[BUG] 72B-Chat版本微调时lr一直是0？loss不正常。 - Githubissues

QwenLM / Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Apache License 2.0

13.59k stars 1.11k forks source link

[BUG] 72B-Chat版本微调时lr一直是0？loss不正常。 #988

Closed chenyzh28 closed 8 months ago

chenyzh28 commented 8 months ago

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

[X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

[X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

No response

期望行为 | Expected Behavior

运行finetune_lora_ds.sh

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

OS: Ubuntu 20.04
Python: 3.8
Transformers: 4.31.0
PyTorch: 2.0.1
CUDA: 11.4

备注 | Anything else?

50986F4F-8974-411E-BE02-C724190FB9C5

jklj077 commented 8 months ago

请先升级下transformers版本看看。