rohanjain2312/grpo-reward-hacked-sentiment-qwen05b

AI model by rohanjain2312

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

This is the reward-hacked model. It is published as a negative result, not as a model to use. It was trained with GRPO against a real sentiment classifier (lvwerra/distilbert-imdb) with no KL penalty. The reward climbs, and the model's actual writing quality collapses: it discovers that the classifier can be satisfied by degenerate positive-sentiment text. A three-part demo of reward hacking in GRPO: Full metrics and generated samples for every checkpoint are in logs/metrics.jsonl and logs/samples.jsonl in this repo. Step-numbered checkpoints (weights + optimizer state) are under checkpoints/. Both runs were configured for 100 steps and stopped at step 80, when the Hugging Face Jobs credit balance on the training…

rohanjain2312/grpo-reward-hacked-sentiment-qwen05b on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-21T08:58:40.981Z

Inside the original model card — Document outline
  1. grpo-reward-hacked-sentiment-qwen05b
  2. What this is part of
  3. Setup actually used
  4. Results on the held-out eval prompts
  5. A note on run length
  6. Intended use

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

rohanjain2312/grpo-reward-hacked-sentiment-qwen05b is a task-unspecified model repository published by rohanjain2312 on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-09-21T06:18:26.000Z
Last modified
2026-09-21T06:18:26.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:48.800Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models