open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Added games training and evaluation configuration (#426)

Browse source 
* 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
This commit is contained in:
joesharratt1229 2025-04-26 19:45:32 +01:00 • committed by GitHub
parent 10863ea12b
commit 73e3cb33a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 10 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

28
training/evaluations/eval_algorithmic_composite.yaml
View file

@ -1,28 +0,0 @@
# Model configuration
model_path: ../utils/qwen3b_algorithmic_500
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: number_sorting
size: 100
seed: 42
params:
min_numbers: 3
max_numbers: 10
min_decimals: 0
max_decimals: 2
min_value: -100.0
max_value: 100.0