mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
850c1cf6f4
The script now supports: - YAML and JSON configurations - Dataset-specific parameters - Overriding configuration via command line - Detailed logging and error handling
33 lines
766 B
YAML
33 lines
766 B
YAML
# Example configuration for the evaluation script
|
|
model: "meta-llama/llama-3.3-70b-instruct"
|
|
provider: "Hyperbolic"
|
|
output_dir: "results"
|
|
max_concurrent: 10
|
|
default_size: 20 # Default size for all datasets
|
|
default_seed: 42 # Default seed for all datasets
|
|
|
|
categories:
|
|
- category: "algebra"
|
|
datasets:
|
|
- dataset: "complex_arithmetic"
|
|
params:
|
|
min_real: -10
|
|
max_real: 10
|
|
min_imag: -10
|
|
max_imag: 10
|
|
|
|
- category: "arithmetic"
|
|
datasets:
|
|
- dataset: "products"
|
|
size: 10
|
|
seed: 43
|
|
params:
|
|
min_digits: 2
|
|
allow_negation: true
|
|
|
|
- dataset: "chain_sum"
|
|
size: 12
|
|
seed: 43
|
|
params:
|
|
min_digits: 2
|
|
allow_negation: true
|