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
575 B
YAML
24 lines
575 B
YAML
model_path: ../utils/games
|
|
max_tokens: 2048
|
|
temperature: 0.6 # Lower temperature for more focused responses
|
|
top_p: 0.9 # From rollout top_p
|
|
developer_prompt: DeepSeekZero
|
|
developer_role: system # Standard role for system prompts
|
|
|
|
output_dir: results
|
|
save_metadata: true
|
|
save_full_results: true
|
|
eval_repeats: 3
|
|
|
|
# Categories and datasets to evaluate
|
|
categories:
|
|
- category: reasoning
|
|
datasets:
|
|
- dataset: tower_of_hanoi
|
|
size: 100
|
|
seed: 42
|
|
params:
|
|
min_disks: 3
|
|
max_disks: 4
|
|
min_pegs: 3
|
|
max_pegs: 4
|