mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
d0ef136d5b
* added curriculum * readapted readme * corrected small errors * Delete eval/eval/r1/algorithmic/word_sorting.json * removed redundant argument * added spell * removed duplicated fit * changed config * added composite changes * added composite changes * updated yaml * added spell backward * updated read me * added qwen2.5 * added * Add files via upload * updated missing trainer func * updated curr * updated spell back * updated correctness score func * updated configs * added local evals * added updates * updated datasets * added fsdp to hf utility * added algorithmic qwen 3b yaml * updated read me * updated configs * added preappend token * updated with thinking token * updated test score board * resolved comments * added evaluation scripts * removed results from pr * added config * added partial reward scoring * added evaluation composites * added training configs * added games eval * added rubriks cube * resolved merge cinflicts * added games config * added latest eval configs * updated strucutre * Delete training/evaluations/eval_graphs_composite.yaml --------- Co-authored-by: joesharratt1229 <joesharrat1229@gmail.com>
24 lines
596 B
YAML
24 lines
596 B
YAML
# Model configuration
|
|
model_path: ../utils/qwen3b_games
|
|
max_tokens: 1024
|
|
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 configuration
|
|
output_dir: results
|
|
save_metadata: true
|
|
save_full_results: true
|
|
eval_repeats: 3
|
|
|
|
# Categories and datasets to evaluate
|
|
categories:
|
|
- category: reasoning
|
|
datasets:
|
|
- dataset: mahjong_puzzle
|
|
size: 100
|
|
seed: 42
|
|
params:
|
|
min_num_rounds: 10
|
|
max_num_rounds: 50
|