xlm-roberta-base-finetuned-language-detection
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5624
- Accuracy: 0.8195
- F1: 0.8195
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5881 | 1.0 | 941 | 0.5179 | 0.7917 | 0.7915 |
| 0.4524 | 2.0 | 1882 | 0.5121 | 0.8097 | 0.8103 |
| 0.3749 | 3.0 | 2823 | 0.5268 | 0.8142 | 0.8142 |
| 0.3159 | 4.0 | 3764 | 0.5388 | 0.8176 | 0.8176 |
| 0.2721 | 5.0 | 4705 | 0.5624 | 0.8195 | 0.8195 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 27
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.