Comments (3)
所以你的特定领域数据集大小大概是?以及你最终的loss是?
from chatglm-llama-chinese-insturct.
目前我用的数据集较小才1000条问答数据,最终的loss如下,可以请教一下怎么样才能提升微调效果嘛,需要增加数据集到多少条?语料的质量是不是也会对微调结果产生比较大的影响?
train/epoch 3.0
wandb: train/global_step 1497
wandb: train/loss 3.3408
wandb: train/total_flos 8172835011870720.0
wandb: train/train_loss 3.5233
from chatglm-llama-chinese-insturct.
我微调后loss是0.0几,然而加载模型后也没有效果,完全没有,很奇怪
from chatglm-llama-chinese-insturct.
Related Issues (20)
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1! HOT 4
- 指定一下device吧
- 微调之后,chatglm-lora.pt的大小6.4G,是不是有问题啊? HOT 9
- 扩充中文词表后微调 HOT 1
- RuntimeError: Boolean value of Tensor with more than one value is ambiguous HOT 4
- 生成的回复有额外的“问题”是啥原因 HOT 5
- tensor不匹配问题 HOT 4
- ValueError: Can't find config.json at './best_ckpt' HOT 1
- 微调报错:RuntimeError: CUDA error: device-side assert triggered HOT 2
- llama-7b 自己的数据微调完answer一直在重复同一句话,而且也不是正确答案 HOT 7
- ValueError: 150004 is not in list 貌似是 input_ids的问题,麻烦帮忙看下哈 HOT 1
- 如何制作训练样本zh-data01.json? HOT 1
- 貌似这份代码在处理数据的时候把中文标点符号转化成了英文的?能帮忙指明下这部分代码在哪里吗?
- AttributeError: /root/anaconda3/envs/bab/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cget_col_row_stats HOT 1
- 训练时间的问题? HOT 1
- 请问作者是在A100训练的吗,我在A100没问题,在V100会报错,调整之后loss为0
- 怎么在input中把history加进去? HOT 3
- 请问下为什么在训练数据时要限制320最大长度? HOT 1
- bug
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 chatglm-llama-chinese-insturct.