-
Notifications
You must be signed in to change notification settings - Fork 136
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
train 成功了,分享一些细节。 trained successfully! Share some details with guys. #25
Comments
Thanks! Here is the English version: The training was successful! Here are the details of the environment:
{"messages":[{"role": "user", "content": "What's the weather like in Beijing?"}, {"role": "assistant", "content": "Today's weather in Beijing is clear with temperatures around 25°C."}]}
{"messages":[{"role": "user", "content": "How can I implement the Singleton pattern in Java?"}, {"role": "assistant", "content": "You can use the eager or lazy initialization method to implement the Singleton pattern. Here's an example of eager initialization:\n```java\npublic class Singleton {\n private static final Singleton instance = new Singleton();\n private Singleton() {}\n public static Singleton getInstance() {\n return instance;\n }\n}\n```"}]}
{"messages":[{"role": "user", "content": "Do you know what the Four Great Inventions of China are?"}, {"role": "assistant", "content": "China's Four Great Inventions are paper making, the compass, gunpowder, and printing."}]}
{"messages":[{"role": "user", "content": "Can you recommend any Chinese books?"}, {"role": "assistant", "content": "If you're interested in historical books, I recommend *Zizhi Tongjian*. If you're into literature, you might enjoy *Dream of the Red Chamber*."}]}
{"messages":[{"role": "user", "content": "What's the weather like in New York?"}, {"role": "assistant", "content": "The weather in New York is cloudy with a temperature around 18°C."}]}
{"messages":[{"role": "user", "content": "How can I implement a stack in Python?"}, {"role": "assistant", "content": "You can implement a stack using a list in Python. Here’s a simple example:\n```python\nstack = []\nstack.append(1)\nstack.append(2)\nprint(stack.pop()) # Outputs 2\n```"}]}
{"messages":[{"role": "user", "content": "Can you explain the concept of machine learning?"}, {"role": "assistant", "content": "Machine learning is a field of artificial intelligence where algorithms learn from data to make predictions or decisions without being explicitly programmed."}]}
{"messages":[{"role": "user", "content": "What's a good book to learn about AI?"}, {"role": "assistant", "content": "A great book to start with is 'Artificial Intelligence: A Modern Approach' by Stuart Russell and Peter Norvig. It covers a wide range of AI topics comprehensively."}]}
If you're unsure whether this step was successful, you can add some comments in these two files yourself. If an error occurs, check if the error code contains those comments. |
@LYCnight 大佬 训练的时候预计要多大的显存 |
@LYCnight 按照大佬的环境,成功的开启了训练,但是为什么训练完后的文件超级大呢?存储空间不够了…… |
GLM-4-9b 32k训练需要8卡80G。如果显存不够可以试试lora或者qlora。 |
9B的模型存下来就是这么大的,你可以设置只存模型参数不存训练的optimizer state,这样文件能小一些。 |
我的是 8 * 80G 全部跑满 |
确实大,等等官方的压缩大小的设置的文档吧 |
train成功了,分享一下环境:
modeling_chatglm.py
和tokenization_chatglm.py
都已经替换"stage3_prefetch_bucket_size": 15099494
"seq_length": 131072
tips:
/glm-4-9b 目录下的
modeling_chatglm.py
和tokenization_chatglm.py
都已经替换这一步不确定自己是否成功的小伙伴,可以在这两个代码中自己加一些注释,如果报错了就检查一下报错代码中有没有这些注释。
The text was updated successfully, but these errors were encountered: