# XNLI Base Model

This model was trained on the XNLI dataset using random data selection.

## Training Parameters

- **Dataset**: XNLI
- **Mode**: Base
- **Selection Method**: Random
- **Train Size**: 2400 examples
- **Epochs**: 8
- **Batch Size**: 16
- **Effective Batch Size**: 64 (batch_size * gradient_accumulation_steps)
- **Learning Rate**: 1e-05
- **Patience**: 6
- **Max Length**: 256
- **Gradient Accumulation Steps**: 4
- **Warmup Ratio**: 0.1
- **Weight Decay**: 0.01
- **Optimizer**: AdamW
- **Scheduler**: cosine_with_warmup
- **Random Seed**: 42

## Performance

- **Overall Accuracy**: 65.47%
- **Overall Loss**: 0.0141

### Language-Specific Performance
- **English (EN)**: 72.22%
- **German (DE)**: 67.60%
- **Arabic (AR)**: 63.21%
- **Spanish (ES)**: 68.72%
- **Hindi (HI)**: 62.04%
- **Swahili (SW)**: 59.00%

## Model Information

- **Base Model**: bert-base-multilingual-cased
- **Task**: Natural Language Inference
- **Languages**: 6 languages (EN, DE, AR, ES, HI, SW)