|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: SloBertAA_Top100_WithOOC_082023_MultilingualBertBase |
|
results: [] |
|
--- |
|
|
|
<!-- 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_Top100_WithOOC_082023_MultilingualBertBase |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8608 |
|
- Accuracy: 0.6898 |
|
- F1: 0.6904 |
|
- Precision: 0.6936 |
|
- Recall: 0.6898 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.7313 | 1.0 | 45122 | 1.6826 | 0.5773 | 0.5766 | 0.5997 | 0.5773 | |
|
| 1.4117 | 2.0 | 90244 | 1.4419 | 0.6341 | 0.6345 | 0.6529 | 0.6341 | |
|
| 1.1573 | 3.0 | 135366 | 1.3509 | 0.6614 | 0.6620 | 0.6733 | 0.6614 | |
|
| 0.9147 | 4.0 | 180488 | 1.3583 | 0.6695 | 0.6699 | 0.6817 | 0.6695 | |
|
| 0.7452 | 5.0 | 225610 | 1.3881 | 0.6797 | 0.6800 | 0.6887 | 0.6797 | |
|
| 0.5393 | 6.0 | 270732 | 1.4650 | 0.6828 | 0.6835 | 0.6897 | 0.6828 | |
|
| 0.4207 | 7.0 | 315854 | 1.5770 | 0.6839 | 0.6840 | 0.6905 | 0.6839 | |
|
| 0.2985 | 8.0 | 360976 | 1.6813 | 0.6869 | 0.6877 | 0.6921 | 0.6869 | |
|
| 0.2029 | 9.0 | 406098 | 1.7977 | 0.6882 | 0.6886 | 0.6923 | 0.6882 | |
|
| 0.1546 | 10.0 | 451220 | 1.8608 | 0.6898 | 0.6904 | 0.6936 | 0.6898 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.8.0 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
