Devansh Choubey
Devansh Choubey
Hi @berlino, can you please tell me when can we expect those reparsed trees that are corrupt and is that the reason also for lower accuracy.
Hi @karthikj11 is there a possibility that you can share your trained model?? with me???
thanks @berlino kudos to you and @alexpolozov just one more question you guys trained on a v100 with 16gb mem with the same default code with bs=6 and num_batch_accumulated=4 without...
@berlino @alexpolozov Hi, i was able to reparse all the AST from @rshin generate.sh it did improve something but not much still there is a lot of difference in loss...
@senthurRam33, yeah got that after training for 6000 steps... anyway how much accuracy did you get???on EVAL??
@berlino @alexpolozov Finally after changing the loss to label_smooth, I got 65 percent accuracy at around 22000 steps, gonna keep training, let's see how much it can improve.... anyway ,...
Hi @Sea-Snell, yeah, exactly even I am at 67% at 26000 steps, still training going on...but will same LR 3e-6 latest update got 69.2 accuracy at 41800 seems label_smooth was...
Hi @kartts, this happens most probably because of memory overflow, please check....
I have tried tonnes of ways to do that, but as far as I know, it's not possible technically to run docker on colab or kaggle, don't remember the exact...