<!-- 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. -->
train
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1100
- F1: 0.6074
- Roc Auc: 0.7538
- Accuracy: 0.8966
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2023 | 1.0 | 5261 | 0.1159 | 0.5889 | 0.7525 | 0.8851 |
| 0.1663 | 2.0 | 10522 | 0.1100 | 0.6074 | 0.7538 | 0.8966 |
| 0.1472 | 3.0 | 15783 | 0.1132 | 0.5736 | 0.7679 | 0.8634 |
| 0.1312 | 4.0 | 21044 | 0.1159 | 0.5975 | 0.7462 | 0.8911 |
| 0.1175 | 5.0 | 26305 | 0.1289 | 0.5922 | 0.7390 | 0.8936 |
| 0.1036 | 6.0 | 31566 | 0.1380 | 0.6062 | 0.7463 | 0.897 |
| 0.089 | 7.0 | 36827 | 0.1440 | 0.5927 | 0.7395 | 0.894 |
| 0.077 | 8.0 | 42088 | 0.1579 | 0.5998 | 0.7463 | 0.8944 |
| 0.0661 | 9.0 | 47349 | 0.1662 | 0.5933 | 0.7382 | 0.8956 |
| 0.0584 | 10.0 | 52610 | 0.1665 | 0.5940 | 0.7424 | 0.8922 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Tokenizers 0.13.2
