<!-- 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. -->
synthetic-60-vsfc-xlm-r
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: 1.9000
- Precision: 0.8724
- Recall: 0.4738
- F1 Weighted: 0.5881
- F1 Macro: 0.4471
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: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Weighted | F1 Macro |
|---|---|---|---|---|---|---|---|
| 1.1177 | 0.26 | 25 | 1.0206 | 0.6156 | 0.6273 | 0.5871 | 0.4051 |
| 0.775 | 0.52 | 50 | 1.0222 | 0.8723 | 0.4611 | 0.5609 | 0.4297 |
| 0.603 | 0.78 | 75 | 0.9684 | 0.8147 | 0.7037 | 0.7494 | 0.5713 |
| 0.5153 | 1.04 | 100 | 1.1462 | 0.8824 | 0.5313 | 0.6387 | 0.4904 |
| 0.4893 | 1.3 | 125 | 1.6944 | 0.8437 | 0.4163 | 0.5168 | 0.3994 |
| 0.4323 | 1.56 | 150 | 1.6921 | 0.8648 | 0.4460 | 0.5312 | 0.4104 |
| 0.4281 | 1.82 | 175 | 1.3086 | 0.8351 | 0.5161 | 0.6038 | 0.4573 |
| 0.4343 | 2.08 | 200 | 1.4962 | 0.8800 | 0.4870 | 0.5859 | 0.4480 |
| 0.338 | 2.34 | 225 | 1.9000 | 0.8724 | 0.4738 | 0.5881 | 0.4471 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
