<!-- 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-v4
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: 0.7988
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: 8e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|
| 1.3065 | 1.0 | 93 | 1.0228 |
| 0.7956 | 2.0 | 186 | 0.7859 |
| 0.6896 | 3.0 | 279 | 0.7428 |
| 0.5774 | 4.0 | 372 | 0.7281 |
| 0.4874 | 5.0 | 465 | 0.7300 |
| 0.3809 | 6.0 | 558 | 0.7324 |
| 0.3538 | 7.0 | 651 | 0.7640 |
| 0.3919 | 8.0 | 744 | 0.7800 |
| 0.5298 | 9.0 | 837 | 0.7840 |
| 0.3136 | 10.0 | 930 | 0.7988 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.6.1
- Tokenizers 0.12.1
