<!-- 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-20-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: 1.9792
- Precision: 0.8762
- Recall: 0.4403
- F1 Weighted: 0.5325
- F1 Macro: 0.4085
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 |
|---|---|---|---|---|---|---|---|
| 1.1229 | 0.78 | 25 | 1.1125 | 0.2741 | 0.5085 | 0.3441 | 0.2335 |
| 0.8029 | 1.56 | 50 | 0.7848 | 0.8064 | 0.7334 | 0.7660 | 0.5695 |
| 0.5565 | 2.34 | 75 | 0.9492 | 0.8333 | 0.5546 | 0.6380 | 0.4791 |
| 0.3928 | 3.12 | 100 | 1.4848 | 0.8262 | 0.5212 | 0.6141 | 0.4681 |
| 0.3988 | 3.91 | 125 | 1.6936 | 0.8733 | 0.4226 | 0.4931 | 0.3806 |
| 0.3452 | 4.69 | 150 | 1.9792 | 0.8762 | 0.4403 | 0.5325 | 0.4085 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
