Wenxuan Zeng
Wenxuan Zeng
I have read other issues in this repo and I find the number of epochs is set to 200 by default. Other training details are: `batch-size=128, learning-rate=0.1, momentum=0.9, weight-decay=1e-4, optimizer='SGD',...
The version of your installed tensorflow lib should be modified as follows: ``` pip install tensorflow==2.9.1 ```
> Hi, @zwxandy In fact, I have the same issue during the re-implementation of this paper. Also, it seems that during training, the 'zoom' effect fades away eventually. (see #1)...
> Thanks for your patience, but specify "tokenizer.pad_token_id=tokenizer.eos_token_id" still cannot solve the problem. Since I couldn't come up with a better solution, I just skip the sample 797 in the...
> Hi everyone, I have another question regarding reproducing XSUM results. In h2o_hf/scripts/summarization/eval.sh, it sets a fixed HH_SIZE and RECENT_SIZE, but the x-axis of figure 4 represents KV Cache Budget...
> Hi everyone, I have another question regarding reproducing XSUM results. In h2o_hf/scripts/summarization/eval.sh, it sets a fixed HH_SIZE and RECENT_SIZE, but the x-axis of figure 4 represents KV Cache Budget...
> datasets Hi, have you solved this bug? Today I also met the same problem about `livecodebench/code_generation_lite` when evaluating the `Open-R1` repo. I am looking forward to your reply! 
> Hey guys, I tried to reproduce the issue and it works fine. I used google colab as enviroment. > >  Thanks for your kind reply! I wonder which...
> > [@Serzhanov](https://github.com/Serzhanov) [@zwxandy](https://github.com/zwxandy) I have met the same problem, have this problem be solved? > > I try to downgrade datasets version to 2.20.0，and it works for me [@Serzhanov](https://github.com/Serzhanov)...
> > > datasets > > > > > > Hi, have you solved this bug? Today I also met the same problem about `livecodebench/code_generation_lite` when evaluating the `Open-R1` repo....