Downloads · 30 days
14
5% of all-time downloads
ASTBERT-gb-5k-methods-multipath
JasperGrant/ASTBERT-gb-5k-methods-multipath
ASTBERT-gb-5k-methods-multipath is a fill-mask model from JasperGrant. 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
263
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5655 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 25, 2024
- Updated
- Mar 25, 2024
- SHA
- 5aa1c434
Try a prompt
Base models
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. -->
ASTBERT-gb-5k-methods-multipath
This model is a fine-tuned version of microsoft/graphcodebert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1757
- Train Accuracy: 0.9637
- Epoch: 9
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': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Epoch |
|---|---|---|
| 1.0763 | 0.8934 | 0 |
| 0.5565 | 0.9292 | 1 |
| 0.5056 | 0.9298 | 2 |
| 0.4761 | 0.9317 | 3 |
| 0.4387 | 0.9346 | 4 |
| 0.3948 | 0.9375 | 5 |
| 0.3434 | 0.9418 | 6 |
| 0.2872 | 0.9474 | 7 |
| 0.2297 | 0.9550 | 8 |
| 0.1757 | 0.9637 | 9 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.10.0
- Datasets 2.18.0
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Mar 25, 2024
- Updated
- Mar 25, 2024