xnli_m_bert_only_el
This model is a fine-tuned version of bert-base-multilingual-cased on the xnli dataset. It achieves the following results on the evaluation set:
- Loss: 1.2248
- Accuracy: 0.7434
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: 128
- eval_batch_size: 128
- seed: 42
- 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 | Accuracy |
|---|---|---|---|---|
| 0.6802 | 1.0 | 3068 | 0.7046 | 0.6968 |
| 0.6029 | 2.0 | 6136 | 0.6539 | 0.7317 |
| 0.5235 | 3.0 | 9204 | 0.6539 | 0.7281 |
| 0.4465 | 4.0 | 12272 | 0.6684 | 0.7353 |
| 0.3713 | 5.0 | 15340 | 0.7089 | 0.7470 |
| 0.2982 | 6.0 | 18408 | 0.8163 | 0.7406 |
| 0.2334 | 7.0 | 21476 | 0.8506 | 0.7478 |
| 0.1798 | 8.0 | 24544 | 0.9669 | 0.7434 |
| 0.1377 | 9.0 | 27612 | 1.1195 | 0.7446 |
| 0.1053 | 10.0 | 30680 | 1.2248 | 0.7434 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.