<!-- 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-large-finetuned-sinquad-v2
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7850
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5061 | 0.99 | 23 | 1.3749 |
| 0.8976 | 1.98 | 46 | 0.8803 |
| 0.7572 | 2.97 | 69 | 0.7758 |
| 0.6854 | 4.0 | 93 | 0.7380 |
| 0.5903 | 4.99 | 116 | 0.7158 |
| 0.5114 | 5.98 | 139 | 0.7311 |
| 0.4291 | 6.97 | 162 | 0.7533 |
| 0.4113 | 8.0 | 186 | 0.7650 |
| 0.3564 | 8.99 | 209 | 0.7734 |
| 0.3516 | 9.89 | 230 | 0.7850 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.6.1
- Tokenizers 0.12.1
{'exact_match': 67.75914634146342, 'f1': 86.42992384115712}
