Qwen 2.5 Math 14B Iter 1
Collection
Qwen 2.5 is missing it's 14B and 32B math variants!! I have taken it upon myself to create them :)
•
4 items
•
Updated
•
1
This Qwen 2.5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
I fine-tuned it for 400 steps on garage-bAInd/Open-Platypus with a batch size of 3.
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 36.71 |
IFEval (0-Shot) | 60.66 |
BBH (3-Shot) | 47.02 |
MATH Lvl 5 (4-Shot) | 28.47 |
GPQA (0-shot) | 16.33 |
MuSR (0-shot) | 19.63 |
MMLU-PRO (5-shot) | 48.12 |