Open abhishek-jha13 opened 4 years ago
Sorry, I haven't released trained CoQA model to public yet
No Worries, I was able to train the model using your code
Great!
No Worries, I was able to train the model using your code
what accuracy were you able to achieve?
Sorry, I haven't released trained CoQA model to public yet
Hi! I’m wondering if you’vr released trained CoQa model by now?
No Worries, I was able to train the model using your code
what accuracy were you able to achieve?
I was able to achieve an F1 score of 87. If you need my help, email me at abhishekjha13@gmail.com
Sorry, I haven't released trained CoQA model to public yet
I'm trying to train XLNET on COQA using your 'run_coqa' script, but my Google Colab notebooks keep crashing. I tried using both CPU and GPU notebook instances and changing batch_size to 1, but they still keep crashing and showing the:
'Allocation of 16777216 exceeds 10% of system memory.' error.
Did you face any similar memory usage errors and did you manage to fix them?
There is bug in the code which causes an infinite loop which causes crashing. Try to fix that.
Hmm, do you mean in my code or in the xlnet library?
On Wed, 9 Sep 2020 at 05:29, abhishek-jha13 notifications@github.com wrote:
There is bug in the code which causes an infinite loop which causes crashing. Try to fix that.
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/stevezheng23/xlnet_extension_tf/issues/79#issuecomment-689277315, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQQZJ3FDV3P3AFNBQMD6TW3SE3ZA3ANCNFSM4KNBDRXQ .
There is a bug in the run_coqa.py
I’m really struggling to find it. Could you make a pull-request on this repo, so that this can be patched?
On Wed, 9 Sep 2020 at 08:28, abhishek-jha13 notifications@github.com wrote:
There is a bug in the run_coqa.py
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/stevezheng23/xlnet_extension_tf/issues/79#issuecomment-689336396, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQQZJ3HHEGKURBSLUVYJF7DSE4OCLANCNFSM4KNBDRXQ .
There is a bug in the run_coqa.py
Please feel free to send out a PR for fixing the bug, thanks!
I want to use pre-trained question answering model trained on coQA like hugging face. Do we have something available?