<!-- 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. -->
mongolian-distilbert-base-multilingual-cased
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1406
- Precision: 0.8746
- Recall: 0.8997
- F1: 0.8869
- Accuracy: 0.9721
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2177 | 1.0 | 477 | 0.1185 | 0.8180 | 0.8560 | 0.8366 | 0.9629 |
| 0.1017 | 2.0 | 954 | 0.1035 | 0.8538 | 0.8841 | 0.8687 | 0.9694 |
| 0.0676 | 3.0 | 1431 | 0.1056 | 0.8545 | 0.8869 | 0.8704 | 0.9694 |
| 0.0476 | 4.0 | 1908 | 0.1087 | 0.8737 | 0.8958 | 0.8846 | 0.9715 |
| 0.0348 | 5.0 | 2385 | 0.1165 | 0.8601 | 0.8924 | 0.8759 | 0.9703 |
| 0.0246 | 6.0 | 2862 | 0.1294 | 0.8625 | 0.8925 | 0.8772 | 0.9703 |
| 0.0168 | 7.0 | 3339 | 0.1366 | 0.8697 | 0.8968 | 0.8830 | 0.9707 |
| 0.0133 | 8.0 | 3816 | 0.1391 | 0.8776 | 0.9007 | 0.8890 | 0.9727 |
| 0.0103 | 9.0 | 4293 | 0.1406 | 0.8746 | 0.8997 | 0.8869 | 0.9721 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
