Delete MODEL_CARD.md with huggingface_hub
Browse files- MODEL_CARD.md +0 -39
MODEL_CARD.md
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
library_name: transformers
|
| 4 |
-
---
|
| 5 |
-
# BestSweepModel
|
| 6 |
-
|
| 7 |
-
This model was selected from a hyperparameter sweep over 5 configurations. The run with the lowest validation loss was chosen as the final model.
|
| 8 |
-
|
| 9 |
-
## Training Configuration
|
| 10 |
-
|
| 11 |
-
All runs used the same base architecture (BERT-base) and training setup, varying only the learning rate and weight decay.
|
| 12 |
-
|
| 13 |
-
## Sweep Results
|
| 14 |
-
|
| 15 |
-
| Run | Learning Rate | Weight Decay | Train Loss | Val Loss | Val Accuracy | Val F1 |
|
| 16 |
-
|---|---|---|---|---|---|---|
|
| 17 |
-
| run_lr1e-3_wd0.01 | 0.001000 | 0.0100 | 0.082 | 0.347 | 0.882 | 0.871 |
|
| 18 |
-
| run_lr5e-4_wd0.001 | 0.000500 | 0.0010 | 0.119 | 0.285 | 0.904 | 0.898 |
|
| 19 |
-
| run_lr1e-4_wd0.1 | 0.000100 | 0.1000 | 0.451 | 0.523 | 0.791 | 0.776 |
|
| 20 |
-
| run_lr3e-4_wd0.01 | 0.000300 | 0.0100 | 0.098 | 0.261 | 0.917 | 0.911 |
|
| 21 |
-
| run_lr2e-4_wd0.05 | 0.000200 | 0.0500 | 0.203 | 0.312 | 0.895 | 0.887 |
|
| 22 |
-
|
| 23 |
-
**Best run**: run_lr3e-4_wd0.01 (lowest val_loss = 0.261)
|
| 24 |
-
|
| 25 |
-
## Intended Use
|
| 26 |
-
|
| 27 |
-
This model is intended for text classification tasks. It was trained on a standard benchmark dataset.
|
| 28 |
-
|
| 29 |
-
## How to Use
|
| 30 |
-
|
| 31 |
-
```python
|
| 32 |
-
from transformers import AutoModel, AutoTokenizer
|
| 33 |
-
model = AutoModel.from_pretrained("BestSweepModel-TestRepo")
|
| 34 |
-
tokenizer = AutoTokenizer.from_pretrained("BestSweepModel-TestRepo")
|
| 35 |
-
```
|
| 36 |
-
|
| 37 |
-
## License
|
| 38 |
-
|
| 39 |
-
Apache 2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|