Heavenn
Heavenn
> Thank you so much! I will try it out. @yuzc19 Hi! Thanks for sharing your training logs. But I am wondering what is the difference between baseline_200k and baseline_200_full....
@yuzc19 Thanks for your reply! > For the name without full, I only use 1/4 Pile data (randomly sampled) as I only trained the model for 50k steps rather than...
@yuzc19 Oh, I have just noticed that validation datasets also use domain weights. So models with different training domain weights are also with different validation sets. In my own training...
> Good question, the evidence so far suggests that the tokenizer is the biggest thing that changes results (since it changes the data itself). I expect some degradation if the...
@yiyixuxu @asomoza
> can you run `make style` and `make quality` please. @asomoza Hi! There are my results. Please have a look. thank you `make style` ``` examples/research_projects/geodiff/geodiff_molecule_conformation.ipynb:cell 53:59:7: F821 Undefined name...