mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
73e3cb33a4
* added games * Update eval_games_composite.yaml * Delete training/evaluations/eval_qwen_3b.yaml * Add files via upload * Delete training/evaluations/eval_algebraic_composite.yaml * Delete training/evaluations/eval_algorithmic_composite.yaml * Delete training/evaluations/eval_arithmetic_composite.yaml * Delete training/evaluations/eval_cognition_composite.yaml * Delete training/evaluations/eval_games_composite.yaml
24 lines
531 B
YAML
24 lines
531 B
YAML
# Model configuration
|
|
model_path: ../utils/qwen_3b_arithmetic_100
|
|
max_tokens: 1024
|
|
temperature: 0.6
|
|
top_p: 0.9
|
|
developer_prompt: DeepSeekZero
|
|
developer_role: system # Standard role for system prompts
|
|
|
|
# Output configuration
|
|
output_dir: results
|
|
save_metadata: true
|
|
save_full_results: true
|
|
eval_repeats: 3
|
|
|
|
# Categories and datasets to evaluate
|
|
categories:
|
|
- category: reasoning
|
|
datasets:
|
|
- dataset: prime_factorization
|
|
size: 100
|
|
seed: 42
|
|
params:
|
|
min_value: 2
|
|
max_value: 1000
|