Comments (2)
设置 train_on_prompt: false
from llama-factory.
是因为GLM3无法使用train on prompt吗,什么时候能有支持prompt训练的模板?或者是需要我自己创建模板进行训练。
from llama-factory.
Related Issues (20)
- 大佬们,如何使用vllm进行predict预测blue和rouge分数
- 大佬问一个大模型分词问题
- 训练完成之后结果非常不理想
- 可以支持DashInfer格式的大模型训练吗?
- 如何避免每个GPU都开启一个模型 HOT 4
- DPO训练报错: TypeError: only integer tensors of a single element can be converted to an index,但是SFT训练正常运行。 HOT 3
- 节点数变大之后,数据处理会报错
- llama3添加系统提示词后回答出现Human: Assistant: HOT 5
- DoRA能够正常训练,但训练生成的检查点加载后占用显存过高。
- llama微调后重复输出,在常见问题中未能解决 HOT 5
- 微调glm4模型的时候会出现loss一直为0.0的情况 HOT 2
- predict计算blue和rouge分数,如何看日志啊?
- 验证时没有计算eval_loss HOT 1
- 微调完成后,模型怎么保存成bf16数据类型。 HOT 1
- DPO 6卡4090 使用deepspeed zero3训练很慢
- If I want to randomly freeze a specified number of layers during training, which training method should I change? HOT 1
- cannot import name 'log' from 'torch.distributed.elastic.agent.server.api' HOT 1
- safetensors_rust.SafetensorError: Error while serializing: IoError(Os { code: 28, kind: StorageFull, message: "No space left on device" }) HOT 1
- ppo 训练 HOT 2
- `main_process_ip` 和 `main_process_port` 未配置,重新运行 accelerate config HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llama-factory.