bert-small-nli
Fine-tuned prajjwal1/bert-small for natural language
inference (entailment / neutral / contradiction), intended for use as a zero-shot
text classification model via the entailment trick (hypothesis = "This text is
about {label}.").
Trained on Pankaj8922/nli-high-quality-balanced, a
combined and filtered subset of MNLI, SNLI, FEVER-NLI, and ANLI:
annotator-agreement filtered, deduplicated, teacher-confidence filtered,
hypothesis-only artifact filtered, and class-balanced.
Results
| Split | Accuracy | F1 (macro) | Precision (macro) | Recall (macro) |
|---|---|---|---|---|
| Validation | 0.8048 | 0.8047 | 0.8047 | 0.8048 |
| Test | 0.8045 | 0.8044 | 0.8045 | 0.8045 |
Training details
- Base model:
prajjwal1/bert-small - Epochs: 3
- Batch size: 64 (train), 128 (eval)
- Learning rate: 5e-05
- Max sequence length: 256
Labels
- 0: entailment
- 1: neutral
- 2: contradiction
Intended use / limitations
This is a small (~29M parameter) model, so its ceiling on zero-shot performance against novel, unseen label sets is lower than larger NLI-tuned checkpoints (e.g. DeBERTa-v3-base or -large variants). Best suited for fast inference or resource-constrained settings rather than maximum accuracy.