Dong Jiancheng

1. 我微调的是llama3 base，所以PROMPT_TEMPLATE.llama2_chat表现正常可能只是因为其中没有特殊token？ 2. 评测阶段都是用gsm8k标准对话模板，都没有对应修改 抱歉，我使用的模型是llama3 base

# Copyright (c) OpenMMLab. All rights reserved. import torch from datasets import load_dataset from mmengine.dataset import DefaultSampler from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook, LoggerHook, ParamSchedulerHook) from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR,...

好的 2024/05/07 11:11:41 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0] CUDA available: True MUSA available: False numpy_random_seed: 2139977810...