<!-- 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_Top5_WithOOC_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: 1.1001
- Accuracy: 0.8632
- F1: 0.8624
- Precision: 0.8622
- Recall: 0.8632
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 |
|---|---|---|---|---|---|---|---|
| 0.4675 | 1.0 | 10508 | 0.4490 | 0.8365 | 0.8351 | 0.8355 | 0.8365 |
| 0.3655 | 2.0 | 21016 | 0.4580 | 0.8508 | 0.8493 | 0.8489 | 0.8508 |
| 0.3053 | 3.0 | 31524 | 0.4766 | 0.8544 | 0.8543 | 0.8555 | 0.8544 |
| 0.2454 | 4.0 | 42032 | 0.5682 | 0.8625 | 0.8621 | 0.8619 | 0.8625 |
| 0.1867 | 5.0 | 52540 | 0.7710 | 0.8575 | 0.8584 | 0.8610 | 0.8575 |
| 0.1376 | 6.0 | 63048 | 0.8143 | 0.8564 | 0.8560 | 0.8570 | 0.8564 |
| 0.1104 | 7.0 | 73556 | 0.9258 | 0.8588 | 0.8575 | 0.8576 | 0.8588 |
| 0.066 | 8.0 | 84064 | 0.9841 | 0.8625 | 0.8624 | 0.8625 | 0.8625 |
| 0.0412 | 9.0 | 94572 | 1.0835 | 0.8628 | 0.8614 | 0.8617 | 0.8628 |
| 0.034 | 10.0 | 105080 | 1.1001 | 0.8632 | 0.8624 | 0.8622 | 0.8632 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2
