<!-- 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-base-uncased-PINA
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0862
- Accuracy: 0.7553
- Precision: 0.5016
- Recall: 0.4522
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|
| 2.7204 | 1.0 | 234 | 2.4959 | 0.4220 | 0.0124 | 0.0269 |
| 2.2553 | 2.0 | 468 | 1.9819 | 0.5 | 0.0498 | 0.0802 |
| 1.9593 | 3.0 | 702 | 1.7527 | 0.5513 | 0.1222 | 0.1377 |
| 1.6947 | 4.0 | 936 | 1.5375 | 0.6325 | 0.2466 | 0.2480 |
| 1.4593 | 5.0 | 1170 | 1.3773 | 0.6848 | 0.4074 | 0.3414 |
| 1.2381 | 6.0 | 1404 | 1.2560 | 0.7094 | 0.4273 | 0.3638 |
| 1.0986 | 7.0 | 1638 | 1.1813 | 0.7286 | 0.4396 | 0.4033 |
| 0.9817 | 8.0 | 1872 | 1.1668 | 0.7361 | 0.4824 | 0.4345 |
| 0.8894 | 9.0 | 2106 | 1.1054 | 0.7521 | 0.5155 | 0.4461 |
| 0.8518 | 10.0 | 2340 | 1.0862 | 0.7553 | 0.5016 | 0.4522 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
