Downloads · 30 days
4
1% of all-time downloads
DistillBerTurk_15_epoch
Buseak/DistillBerTurk_15_epoch
DistillBerTurk_15_epoch is a text classification model from Buseak. 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
311
Public
Repo size
817 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin272 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- distilbert
- Access
- Public
- Created
- Jan 15, 2023
- Updated
- Jan 15, 2023
- SHA
- 7d19ec0e
Try a prompt
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. -->
DistillBerTurk_15_epoch
This model is a fine-tuned version of dbmdz/distilbert-base-turkish-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0549
- Accuracy: 0.9931
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 50 | 0.6766 | 0.625 |
| No log | 2.0 | 100 | 0.3955 | 0.9583 |
| No log | 3.0 | 150 | 0.0874 | 0.9792 |
| No log | 4.0 | 200 | 0.0446 | 0.9861 |
| No log | 5.0 | 250 | 0.0725 | 0.9792 |
| No log | 6.0 | 300 | 0.0352 | 0.9931 |
| No log | 7.0 | 350 | 0.0452 | 0.9931 |
| No log | 8.0 | 400 | 0.0442 | 0.9931 |
| No log | 9.0 | 450 | 0.0499 | 0.9931 |
| 0.1537 | 10.0 | 500 | 0.0514 | 0.9931 |
| 0.1537 | 11.0 | 550 | 0.0542 | 0.9931 |
| 0.1537 | 12.0 | 600 | 0.0545 | 0.9931 |
| 0.1537 | 13.0 | 650 | 0.0548 | 0.9931 |
| 0.1537 | 14.0 | 700 | 0.0550 | 0.9931 |
| 0.1537 | 15.0 | 750 | 0.0549 | 0.9931 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- mit
- Created
- Jan 15, 2023
- Updated
- Jan 15, 2023