|
--- |
|
license: mit |
|
base_model: dbmdz/distilbert-base-turkish-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
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: 0.1938 |
|
- Accuracy: 0.9592 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.9211 | 0.07 | 100 | 1.8456 | 0.3225 | |
|
| 1.6177 | 0.14 | 200 | 1.2261 | 0.5982 | |
|
| 0.8794 | 0.21 | 300 | 0.4865 | 0.8638 | |
|
| 0.428 | 0.27 | 400 | 0.3350 | 0.8991 | |
|
| 0.3189 | 0.34 | 500 | 0.2934 | 0.9128 | |
|
| 0.2869 | 0.41 | 600 | 0.2728 | 0.9219 | |
|
| 0.2776 | 0.48 | 700 | 0.2529 | 0.9267 | |
|
| 0.2334 | 0.55 | 800 | 0.2609 | 0.9303 | |
|
| 0.2314 | 0.62 | 900 | 0.2157 | 0.9369 | |
|
| 0.2381 | 0.69 | 1000 | 0.1924 | 0.9431 | |
|
| 0.2574 | 0.75 | 1100 | 0.2476 | 0.9260 | |
|
| 0.2068 | 0.82 | 1200 | 0.1919 | 0.9429 | |
|
| 0.241 | 0.89 | 1300 | 0.1865 | 0.9417 | |
|
| 0.1894 | 0.96 | 1400 | 0.2022 | 0.9453 | |
|
| 0.1791 | 1.03 | 1500 | 0.2078 | 0.9448 | |
|
| 0.1131 | 1.1 | 1600 | 0.1995 | 0.9493 | |
|
| 0.1082 | 1.17 | 1700 | 0.2074 | 0.9498 | |
|
| 0.1088 | 1.23 | 1800 | 0.2139 | 0.9467 | |
|
| 0.1123 | 1.3 | 1900 | 0.2086 | 0.9481 | |
|
| 0.1083 | 1.37 | 2000 | 0.1964 | 0.9498 | |
|
| 0.1318 | 1.44 | 2100 | 0.1872 | 0.9503 | |
|
| 0.1016 | 1.51 | 2200 | 0.2005 | 0.9486 | |
|
| 0.1415 | 1.58 | 2300 | 0.1918 | 0.9507 | |
|
| 0.1292 | 1.64 | 2400 | 0.1848 | 0.9520 | |
|
| 0.0939 | 1.71 | 2500 | 0.1870 | 0.9539 | |
|
| 0.1301 | 1.78 | 2600 | 0.1950 | 0.9525 | |
|
| 0.1415 | 1.85 | 2700 | 0.1955 | 0.9501 | |
|
| 0.1474 | 1.92 | 2800 | 0.1797 | 0.9556 | |
|
| 0.1169 | 1.99 | 2900 | 0.1767 | 0.9577 | |
|
| 0.0562 | 2.06 | 3000 | 0.1847 | 0.9563 | |
|
| 0.0653 | 2.12 | 3100 | 0.1839 | 0.9584 | |
|
| 0.0431 | 2.19 | 3200 | 0.1853 | 0.9565 | |
|
| 0.0289 | 2.26 | 3300 | 0.1922 | 0.9572 | |
|
| 0.0507 | 2.33 | 3400 | 0.1989 | 0.9582 | |
|
| 0.0475 | 2.4 | 3500 | 0.2009 | 0.9573 | |
|
| 0.0434 | 2.47 | 3600 | 0.1959 | 0.9580 | |
|
| 0.0479 | 2.54 | 3700 | 0.1942 | 0.9585 | |
|
| 0.0421 | 2.6 | 3800 | 0.1986 | 0.9578 | |
|
| 0.0496 | 2.67 | 3900 | 0.1947 | 0.9577 | |
|
| 0.0452 | 2.74 | 4000 | 0.1938 | 0.9594 | |
|
| 0.0329 | 2.81 | 4100 | 0.1936 | 0.9594 | |
|
| 0.0568 | 2.88 | 4200 | 0.1934 | 0.9584 | |
|
| 0.0441 | 2.95 | 4300 | 0.1938 | 0.9592 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|