<!-- 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-cased-finetuned-on-REDv2_EN
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: 0.3020
- F1: 0.6551
- Roc Auc: 0.7921
- Accuracy: 0.5414
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 255 | 0.3231 | 0.4506 | 0.6522 | 0.3112 |
| 0.3531 | 2.0 | 511 | 0.2683 | 0.6117 | 0.7446 | 0.4899 |
| 0.3531 | 3.0 | 766 | 0.2630 | 0.6603 | 0.7842 | 0.5617 |
| 0.2223 | 4.0 | 1022 | 0.2579 | 0.6567 | 0.7812 | 0.5709 |
| 0.2223 | 5.0 | 1277 | 0.2603 | 0.6707 | 0.7930 | 0.5764 |
| 0.1589 | 6.0 | 1533 | 0.2799 | 0.6475 | 0.7826 | 0.5488 |
| 0.1589 | 7.0 | 1788 | 0.2833 | 0.6538 | 0.7883 | 0.5562 |
| 0.1163 | 8.0 | 2044 | 0.2936 | 0.6655 | 0.7951 | 0.5580 |
| 0.1163 | 9.0 | 2299 | 0.2949 | 0.6678 | 0.7978 | 0.5727 |
| 0.0943 | 9.98 | 2550 | 0.3020 | 0.6551 | 0.7921 | 0.5414 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
