Dannyang/EvoNB_1
Full fine-tune vs facebook/esm2_t33_650M_UR50D. Fine-tune: 100% of the weights changed, across 33 of 33 layers.
Tensors changed: other 132/134, Embeddings 1/35, Norms 134/134, Attention 264/264, lm_head 5/5
Full fine-tune vs facebook/esm2_t33_650M_UR50D. Fine-tune: 100% of the weights changed, across 33 of 33 layers.
Tensors changed: other 132/134, Embeddings 1/35, Norms 134/134, Attention 264/264, lm_head 5/5