qing-yao/ppt-pythia-160m-uniform250-uniform-seed208-stage1
Full fine-tune vs EleutherAI/pythia-160m. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 50/50, Attention 48/48, MLP 48/48
Full fine-tune vs EleutherAI/pythia-160m. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 50/50, Attention 48/48, MLP 48/48