DGurgurov/xlm-r_bulgarian_sentiment

Fine-tuned XLM-R Model for bulgarian Sentiment Analysis

This is a fine-tuned XLM-R model for sentiment analysis in bulgarian.

Model Details

• Model Name: XLM-R Sentiment Analysis
• Language: bulgarian
• Fine-tuning Dataset: DGurgurov/bulgarian_sa

Training Details

• Epochs: 20
• Batch Size: 32 (train), 64 (eval)
• Optimizer: AdamW
• Learning Rate: 5e-5

Performance Metrics

• Accuracy: 0.94381
• Macro F1: 0.90809
• Micro F1: 0.94381

Usage

To use this model, you can load it with the Hugging Face Transformers library:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("DGurgurov/xlm-r_bulgarian_sentiment")
model = AutoModelForSequenceClassification.from_pretrained("DGurgurov/xlm-r_bulgarian_sentiment")

License

[MIT]