17 lines
590 B
Markdown
17 lines
590 B
Markdown
---
|
|
base_model: Qwen/Qwen2.5-7B
|
|
tags:
|
|
- grpo
|
|
- cross-lingual
|
|
- ablation
|
|
---
|
|
|
|
# Qwen-2.5-7B-grpo-bonus5-ablation
|
|
|
|
GRPO all_correct_bonus ablation on Qwen2.5-7B, trained on the WIKI-FACT /
|
|
PolyFact cross-lingual factual-recall task (see
|
|
[jvonrad/Lost-in-Mistranslation](https://github.com/jvonrad/Lost-in-Mistranslation)).
|
|
`--all_correct_bonus 5.0` (all other hyperparameters match the paper's main
|
|
GRPO run). Evaluated in `results/qwen-2.5-7b-grpo-bonus5-ablation_polyfact_consistency.json` and
|
|
`results/qwen-2.5-7b-grpo-bonus5-ablation_gmmlu_lite_consistency.json` in the repo above.
|