Files
qwen3-4b-gsm8k/.eval_results/gsm8k.yaml

9 lines
163 B
YAML
Raw Normal View History

- dataset:
id: openai/gsm8k
task_id: gsm8k
config: main
split: test
value: 0.095527
date: "2026-05-09"
notes: "greedy, no-tools, local eval"