metinovadilet/kyrgyz-stsb-mbert

Kyrgyz STS-B mBERT

This repository contains a fine-tuned mBERT checkpoint for Kyrgyz semantic textual similarity regression.

Dataset

• Dataset: Kyrgyz STS-B
• Language: Kyrgyz (ky)

Model

• Base model: bert-base-multilingual-cased
• Role: multilingual baseline/reference checkpoint
• Framework: Hugging Face Transformers

Reported Results

Metric	Score
Pearson	0.7029
Spearman	0.7056

Training Summary

Setting	Value
Epochs	3
Batch size	64
Learning rate	2e-5
Training time	15.2 seconds

Notes

This is a multilingual reference checkpoint for the Kyrgyz STS-B task.

Intended Use

This checkpoint is intended for baseline/reference evaluation for Kyrgyz semantic textual similarity. It is intended for research, reproducibility, and educational use by the Kyrgyz NLP community. It should not be used for high-stakes decisions or production deployment without separate validation for the target domain.

License and Usage

License metadata is set to other. The checkpoint is released for research and reproducibility. Downstream datasets and base models may have their own licenses or usage terms; users are responsible for following the corresponding dataset cards and upstream model licenses. The checkpoint is provided without warranty.