|
--- |
|
library_name: keras |
|
language: |
|
- en |
|
pipeline_tag: text-classification |
|
tags: |
|
- toxic |
|
- comment |
|
- toxic comment |
|
--- |
|
|
|
## Model description |
|
|
|
This model used for text classification with toxic and non-toxic labels. |
|
|
|
## Intended uses & limitations |
|
|
|
If you want to reuse model, try copy this |
|
``` |
|
from huggingface_hub import from_pretrained_keras |
|
reloaded_model = from_pretrained_keras('Johnesss/Toxic-Comment-Classification') |
|
|
|
y_testing=reloaded_model.predict(x_testing,verbose=1,batch_size=32) |
|
test_df['Toxic']=['Not Toxic' if x<0.5 else 'Toxic' for x in y_testing] |
|
test_df[['comment_text','Toxic']].head(20) |
|
``` |
|
## Training and evaluation data |
|
|
|
Full info in .ipynb file |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
|
|
| Hyperparameters | Value | |
|
| :-- | :-- | |
|
| name | Adam | |
|
| weight_decay | None | |
|
| clipnorm | None | |
|
| global_clipnorm | None | |
|
| clipvalue | None | |
|
| use_ema | False | |
|
| ema_momentum | 0.99 | |
|
| ema_overwrite_frequency | None | |
|
| jit_compile | False | |
|
| is_legacy_optimizer | False | |
|
| learning_rate | 0.0010000000474974513 | |
|
| beta_1 | 0.9 | |
|
| beta_2 | 0.999 | |
|
| epsilon | 1e-07 | |
|
| amsgrad | False | |
|
| training_precision | float32 | |
|
|
|
|
|
## Model Plot |
|
|
|
<details> |
|
<summary>View Model Plot</summary> |
|
|
|
 |
|
|
|
</details> |
