<!-- 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. -->
xnli_xlm_r_only_ar
This model is a fine-tuned version of xlm-roberta-base on the xnli dataset. It achieves the following results on the evaluation set:
- Loss: 0.8547
- Accuracy: 0.7450
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7468 | 1.0 | 3068 | 0.6949 | 0.7129 |
| 0.6117 | 2.0 | 6136 | 0.6233 | 0.7474 |
| 0.5475 | 3.0 | 9204 | 0.6406 | 0.7538 |
| 0.4947 | 4.0 | 12272 | 0.6487 | 0.7486 |
| 0.4484 | 5.0 | 15340 | 0.6633 | 0.7598 |
| 0.4054 | 6.0 | 18408 | 0.7546 | 0.7337 |
| 0.3683 | 7.0 | 21476 | 0.7406 | 0.7418 |
| 0.3366 | 8.0 | 24544 | 0.7835 | 0.7454 |
| 0.3105 | 9.0 | 27612 | 0.8255 | 0.7454 |
| 0.2923 | 10.0 | 30680 | 0.8547 | 0.7450 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
