reasoning-gym/eval/yaml/deepseek-r1.yaml
Andreas Köpf 850c1cf6f4
Eval script consolidation (#238)
The script now supports:
   - YAML and JSON configurations
   - Dataset-specific parameters
   - Overriding configuration via command line
   - Detailed logging and error handling
2025-02-27 17:39:14 +01:00

61 lines
1.7 KiB
YAML

# Combined configuration for deepseek-r1
model: "deepseek/deepseek-r1"
provider: "Nebius"
output_dir: "results"
max_concurrent: 10
default_size: 50
default_seed: 45
categories:
- category: "algebra"
datasets:
- dataset: "intermediate_integration"
- dataset: "polynomial_equations"
- dataset: "polynomial_multiplication"
- dataset: "simple_equations"
- dataset: "simple_integration"
- dataset: "complex_arithmetic"
- category: "algorithmic"
datasets:
- dataset: "ab"
- dataset: "base_conversion"
- dataset: "binary_matrix"
- dataset: "caesar_cipher"
- dataset: "count_primes"
- dataset: "game_of_life"
- dataset: "graph_color"
- dataset: "group_anagrams"
- dataset: "isomorphic_strings"
- dataset: "letter_counting"
- dataset: "letter_jumble"
- dataset: "manipulate_matrix"
- dataset: "number_filtering"
- dataset: "number_sorting"
- dataset: "palindrome"
- dataset: "pool_matrix"
- dataset: "ransom_note"
- dataset: "rotate_matrix"
- dataset: "sentence_reordering"
- dataset: "spell_backward"
- dataset: "spiral_matrix"
- dataset: "string_insertion"
- dataset: "string_manipulation"
- dataset: "string_synthesis"
- dataset: "word_ladder"
- dataset: "word_sequence_reversal"
- dataset: "word_sorting"
- category: "cognition"
datasets:
- dataset: "color_cube_rotation"
- dataset: "figlet_font"
- dataset: "number_sequence"
- dataset: "rubiks_cube"
- category: "logic"
datasets:
- dataset: "propositional_logic"
- dataset: "self_reference"
- dataset: "syllogism"
- dataset: "zebra_puzzles"