---
base_model: Qwen/Qwen3-1.7B
license: mit
library_name: peft
pipeline_tag: text-generation
---

# AtomicVision Hard Recall Micro Boost LoRA

This adapter materializes the promoted `checkpoint-1` checkpoint from the
targeted hard recall micro-repair continuation.

## Parent
- Base adapter: [prodigyhuh/atomicvision-medium-fidelity-boost-lora](https://huggingface.co/prodigyhuh/atomicvision-medium-fidelity-boost-lora)
- Source HF job: [69ed269fd70108f37acdef6d](https://huggingface.co/jobs/prodigyhuh/69ed269fd70108f37acdef6d)
- Source commit: `3838f9048bce4c6bc81e57f5c0dab00980c7fa08`

## Held-out strict eval (`seed_start=10000`, `episodes=32`)

| Difficulty | Reward | F1 | MAE | Strict | Normalized | Done | Submit |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| medium | 4.5065 | 0.7891 | 0.02712 | 1.00 | 1.00 | 1.00 | 1.00 |
| hard | 4.7148 | 0.8207 | 0.02552 | 1.00 | 1.00 | 1.00 | 1.00 |

This run preserves perfect strict execution and slightly improves the hard slice
over the previous best published adapter without regressing medium.