Views
No views yet
examples/echo_world_model/train_echo.py to
predict OpenEnv terminal environment outputs from verifier-free ECHO loss.| metric | value |
|---|---|
best_step | 35 |
heldout_ce_after | 0.26466473937034607 |
heldout_ce_before | 6.246147632598877 |
heldout_ce_delta | -5.981482893228531 |
heldout_ce_improvement_pct | 95.76275242056317 |
heldout_token_acc_after | 0.8421052631578947 |
heldout_token_acc_before | 0.10526315789473684 |
lr | 5e-05 |
model | distilgpt2 |
seed | 2 |
steps | 60 |