metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: germanic_antielite_Dutch
results: []
germanic_antielite_Dutch
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2547
- Accuracy: 0.8557
- F1: 0.0667
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 97 | 0.6825 | 0.8376 | 0.1127 |
| 0.1766 | 2.0 | 194 | 0.4794 | 0.8428 | 0.0896 |
| 0.2952 | 3.0 | 291 | 0.8158 | 0.8299 | 0.1081 |
| 0.1576 | 4.0 | 388 | 0.9771 | 0.8531 | 0.0952 |
| 0.0718 | 5.0 | 485 | 1.1854 | 0.8247 | 0.0811 |
| 0.0352 | 6.0 | 582 | 1.1599 | 0.8325 | 0.0580 |
| 0.0167 | 7.0 | 679 | 1.2373 | 0.8376 | 0.0308 |
| 0.0058 | 8.0 | 776 | 1.4320 | 0.8015 | 0.0941 |
| 0.0065 | 9.0 | 873 | 1.2486 | 0.8557 | 0.0667 |
| 0.0021 | 10.0 | 970 | 1.2547 | 0.8557 | 0.0667 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3