router-expert-medicine
LoRA expert for the medicine target of the route-then-admit pool, trained on meirdick/router-experts-data data/experts/medicine.jsonl.
- base:
Qwen/Qwen3-4B-Instruct-2507 - rank 16, alpha 32, dropout 0.05, modules q_proj, k_proj, v_proj, o_proj
- 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
| field | value |
|---|---|
| target | medicine |
| items | 1500 |
| recipes | direct,cot_short |
| kinds | {'mc': 1500} |
| mc_padded | 575 |
| examples | 3000 |
| encoded | 3000 |
| dropped_too_long | 0 |
| train_rows | 2850 |
| val_rows | 150 |
| train_batches | 61 |
| train_tokens | 479293 |
| supervised_tokens | 75034 |
| steps | 122 |
| train_loss | 0.9848943461404472 |
| val_loss_before | 3.85815666309016 |
| val_loss | 0.8913045382001195 |
| seconds | 221.88 |
| trainable_params | 11796480 |
- Downloads last month
- 14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for meirdick/router-expert-medicine
Base model
Qwen/Qwen3-4B-Instruct-2507