<!-- 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. -->
20231005-3-bert-base-multilingual-cased-new
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.6077
- Loss: 1.7371
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.9237 | 1.82 | 200 | 0.4526 | 2.4628 |
| 2.3796 | 3.64 | 400 | 0.4668 | 2.4166 |
| 2.2074 | 5.45 | 600 | 0.5011 | 2.1639 |
| 2.1154 | 7.27 | 800 | 0.5333 | 1.9224 |
| 1.9577 | 9.09 | 1000 | 0.5607 | 1.8915 |
| 1.8846 | 10.91 | 1200 | 0.6009 | 1.5682 |
| 1.8251 | 12.73 | 1400 | 0.6024 | 1.6171 |
| 1.7344 | 14.55 | 1600 | 0.5923 | 1.6795 |
| 1.7236 | 16.36 | 1800 | 0.6191 | 1.5585 |
| 1.7099 | 18.18 | 2000 | 0.6241 | 1.6113 |
| 1.6309 | 20.0 | 2200 | 0.6077 | 1.7371 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
