20231005-7-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: 0.5772
- Loss: 1.7150
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 |
|---|---|---|---|---|
| 2.874 | 1.82 | 200 | 0.4369 | 2.5306 |
| 2.4348 | 3.64 | 400 | 0.4769 | 2.3597 |
| 2.2095 | 5.45 | 600 | 0.5075 | 2.1530 |
| 2.0581 | 7.27 | 800 | 0.54 | 1.9225 |
| 1.9638 | 9.09 | 1000 | 0.5374 | 1.9407 |
| 1.8751 | 10.91 | 1200 | 0.5792 | 1.7523 |
| 1.8096 | 12.73 | 1400 | 0.5839 | 1.9942 |
| 1.7306 | 14.55 | 1600 | 0.6185 | 1.6402 |
| 1.699 | 16.36 | 1800 | 0.5956 | 1.7014 |
| 1.6946 | 18.18 | 2000 | 0.5679 | 1.8545 |
| 1.6581 | 20.0 | 2200 | 0.5772 | 1.7150 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1