worstchan/EAT-large_epoch20_finetune_AS2M
Full fine-tune vs worstchan/EAT-large_epoch20_pretrain. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 96/96, MLP 96/96, Norms 98/98, other 4/4
Full fine-tune vs worstchan/EAT-large_epoch20_pretrain. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 96/96, MLP 96/96, Norms 98/98, other 4/4