<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
XLM_Roberta_Large_Greek_Offensive
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7552
- Macro F1: 0.7352
- Micro F1: 0.7989
- Accuracy: 0.7989
Results on test set: -Accuracy: 0.905440414507772
-F1 score: 0.8394228385651885
-Precision: 0.8115009990009989
-Recall : 0.8800129489279049
-Matthews Correlation Coefficient: 0.6881116572893037
-Precision of each class: [0.96915584 0.65384615]
-Recall of each class: [0.91705069 0.84297521]
-F1 score of each class: [0.94238358 0.73646209]
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Micro F1 | Accuracy |
|---|---|---|---|---|---|---|
| 0.547 | 1.0 | 1967 | 0.6330 | 0.7245 | 0.8057 | 0.8057 |
| 0.5369 | 2.0 | 3934 | 0.5186 | 0.7328 | 0.8057 | 0.8057 |
| 0.5571 | 3.0 | 5901 | 0.6156 | 0.7495 | 0.8149 | 0.8149 |
| 0.5426 | 4.0 | 7868 | 0.6820 | 0.7388 | 0.8126 | 0.8126 |
| 0.4842 | 5.0 | 9835 | 0.7268 | 0.7386 | 0.7897 | 0.7897 |
| 0.5113 | 6.0 | 11802 | 0.7552 | 0.7352 | 0.7989 | 0.7989 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1+cu118
- Datasets 2.9.0
- Tokenizers 0.13.3
