-
对比的 math23k 数据集来源：https://paperswithcode.com/dataset/math23k
上面测试集的测试集只有 1000 条，MathEval 提供的 math23k 测试集有 2317 条，并且对多出来的数据抽样发现是在上面数据集的训练集里的
请问 MathEval 提供的 math23k 评测数据是否使用了训练集的数据？
-
I'm using the processed data you provided to reproduce the results for MathQA.
Following the instructions, I replace the vocab.txt for bert-base-uncased folder. I use train_ft_monolingual-en.sh. Howe…
-
I got 'value accu=40.0' and found that the model uses 'bert-base-uncased' as the encoder by default. Could the reason be that I were not using a Chinese bert for math23k?
here is my instruction：
`…
-
### Describe the feature
· https://github.com/SCNU203/Math23k
Math23K is a dataset consisting of 23,164 elementary school Chinese math application problems. These questions are collected from variou…
-
Hi, I wanted to trained the model by RobertaGen, but it always showed the error "robertagen can't be found", why did it happend? That's my code below:
python run_mwptoolkit.py --model=RoBERTaGen --da…
-
Hello,
Thank you for the code.But I ran into some problems,I don't know how to run your code.
I wanted to reproduce your training results, but I packed up the entire file and uploaded it to Goog…
-
I would like to use your pre-trained model.
Would there be any way to use it?
-
I would like to ask you if you can provide the check points of the model with MAWPS as well.
-
↓日本語論文まとめ
-
### 起始日期 | Start Date
_No response_
### 实现PR | Implementation PR
_No response_
### 相关Issues | Reference Issues
_No response_
### 摘要 | Summary
可以提供Math23K数据集对应的评测脚本和数据吗？
### 基本示例 | Basic Exampl…