hcd-causal arm β€” Hierarchical Concept-Diffusion synth run

  • arm: hcd-causal
  • params: 45,144,966
  • steps: 12000
  • seq_len: 256, batch: 32
  • final val LM loss: 4.4077
  • data: PleIAs/SYNTH (en subset: query+reasoning+answer, streaming, gpt2 tokenizer)
  • optimizer: AdamW lr 0.0001, wd 0.1, cosine, warmup 200
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support