Downloads · 30 days
10
21% of all-time downloads
bert-turkish-from-scratch-2
Xessen/bert-turkish-from-scratch-2
bert-turkish-from-scratch-2 is a fill-mask model from Xessen. Use it when you need the model to fill a missing word. It is set up for transformers.
probably proofread and complete it, then remove this comment. --
All-time downloads
47
Public
Repo size
543 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5543 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Dec 26, 2022
- Updated
- Dec 26, 2022
- SHA
- 0a4d4ef0
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
bert-turkish-from-scratch-2
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2439
- Train Accuracy: 0.9903
- Epoch: 6
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:
- optimizer: {'name': 'Adagrad', 'learning_rate': 0.001, 'decay': 0.0, 'initial_accumulator_value': 0.1, 'epsilon': 1e-07}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Epoch |
|---|---|---|
| 0.5831 | 0.9423 | 0 |
| 0.4659 | 0.9522 | 1 |
| 0.3938 | 0.9603 | 2 |
| 0.3409 | 0.9700 | 3 |
| 0.3003 | 0.9807 | 4 |
| 0.2690 | 0.9874 | 5 |
| 0.2439 | 0.9903 | 6 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.9.2
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Dec 26, 2022
- Updated
- Dec 26, 2022