Commit History

  1. meta_001950.json: add user_config so chat_sft inherits the run's LRs

    Verified signature
    1bfa5e5
  2. Add nanochat-format d24 checkpoint (step 5568) + world_size=8 optimizer shards

    Verified signature
    7b1ab30
  3. Flag that val bpb is not comparable across the batched/varlen pipelines

    Verified signature
    4c66da7
  4. Converter now emits nanochat optimizer shards for an SFT warm-start

    Verified signature
    412ea12
  5. Correct optimizer-state notes: SFT needs only the weights; W_O axis is a no-op at d24

    Verified signature
    162df34
  6. Add model card, meta.json, logs, tokenizer, training source, and nanochat converter

    Verified signature
    11f07f9
  7. Upload folder using huggingface_hub

    Verified signature
    a669958
  8. initial commit

    Verified signature
    f911c2f