fpadovani/eng-latn-100mb-after-ppt-Dp-100mb-packed-ckpt500_seed455_seed455
Full fine-tune vs fpadovani/eng-latn-100mb-ppt-Dp-100mb-packed_seed455. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Attention 48/48, Norms 25/50, MLP 48/48, Embeddings 2/2