metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mbert-en-finetuned-sinta-e10
results: []
mbert-en-finetuned-sinta-e10
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1755
- F1: 0.7669
- Roc Auc: 0.8281
- Accuracy: 0.4681
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 141 | 0.2791 | 0.5873 | 0.7299 | 0.1631 |
| No log | 2.0 | 282 | 0.2282 | 0.7026 | 0.7830 | 0.3475 |
| No log | 3.0 | 423 | 0.2069 | 0.7022 | 0.7853 | 0.3546 |
| 0.2721 | 4.0 | 564 | 0.1903 | 0.7344 | 0.8029 | 0.3901 |
| 0.2721 | 5.0 | 705 | 0.1817 | 0.7467 | 0.8148 | 0.4397 |
| 0.2721 | 6.0 | 846 | 0.1755 | 0.7669 | 0.8281 | 0.4681 |
| 0.2721 | 7.0 | 987 | 0.1706 | 0.7628 | 0.8236 | 0.4539 |
| 0.1659 | 8.0 | 1128 | 0.1666 | 0.7664 | 0.8292 | 0.4823 |
| 0.1659 | 9.0 | 1269 | 0.1650 | 0.7626 | 0.8274 | 0.4681 |
| 0.1659 | 10.0 | 1410 | 0.1645 | 0.7649 | 0.8290 | 0.4681 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1