xnli_m_bert_only_es
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: 1.1865
- Accuracy: 0.7795
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 |
---|---|---|---|---|
0.6124 | 1.0 | 3068 | 0.6275 | 0.7333 |
0.5209 | 2.0 | 6136 | 0.5399 | 0.7759 |
0.4244 | 3.0 | 9204 | 0.6163 | 0.7671 |
0.3365 | 4.0 | 12272 | 0.6123 | 0.7667 |
0.2594 | 5.0 | 15340 | 0.6834 | 0.7739 |
0.1901 | 6.0 | 18408 | 0.8212 | 0.7639 |
0.1419 | 7.0 | 21476 | 0.8601 | 0.7719 |
0.1023 | 8.0 | 24544 | 1.0357 | 0.7635 |
0.0751 | 9.0 | 27612 | 1.0908 | 0.7727 |
0.0541 | 10.0 | 30680 | 1.1865 | 0.7795 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 7
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.