geocoder_model
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:
- Loss: 0.2632
- Accuracy: {'accuracy': 0.9005447386872337}
- F1: {'f1': 0.8323636363636362}
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.26 | 1.0 | 4636 | 0.2405 | {'accuracy': 0.8972547327544361} | {'f1': 0.827866630523177} |
| 0.2069 | 2.0 | 9272 | 0.2632 | {'accuracy': 0.9005447386872337} | {'f1': 0.8323636363636362} |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Tokenizers 0.13.2
- Downloads last month
- 5