Comments (4)
Hi~ zhangir-azerbayev, Thanks for your attention!
have you fixed this error?
I retested it, and I am able to obtain the expected numbers. it works for both 1x A100 80GB and 8x A100 80GB
The environment I am using is:
torch==2.0.1+cu117
vllm==0.1.4
transformers==4.31.0
from metamath.
Hi~ zhangir-azerbayev, Thanks for your attention!
have you fixed this error?
I retested it, and I am able to obtain the expected numbers. it works for both 1x A100 80GB and 8x A100 80GB
The environment I am using is:
torch==2.0.1+cu117
vllm==0.1.4
transformers==4.31.0
Thanks for your response. I'll retry with those package versions and report back.
from metamath.
Thanks, was able to repro the results in this paper with vllm==0.1.4 and transformers==4.31.0. Will PR a requirements.txt file when I have time.
from metamath.
I ran the eval scripts with the weights from meta-math/MetaMath-7(13)B-V1.0 and obtained scores of 0.1948 for 7B and 0.2238 for 13B. However, when I �ran SFT on the metamathqa data for LLama2-7B/13B, I got 0 score for math and 0.71 for gsm8k. What could be the reason for the score of 0 in math, and how can I prevent it? (I don't think it's an issue with the package version.)
The environment I am using is:
torch==2.0.1+cu118
vllm==0.1.4
transformers==4.34.0
from metamath.
Related Issues (20)
- Ask for adding a new baseline——MuggleMATH in the Comparing MetaMath with the LLM models HOT 1
- Modified parameter name that is different from README. HOT 1
- Problem regarding the evaluation codes of the GSM8K - `eval_gsm8k.py` HOT 1
- OOM HOT 1
- will there be ablation studies? HOT 2
- How many tokens did MetaMath train on?
- May I know how you load QLoRA+LLaMA 70B with vllm? HOT 1
- MetaMath-Mistral-7B gsm8k/math acc different from the reported values HOT 2
- the few-shot in-context learning issues. HOT 1
- Is the MetaMathQA dataset suitable for pre-training? HOT 1
- Potential error in eval_gsm8k.py
- path/to/llama-2 HOT 2
- Error in run_create_backward_questions.sh HOT 2
- Questions about MetaMATH dataset
- The accuracy of MATH test set trained on 7B is not consistent with paper. HOT 1
- Metamath dataset for separated for different math subjects
- Issue with Fine-tuning Mistral 7B Model - Results Discrepancy HOT 2
- eval_math and eval_gsm8k
- Transformers and Tokenizers version conflict. HOT 1
- Are the MetaMath Eval Result valid? e.g., What is the standard way to evaluate on MATH?
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 metamath.