{"data":{"kind":"file","path":"README.md","version_id":"klgvbssnszkubjmj1nmdpfr7","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1424,"modified_at":"2025-09-08T17:15:27.397000","content_hash":"88c9ecf073102dc6a0f694f7523bbcd02ce727275a25885ada2e57a7878929f7"},"entries":[],"content":"# fingpt-sentiment\n\n### Overview\n- **Environment ID**: `fingpt-sentiment`\n- **Short description**: Financial sentiment classification environment using fingpt-sentiment dataset.\n- **Tags**: financial-sentiment, single-turn, classification, fingpt\n\n### Datasets\n- **Primary dataset(s)**: fingpt-sentiment\n- **Source links**: FinGPT/fingpt-sentiment-train\n\n### Task\n- **Type**: Single-turn\n- **Parser**: Custom parser to extract sentiment labels\n- **Rubric overview**: Exact sentiment match, partial credit for valid sentiment label\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval fingpt-sentiment\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval fingpt-sentiment   -m gpt-4.1-mini   -n 20 -r 3 -t 1024 -T 0.7   -a '{\"max_examples\": 1000}'\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.\n\n### Environment Arguments\nDocument any supported environment arguments and their meaning. Example:\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `max_examples` | int | `-1` | Limit on dataset size (use -1 for all) |\n\n### Metrics\nSummarize key metrics your rubric emits and how they’re interpreted.\n\n| Metric | Meaning |\n| ------ | ------- |\n| `correct_sentiment_reward_func` | 1.0 if predicted sentiment matches ground truth, else 0.0 |\n| `format_reward_func` | Partial credit for valid sentiment label |\n\n","encoding":"utf-8","truncated":false,"total_bytes":1424},"status":null}