xnli_m_bert_only_tr
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: 1.3355
- Accuracy: 0.7100
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 |
---|---|---|---|---|
0.75 | 1.0 | 3068 | 0.7202 | 0.6928 |
0.6718 | 2.0 | 6136 | 0.6718 | 0.7209 |
0.5933 | 3.0 | 9204 | 0.6959 | 0.7165 |
0.5075 | 4.0 | 12272 | 0.7149 | 0.7245 |
0.4237 | 5.0 | 15340 | 0.8141 | 0.7124 |
0.341 | 6.0 | 18408 | 0.9218 | 0.7072 |
0.2743 | 7.0 | 21476 | 1.0044 | 0.7124 |
0.2135 | 8.0 | 24544 | 1.1326 | 0.7193 |
0.1685 | 9.0 | 27612 | 1.2362 | 0.7056 |
0.1349 | 10.0 | 30680 | 1.3355 | 0.7100 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 6
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.