e_care_xlm_roberta_base_finetuned
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6184
- F1: 0.7208
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: 1e-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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.6735 | 1.0 | 933 | 0.5926 | 0.6639 |
| 0.6001 | 2.0 | 1866 | 0.5624 | 0.6952 |
| 0.5482 | 3.0 | 2799 | 0.5460 | 0.7025 |
| 0.4975 | 4.0 | 3732 | 0.5534 | 0.7122 |
| 0.4487 | 5.0 | 4665 | 0.5646 | 0.7205 |
| 0.4091 | 6.0 | 5598 | 0.5910 | 0.7185 |
| 0.3674 | 7.0 | 6531 | 0.6184 | 0.7208 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1