|
--- |
|
license: mit |
|
base_model: dbmdz/distilbert-base-turkish-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert_turk |
|
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. --> |
|
|
|
# distilbert_turk |
|
|
|
This model is a fine-tuned version of [dbmdz/distilbert-base-turkish-cased](https://huggingface.co/dbmdz/distilbert-base-turkish-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1927 |
|
- F1: 0.8338 |
|
- Roc Auc: 0.9092 |
|
- Accuracy: 0.8047 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- 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 | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.2899 | 1.0 | 1151 | 0.2053 | 0.6418 | 0.7738 | 0.6719 | |
|
| 0.1846 | 2.0 | 2302 | 0.1777 | 0.7480 | 0.8434 | 0.7461 | |
|
| 0.1432 | 3.0 | 3453 | 0.1633 | 0.7879 | 0.8866 | 0.7656 | |
|
| 0.1241 | 4.0 | 4604 | 0.1508 | 0.8256 | 0.9037 | 0.7891 | |
|
| 0.0961 | 5.0 | 5755 | 0.1621 | 0.8203 | 0.9048 | 0.7969 | |
|
| 0.065 | 6.0 | 6906 | 0.1733 | 0.8108 | 0.9092 | 0.7969 | |
|
| 0.0548 | 7.0 | 8057 | 0.1848 | 0.8238 | 0.8993 | 0.7930 | |
|
| 0.0496 | 8.0 | 9208 | 0.1875 | 0.8130 | 0.9055 | 0.7969 | |
|
| 0.0413 | 9.0 | 10359 | 0.1905 | 0.8359 | 0.9096 | 0.8086 | |
|
| 0.038 | 10.0 | 11510 | 0.1927 | 0.8338 | 0.9092 | 0.8047 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
