Scott(SeokHwan) Song
Scott(SeokHwan) Song
When I run it on Collab, it returns this ``` Running mawps with bert model chinese-bert-wwm-ext and var update mode gru scripts/run_math23k.bash: line 18: logs/math23k_chinese-bert-wwm-ext_gru_500.log: No such file or directory...
> Yes, it would be great if I could use that.
Oh, if that is possible, can you try it, please?
Thank you! I am working on MathQA as well now and this is what I got. Can you have a look at it? I cannot figure out what the problem...
I tested the model with the checkpoints of MathQA and as you can see that 'tokenization' does not work well and accuracies are very low. Actually it worked completely well...
I would like to use the models using any English math word problems. These are my questions. 1. I am not familiar with using pre-trained model, so is it enough...