Hugging Face's logo

SaylorTwift
/
lfm-opencode-lora-rl-code

Model card Files
xet
 Community
lfm-opencode-lora-rl-code / eval_adapter.py

Commit History

12 days ago

  1. Eval cells now record turns/tool_calls/completion+prompt tokens; summary gets efficiency-vs-base ratios

    SaylorTwift HF Staff
    Verified signature
    371ff91

13 days ago

  1. Eval robustness: fresh HarborEnv client per rollout (openenv reconnect bug); failed checkpoint evals retried next poll

    SaylorTwift HF Staff
    Verified signature
    75a9ca0

  2. Add per-checkpoint eval worker (eval_watch.py + run_eval_watch.sh); ONLY_MODEL mode in eval_adapter.py

    SaylorTwift HF Staff
    Verified signature
    0298809

17 days ago

  1. eval: pass purpose=eval (server requires it with eval_sampling)

    SaylorTwift HF Staff
    Verified signature
    e7a4c0e

  2. Add held-out eval (base vs adapter) + standalone eval job + final eval stage in training job

    SaylorTwift HF Staff
    Verified signature
    c511323