french-xml-model-a
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2174
- Precision: 0.8228
- Recall: 0.9253
- F1: 0.8711
- Accuracy: 0.9322
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4036 | 1.0 | 976 | 0.2509 | 0.7877 | 0.9197 | 0.8486 | 0.9227 |
| 0.2033 | 2.0 | 1952 | 0.2110 | 0.8204 | 0.9199 | 0.8673 | 0.9312 |
| 0.1734 | 3.0 | 2928 | 0.2174 | 0.8228 | 0.9253 | 0.8711 | 0.9322 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2