Comments (5)
lemuria-wchen
commented on July 28, 2024
猜测可能是 1000步骤左右刚好过了 1 个epoch
from disc-finllm.
lemuria-wchen
commented on July 28, 2024
我们一共训练了2个epoch
from disc-finllm.
BrantonLiu
commented on July 28, 2024
噢明白了 感谢~
from disc-finllm.
ccp123456789
commented on July 28, 2024
我们一共训练了2个epoch
这个loss趋势合理吗？ 第一个epoch的时候阶梯式下降，是不是学习率什么的导致的？
from disc-finllm.
lemuria-wchen
commented on July 28, 2024
我们一共训练了2个epoch
这个loss趋势合理吗？ 第一个epoch的时候阶梯式下降，是不是学习率什么的导致的？
loss的阶梯式下降特别是在训练初期阶段应该是比较常见的现象。这代表模型正在从随机初始化LORA权重快速学习数据集的特征。对于大多数模型和优化算法（如SGD、Adam等）来说，第一个epoch结束时观察到显著的loss下降是合理的，因为模型参数开始适应训练数据。
from disc-finllm.
Related Issues (20)
- One small problem HOT 1
- performance issue HOT 2
- 读入huggingface模型报错 HOT 1
- DISC-FinLLM-SFT 完整训练数据（ToDo） HOT 3
- 下载权重以后推理结果和网站的demo不同，请问是否没有放出demo中的模型参数？ HOT 4
- 模型下载到本地后，运行报网络连接错误 HOT 4
- 请问项目的数据集可以公开么?
- 请问可以提供下 FinGPTV3 的评测代码吗？ HOT 1
- 请问模型支持的最大长度是多少；金融知识检索这个功能要怎么使用，web_demo.py文件里找不到对应功能
- Demo无法使用
- 能开源完整代码吗？包括训练和检索增强部分？
- 请问什么时候可以公开金融SFT数据集？
- 尝试autoeval , 评估chatglm2-6b,baichuan-7b 相同的错误如下： HOT 2
- Could DISC provide a pre-8bit-quantized LLM model for those whose Memory is too small HOT 1
- 公开金融SFT数据集下载 HOT 3
- [Not Issue] Will you try MOE like Mixtral-8X7B? HOT 1
- 在提供的eval复现出来结果和给出的结果有一点差距呢
- 期待公开完整数据集^_^
- Financial Calculation是如何使用的？ HOT 2
- 此项目所用的数据总量是496.000KB吗
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 disc-finllm.