Team Ai
Modelpublic

meirdick/router-expert-math_academic.statistics

sourceHugging Faceapache-2.0updated 22d agoView on Hugging Face
0likes27downloads
Model Card

router-expert-math_academic.statistics

LoRA expert for the math_academic.statistics target of the route-then-admit pool, trained on meirdick/router-experts-data data/experts/math_academic.statistics.jsonl.

  • —base: Qwen/Qwen3-4B-Instruct-2507
  • —rank 16, alpha 32, dropout 0.05, modules qproj, kproj, vproj, oproj
  • —lr 0.0002, epochs 2, max_len 1024, token budget 8192 per batch
  • —one example per item per recipe (direct,cot_short), under the serving system prompt; 40% of the mc items re-lettered to 5 to 10 options
  • —loss on the assistant turn only; held-out 5% for the val loss
fieldvalue
targetmath_academic.statistics
items1500
recipesdirect,cot_short
kinds{'numeric': 1500}
mc_padded0
examples3000
encoded3000
droppedtoolong0
train_rows2850
val_rows150
train_batches48
train_tokens372160
supervised_tokens153837
steps96
train_loss0.6567262684305509
vallossbefore2.4851415606840246
val_loss0.41010173350256024
seconds174.03
trainable_params11796480