<!-- 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_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: 0.6526
- Accuracy: 0.9227
- F1: 0.9228
- Precision: 0.9230
- Recall: 0.9227
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 |
|---|---|---|---|---|---|---|---|
| 0.3056 | 1.0 | 8757 | 0.3510 | 0.8843 | 0.8849 | 0.8893 | 0.8843 |
| 0.2614 | 2.0 | 17514 | 0.2988 | 0.9095 | 0.9094 | 0.9103 | 0.9095 |
| 0.1881 | 3.0 | 26271 | 0.3785 | 0.9106 | 0.9112 | 0.9126 | 0.9106 |
| 0.1491 | 4.0 | 35028 | 0.4143 | 0.9151 | 0.9150 | 0.9153 | 0.9151 |
| 0.1046 | 5.0 | 43785 | 0.5086 | 0.9163 | 0.9161 | 0.9161 | 0.9163 |
| 0.0642 | 6.0 | 52542 | 0.5380 | 0.9189 | 0.9189 | 0.9191 | 0.9189 |
| 0.0434 | 7.0 | 61299 | 0.6107 | 0.9146 | 0.9150 | 0.9171 | 0.9146 |
| 0.0308 | 8.0 | 70056 | 0.6446 | 0.9199 | 0.9200 | 0.9202 | 0.9199 |
| 0.0239 | 9.0 | 78813 | 0.6299 | 0.9226 | 0.9227 | 0.9228 | 0.9226 |
| 0.0106 | 10.0 | 87570 | 0.6526 | 0.9227 | 0.9228 | 0.9230 | 0.9227 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2
