PEFT
Safetensors
lora
qwen3
math
gsm8k
supervised-fine-tuning

added sampler checkpoints from attention_only + main lora runs (3 seeds each)

#1
Commit history is no longer available for this pull request.
No description provided.
sumitdotml changed pull request title from add sampler checkpoint: main-001 attention_only seed-0 step-3169 to added sampler checkpoints from attention_only + main lora runs (3 seeds each)
sumitdotml changed pull request status to merged

Sign up or log in to comment