NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-28 17:29:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

tokenizer bug

Browse source
This commit is contained in:
Jai Suphavadeeprasit 2026-03-11 11:05:44 -04:00
parent 78c0a6d082
commit f1cfc137ec
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
example_trainer/run_gsm8k_teacher_distill_single_terminal.sh
View file

@ -56,7 +56,7 @@ LR="${LR:-1e-5}"
WARMUP_STEPS="${WARMUP_STEPS:-0}"
CLIP_EPS="${CLIP_EPS:-0.2}"
MAX_MODEL_LEN="${MAX_MODEL_LEN:-16384}"
ENV_MAX_TOKEN_LENGTH="${ENV_MAX_TOKEN_LENGTH:-4096}"
ENV_MAX_TOKEN_LENGTH="${ENV_MAX_TOKEN_LENGTH:-4608}"
DISTILL_COEF="${DISTILL_COEF:-0.2}"
DISTILL_TEMPERATURE="${DISTILL_TEMPERATURE:-1.0}"
TEACHER_TOP_K="${TEACHER_TOP_K:-8}"