Downloads · 30 days
8
3% of all-time downloads
bert-turkish-emotion-deprecated2
alperengozeten/bert-turkish-emotion-deprecated2
bert-turkish-emotion-deprecated2 is a text classification model from alperengozeten. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
319
Public
Parameters
111M
443 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors443 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Nov 11, 2023
- Updated
- Nov 11, 2023
- SHA
- 8b962ceb
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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/bert-base-turkish-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1455
- Accuracy: 0.9716
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 |
|---|---|---|---|---|
| 1.6937 | 0.14 | 200 | 0.5659 | 0.8653 |
| 0.3263 | 0.27 | 400 | 0.2603 | 0.9248 |
| 0.2423 | 0.41 | 600 | 0.2538 | 0.9323 |
| 0.2036 | 0.55 | 800 | 0.2016 | 0.9495 |
| 0.1961 | 0.69 | 1000 | 0.1868 | 0.9519 |
| 0.1837 | 0.82 | 1200 | 0.1819 | 0.9537 |
| 0.2017 | 0.96 | 1400 | 0.1481 | 0.9626 |
| 0.1337 | 1.1 | 1600 | 0.1735 | 0.9597 |
| 0.097 | 1.23 | 1800 | 0.1684 | 0.9616 |
| 0.1059 | 1.37 | 2000 | 0.1545 | 0.9614 |
| 0.0968 | 1.51 | 2200 | 0.1436 | 0.9657 |
| 0.1147 | 1.64 | 2400 | 0.1401 | 0.9638 |
| 0.082 | 1.78 | 2600 | 0.1389 | 0.9673 |
| 0.078 | 1.92 | 2800 | 0.1233 | 0.9719 |
| 0.0668 | 2.06 | 3000 | 0.1373 | 0.9690 |
| 0.0279 | 2.19 | 3200 | 0.1512 | 0.9702 |
| 0.0331 | 2.33 | 3400 | 0.1353 | 0.9738 |
| 0.0276 | 2.47 | 3600 | 0.1404 | 0.9733 |
| 0.0339 | 2.6 | 3800 | 0.1527 | 0.9719 |
| 0.031 | 2.74 | 4000 | 0.1483 | 0.9710 |
| 0.0224 | 2.88 | 4200 | 0.1455 | 0.9716 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Nov 11, 2023
- Updated
- Nov 11, 2023