Commit ·
ef28f9a
1
Parent(s): 8a5e9f5
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,12 +6,9 @@ model-index:
|
|
| 6 |
results: []
|
| 7 |
---
|
| 8 |
|
| 9 |
-
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 10 |
-
probably proofread and complete it, then remove this comment. -->
|
| 11 |
-
|
| 12 |
# RobCaamano/toxicity_weighted
|
| 13 |
|
| 14 |
-
This model was trained from scratch on
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
|
| 17 |
- Train Loss: 0.0240
|
|
@@ -21,11 +18,11 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
## Intended uses & limitations
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
|
|
@@ -43,11 +40,11 @@ The following hyperparameters were used during training:
|
|
| 43 |
|
| 44 |
| Train Loss | Train Precision | Train Recall | Epoch |
|
| 45 |
|:----------:|:---------------:|:------------:|:-----:|
|
| 46 |
-
| 0.0440 | 0.9059 | 0.8294 |
|
| 47 |
-
| 0.0380 | 0.9223 | 0.8632 |
|
| 48 |
-
| 0.0314 | 0.9335 | 0.8838 |
|
| 49 |
-
| 0.0282 | 0.9437 | 0.9075 |
|
| 50 |
-
| 0.0240 | 0.9522 | 0.9190 |
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
|
|
|
| 6 |
results: []
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
| 9 |
# RobCaamano/toxicity_weighted
|
| 10 |
|
| 11 |
+
This model was trained from scratch on Distilbert Base Uncased.
|
| 12 |
It achieves the following results on the evaluation set:
|
| 13 |
|
| 14 |
- Train Loss: 0.0240
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
+
Finetuned model that uses Distilbert Base Uncased to detect types of toxic text. These include: "toxic", "severe_toxic", "obscene", "threat", "insult" & "identity_hate".
|
| 22 |
|
| 23 |
## Intended uses & limitations
|
| 24 |
|
| 25 |
+
Intended to classify text into different types of toxicity when it is detected. Trained off a small dataset with underrepresented categories.
|
| 26 |
|
| 27 |
## Training and evaluation data
|
| 28 |
|
|
|
|
| 40 |
|
| 41 |
| Train Loss | Train Precision | Train Recall | Epoch |
|
| 42 |
|:----------:|:---------------:|:------------:|:-----:|
|
| 43 |
+
| 0.0440 | 0.9059 | 0.8294 | 7 |
|
| 44 |
+
| 0.0380 | 0.9223 | 0.8632 | 8 |
|
| 45 |
+
| 0.0314 | 0.9335 | 0.8838 | 9 |
|
| 46 |
+
| 0.0282 | 0.9437 | 0.9075 | 10 |
|
| 47 |
+
| 0.0240 | 0.9522 | 0.9190 | 11 |
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|