|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: turkic-cyrillic-classifier |
|
results: [] |
|
language: |
|
- ba |
|
- cv |
|
- sah |
|
- tt |
|
- ky |
|
- kk |
|
- tyv |
|
- krc |
|
- ru |
|
datasets: |
|
- tatiana-merz/cyrillic_turkic_langs |
|
pipeline_tag: text-classification |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# turkic-cyrillic-classifier |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an tatiana-merz/cyrillic_turkic_langs dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0139 |
|
- Accuracy: 0.9971 |
|
- F1: 0.9971 |
|
|
|
## Model description |
|
|
|
The model classifies text based on a provided Turkic language written in Cyrillic script. |
|
|
|
## Intended uses & limitations |
|
|
|
|
|
|
|
## Training and evaluation data |
|
|
|
[cyrillic_turkic_langs](https://huggingface.co/datasets/tatiana-merz/cyrillic_turkic_langs/) |
|
|
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.1087 | 1.0 | 1000 | 0.0206 | 0.9954 | 0.9954 | |
|
| 0.0111 | 2.0 | 2000 | 0.0139 | 0.9971 | 0.9971 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
