{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 100.0, "global_step": 32, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.032, "grad_norm": 6.537508219915155, "learning_rate": 5e-06, "loss": 1.17765212059021, "step": 1, "token_acc": 0.7183687696061345 }, { "epoch": 0.32, "grad_norm": 2.4235948232112827, "learning_rate": 8.345653031794292e-06, "loss": 0.8832758797539605, "step": 10, "token_acc": 0.7595048365153169 }, { "epoch": 0.64, "grad_norm": 1.9923198359193495, "learning_rate": 3.4549150281252635e-06, "loss": 0.7281403541564941, "step": 20, "token_acc": 0.780530679933665 }, { "epoch": 0.96, "grad_norm": 1.9421069401461988, "learning_rate": 1.0926199633097156e-07, "loss": 0.7198718547821045, "step": 30, "token_acc": 0.782446952482265 } ], "logging_steps": 10, "max_steps": 32, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 942560708608.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }