28 lines
880 B
Markdown
28 lines
880 B
Markdown
---
|
|
license: apache-2.0
|
|
base_model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
|
|
tags:
|
|
- reinforcement-learning
|
|
- code
|
|
- swesmith
|
|
- rl
|
|
- rloo
|
|
datasets:
|
|
- DCAgent/swesmith-oracle-verified-120s-2500
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
---
|
|
|
|
# SweSmith-8B-SFT-NoRope-step58
|
|
|
|
RL-trained Qwen3-8B on SWEsmith tasks (32k context, no rope scaling, 58 steps). Beats the SFT base model on dev_set_71 (pass@1 0.227 vs 0.213) and SWE-bench 100 (0.220 vs 0.210).
|
|
|
|
## Training Details
|
|
|
|
- **Base model**: [laion/r2egym-nl2bash-stack-bugsseq-fixthink-again](https://huggingface.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink-again) (Qwen3-8B SFT)
|
|
- **Training method**: RLOO-N (Reinforcement Learning with Leave-One-Out baselines)
|
|
- **Training data**: 2,500 SWEsmith tasks (oracle-verified, 120s timeout)
|
|
- **Framework**: BenSkyRL + Harbor
|