Downloads · 30 days
2
9% of all-time downloads
distilbertbaseuncasedz
kevinbror/distilbertbaseuncasedz
distilbertbaseuncasedz is a question answering model from kevinbror. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
probably proofread and complete it, then remove this comment. --
All-time downloads
23
Public
Repo size
266 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5266 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Oct 28, 2022
- Updated
- Oct 28, 2022
- SHA
- c9e99260
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. -->
distilbertbaseuncasedz
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5368
- Train End Logits Accuracy: 0.8401
- Train Start Logits Accuracy: 0.8078
- Validation Loss: 1.2427
- Validation End Logits Accuracy: 0.7050
- Validation Start Logits Accuracy: 0.6725
- Epoch: 3
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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 29508, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.3338 | 0.6448 | 0.6045 | 1.1322 | 0.6906 | 0.6563 | 0 |
| 0.9044 | 0.7466 | 0.7090 | 1.0996 | 0.7032 | 0.6720 | 1 |
| 0.6756 | 0.8042 | 0.7680 | 1.1416 | 0.7047 | 0.6718 | 2 |
| 0.5368 | 0.8401 | 0.8078 | 1.2427 | 0.7050 | 0.6725 | 3 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1
- Task
- Question Answering
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Oct 28, 2022
- Updated
- Oct 28, 2022