viewsuite / post_reasoning_training

Commit History

  1. upload iter_000 traj_to_sft/sft_data

    Verified signature
    ecb33ad
  2. upload rollout_data score>1 summary (iter_001)

    Verified signature
    ecd2f51
  3. upload rollout_data filtered to score>1 (iter_001)

    Verified signature
    309b7f0

  1. Delete post_reasoning_training/iter_001

    Verified signature
    1665a87
  2. upload post_reasoning_training/iter_000/sft/sft_model

    Verified signature
    32c6bae

  1. upload post_reasoning_training/iter_000/rl/rollout_data

    Verified signature
    bfaf1ed
  2. upload post_reasoning_training/iter_001/sft/sft_model

    Verified signature
    9be478f
  3. upload post_reasoning_training/iter_001/rl/rl_model

    Verified signature
    2cca735
  4. upload post_reasoning_training/iter_000/sft/sft_model

    Verified signature
    49fc4c4
  5. upload post_reasoning_training/iter_001/sft/sft_model

    Verified signature
    39db689
  6. upload post_reasoning_training/iter_001/rl/rl_model

    Verified signature
    2132e55
  7. upload post_reasoning_training/iter_000/rl/rollout_data

    Verified signature
    44c54fc
  8. upload post_reasoning_training/iter_000/sft/sft_model

    Verified signature
    6a39d7b
  9. upload post_reasoning_training/iter_000/rl/rl_model

    Verified signature
    13183a3