Downloads · 30 days
10
4% of all-time downloads
poebert-eras-balanced
edgertej/poebert-eras-balanced
poebert-eras-balanced is a fill-mask model from edgertej. Use it when you need the model to fill a missing word. 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
274
Public
Repo size
5.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5524 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Feb 9, 2023
- Updated
- Feb 10, 2023
- SHA
- 79a89b4c
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. -->
edgertej/poebert-eras-balanced
This model is a fine-tuned version of edgertej/poebert-eras-balanced on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.5715
- Validation Loss: 3.3710
- 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': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.8002 | 3.5259 | 0 |
| 3.7486 | 3.4938 | 1 |
| 3.7053 | 3.4520 | 2 |
| 3.7315 | 3.4211 | 3 |
| 3.6226 | 3.4031 | 4 |
| 3.6021 | 3.3968 | 5 |
| 3.5715 | 3.3710 | 6 |
Framework versions
- Transformers 4.19.2
- TensorFlow 2.11.0
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Feb 9, 2023
- Updated
- Feb 10, 2023