xnli_m_bert_only_zh
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: 1.1968
- Accuracy: 0.7458
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 |
---|---|---|---|---|
0.6394 | 1.0 | 3068 | 0.6471 | 0.7277 |
0.5624 | 2.0 | 6136 | 0.5779 | 0.7631 |
0.4797 | 3.0 | 9204 | 0.6200 | 0.7470 |
0.395 | 4.0 | 12272 | 0.6384 | 0.7494 |
0.3193 | 5.0 | 15340 | 0.7014 | 0.7618 |
0.2476 | 6.0 | 18408 | 0.8153 | 0.7418 |
0.1902 | 7.0 | 21476 | 0.8486 | 0.7446 |
0.1467 | 8.0 | 24544 | 0.9420 | 0.7506 |
0.1114 | 9.0 | 27612 | 1.1149 | 0.7506 |
0.0848 | 10.0 | 30680 | 1.1968 | 0.7458 |
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.