Astariul
Astariul
In the section [Policy Gradients diagnostics](https://github.com/williamFalcon/DeepRLHacks#policy-gradient-diagnostics), it is mentioned : > If KL is .01 then very small. If 10 then too much. I couldn't find the given values in...
I'm trying to fine tune BERT on STS-B dataset. I used the following [notebook](https://colab.research.google.com/drive/1162FvpuCpmkudylOC3m8Llc2CGdjL8Rl) to fine tune it using BERT-keras. (As described in the paper, I just added a classification...
Because of how WikiHow present its article : > **Summary** > > Text Some article are written in a way where what's supposed to be the summary is actually the...
Creating a `requirements.txt` file might help users for dependencies :)
I'm running your code on the CNN/Dailymail dataset. However, training never end, displaying : > Batch #X with X growing more and more. I waited a long time, then kill...
I tried to run the code with a batch size of 8, however I got this error : > InvalidArgumentError (see above for traceback): Incompatible shapes at component 0: expected...
How did you get the data txt files ? How did you process it ? Did you tokenize it ?
To fix #68, ROUGE-N metric is added to Rouge. Taken from : https://github.com/pltrdy/seq2seq/blob/master/seq2seq/metrics/rouge.py Results might be slightly different from official ROUGE-155 script, but at least code is very simple.