Open macabdul9 opened 3 years ago
I can try, could you please specify exactly what knobs to adjust for your purpose?
Comment line 15 and 16 in UtteranceRNN.py
and re-train it.
PS. Now it will take more time since RoBERTa will also be trained
Seems like I don't have enough RAM for this :(
You were training it on CPU?
No, on GPU... I should have said memory, not RAM :)
In config.py batch size is 64
which will cause CUDA out of Memory
, try with smaller batch size (8 should be fine or you can go with 4 as well) if possible.
Started running now with batch = 16
:)
Each epoch will take around 2 hours, I'll report in a couple days
The checkpoint with unfrozen Roberta achieved 77.6% accuracy! Here's a link to download it. I will probably delete it in a few days, cause it takes a lot of storage in my Dropbox. Download soon if you want it. Also, if someone can host the checkpoint in some permanent storage, please share the link here :) https://www.dropbox.com/s/fkr9n4vgtkwj4j2/epoch%3D11-val_accuracy%3D0.776028.ckpt?dl=0
Can someone train it with unfrozen RoBERTa and upload checkpoint?