acb94e3e20
syy's es runs: humaneval x3, gpqa x2, aime25/26 x12 (already aligned), mmlu_pro/longbench_v2 x1 (temp=0 deterministic -- repeats are noise, and 3x 12k samples is pure cost). temp=1 benches get 3. Co-Authored-By: Claude <noreply@anthropic.com>
61 lines
931 B
YAML
61 lines
931 B
YAML
default:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
stream: true
|
|
max_tokens: 32768
|
|
aime24:
|
|
temperature: 1.0
|
|
repeats: 12
|
|
max_tokens: 8192
|
|
aime25:
|
|
temperature: 1.0
|
|
repeats: 12
|
|
max_tokens: 8192
|
|
aime26:
|
|
temperature: 1.0
|
|
repeats: 12
|
|
max_tokens: 8192
|
|
hmmt26:
|
|
temperature: 1.0
|
|
repeats: 12
|
|
max_tokens: 8192
|
|
imo_answerbench:
|
|
temperature: 1.0
|
|
gpqa_diamond:
|
|
temperature: 1.0
|
|
repeats: 3
|
|
max_tokens: 8192
|
|
mmlu:
|
|
max_tokens: 8192
|
|
mmlu_pro:
|
|
max_tokens: 8192
|
|
cmmlu:
|
|
max_tokens: 8192
|
|
arc:
|
|
max_tokens: 8192
|
|
hellaswag:
|
|
max_tokens: 8192
|
|
winogrande:
|
|
max_tokens: 8192
|
|
simple_qa:
|
|
max_tokens: 8192
|
|
trivia_qa:
|
|
max_tokens: 8192
|
|
humaneval:
|
|
temperature: 1.0
|
|
repeats: 3
|
|
live_code_bench:
|
|
temperature: 1.0
|
|
longbench_v2:
|
|
max_tokens: 8192
|
|
max_input_tokens: 128000
|
|
openai_mrcr:
|
|
max_tokens: 8192
|
|
max_input_tokens: 128000
|
|
bfcl_v3:
|
|
max_tokens: 4096
|
|
general_fc:
|
|
max_tokens: 4096
|
|
tau2_bench:
|
|
max_tokens: 16384
|