<!-- 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-finetuned-panx-en-custom
This model is a fine-tuned version of maren-hugg/xlm-roberta-base-finetuned-panx-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1045
- F1: 0.8782
- Precision: 0.8496
- Recall: 0.9088
- Accuracy: 0.9754
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: 4.886597454037411e-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 | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.128 | 0.75 | 24 | 0.1087 | 0.8514 | 0.8299 | 0.8740 | 0.9713 |
| 0.074 | 1.5 | 48 | 0.1006 | 0.8637 | 0.8505 | 0.8773 | 0.9750 |
| 0.0506 | 2.25 | 72 | 0.0987 | 0.8728 | 0.8587 | 0.8872 | 0.9749 |
| 0.0393 | 3.0 | 96 | 0.1045 | 0.8782 | 0.8496 | 0.9088 | 0.9754 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
