---
language: 
- sl

license: cc-by-sa-4.0
---

# sloberta-si-nli

SloBERTa model finetuned on the SI-NLI dataset for Slovene natural language inference.  
Fine-tuned in a classic sequence pair classification setting on the official training/validation/test split for 10 epochs, using validation set accuracy for model selection.
Optimized using the AdamW optimizer (learning rate 2e-5) and cross-entropy loss.  
Using batch size `82` (selected based on the available GPU memory) and maximum sequence length `102` (99th percentile of the lengths in the training set).

Achieves the following metrics:  
- best validation accuracy: `0.720`
- test accuracy = `0.735`