Siddhartha Shrestha

icon indicating a website link https://www.linkedin.com/in/siddharthashrestha

icon location Kathmandu,Nepal icon location I am hard working AI enthusiast

Results 2 comments of Siddhartha Shrestha

Performance degrades when loading/training with large labeled training file to prepare_train()

> of predicates, then you could meet the recursion limit or max_calls limit before finding a solution that covered all the dupe pairs hi @cbhower did you get why it...

Training on LORA using multi-gpu is giving constant loss

@DRXD1000 I am using sft trainer script from this repo: https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_sft.py Regarding GPU i am using 4*A100 (80GB) GPU from runpods.