 }, { "epoch": 1.0, "grad_norm": 0.27160170674324036, "learning_rate": 0.00018925188358598813, "loss": 0.6282, "step": 10 }, { "epoch": 1.5333333333333332, "grad_norm": 0.16776053607463837, "learning_rate": 0.00016951924276746425, "loss": 0.5601, "step": 15 }, { "epoch": 2.0, "grad_norm": 0.2320907711982727, "learning_rate": 0.0001420934762428335, "loss": 0.5471, "step": 20 }, { "epoch": 2.533333333333333, "grad_norm": 0.15466105937957764, "learning_rate": 0.00011000956916240985, "loss": 0.4923, "step": 25 }, { "epoch": 3.0, "grad_norm": 0.31745201349258423, "learning_rate": 7.681798497324716e-05, "loss": 0.4651, "step": 30 }, { "epoch": 3.533333333333333, "grad_norm": 0.19490917026996613, "learning_rate": 4.6191764683662744e-05, "loss": 0.4367, "step": 35 }, { "epoch": 4.0, "grad_norm": 0.3345278799533844, "learning_rate": 2.1520061472133902e-05, "loss": 0.4268, "step": 40 }, { "epoch": 4.533333333333333, "grad_norm": 0.156062051653862, "learning_rate": 5.533090839208133e-06, "loss": 0.402, "step": 45 }, { "epoch": 5.0, "grad_norm": 0.24310481548309326, "learning_rate": 0.0, "loss": 0.4084, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 6, "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": 2.5642849233567744e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }