<!-- 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-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: 1.5363
- Precision: 0.8271
- Recall: 0.4694
- F1 Weighted: 0.5676
- F1 Macro: 0.4308
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 |
|---|---|---|---|---|---|---|---|
| 1.1067 | 0.16 | 25 | 1.0890 | 0.4082 | 0.4409 | 0.4087 | 0.2919 |
| 0.8313 | 0.31 | 50 | 1.0063 | 0.8055 | 0.4536 | 0.5326 | 0.4108 |
| 0.5543 | 0.47 | 75 | 1.2653 | 0.7821 | 0.5130 | 0.5959 | 0.4533 |
| 0.561 | 0.62 | 100 | 1.2028 | 0.8212 | 0.6001 | 0.6753 | 0.5171 |
| 0.5141 | 0.78 | 125 | 1.3416 | 0.8536 | 0.4896 | 0.5820 | 0.4459 |
| 0.4595 | 0.94 | 150 | 1.2413 | 0.8543 | 0.6349 | 0.7147 | 0.5427 |
| 0.4647 | 1.09 | 175 | 1.4473 | 0.8470 | 0.5894 | 0.6803 | 0.5160 |
| 0.4351 | 1.25 | 200 | 1.2805 | 0.8418 | 0.6267 | 0.7058 | 0.5377 |
| 0.4012 | 1.41 | 225 | 1.6780 | 0.8222 | 0.4176 | 0.5164 | 0.3948 |
| 0.3711 | 1.56 | 250 | 1.5256 | 0.8483 | 0.5186 | 0.6145 | 0.4644 |
| 0.4064 | 1.72 | 275 | 1.6555 | 0.8420 | 0.4593 | 0.5710 | 0.4323 |
| 0.3905 | 1.88 | 300 | 1.5819 | 0.8442 | 0.4024 | 0.4908 | 0.3764 |
| 0.3487 | 2.03 | 325 | 1.5363 | 0.8271 | 0.4694 | 0.5676 | 0.4308 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
