<!-- 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. -->
SloBertAA_Top50_WithoutOOC_082023_MultilingualBertBase
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6236
- Accuracy: 0.7730
- F1: 0.7728
- Precision: 0.7736
- Recall: 0.7730
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: 12
- eval_batch_size: 12
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.1768 | 1.0 | 32692 | 1.1341 | 0.6842 | 0.6855 | 0.7048 | 0.6842 |
| 0.9542 | 2.0 | 65384 | 1.0140 | 0.7208 | 0.7219 | 0.7378 | 0.7208 |
| 0.7375 | 3.0 | 98076 | 0.9313 | 0.7465 | 0.7465 | 0.7513 | 0.7465 |
| 0.6123 | 4.0 | 130768 | 0.9390 | 0.7575 | 0.7578 | 0.7611 | 0.7575 |
| 0.4369 | 5.0 | 163460 | 1.0083 | 0.7619 | 0.7624 | 0.7664 | 0.7619 |
| 0.3249 | 6.0 | 196152 | 1.1329 | 0.7623 | 0.7638 | 0.7701 | 0.7623 |
| 0.2409 | 7.0 | 228844 | 1.2999 | 0.7645 | 0.7644 | 0.7678 | 0.7645 |
| 0.1536 | 8.0 | 261536 | 1.4614 | 0.7674 | 0.7682 | 0.7707 | 0.7674 |
| 0.1163 | 9.0 | 294228 | 1.5755 | 0.7708 | 0.7706 | 0.7719 | 0.7708 |
| 0.0716 | 10.0 | 326920 | 1.6236 | 0.7730 | 0.7728 | 0.7736 | 0.7730 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2
