Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
text-embeddings-inference
Instructions to use caush/Clickbait2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use caush/Clickbait2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="caush/Clickbait2")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("caush/Clickbait2") model = AutoModelForSequenceClassification.from_pretrained("caush/Clickbait2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 0.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -44,36 +44,22 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
-
| No log | 0.05 | 50 | 0.
|
| 48 |
-
| No log | 0.09 | 100 | 0.
|
| 49 |
-
| No log | 0.14 | 150 | 0.
|
| 50 |
-
| No log | 0.18 | 200 | 0.
|
| 51 |
-
| No log | 0.23 | 250 | 0.
|
| 52 |
-
| No log | 0.27 | 300 | 0.
|
| 53 |
-
| No log | 0.32 | 350 | 0.
|
| 54 |
-
| No log | 0.36 | 400 | 0.
|
| 55 |
-
| No log | 0.41 | 450 | 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.0221 | 0.77 | 850 | 0.0217 |
|
| 64 |
-
| 0.0221 | 0.82 | 900 | 0.0222 |
|
| 65 |
-
| 0.0221 | 0.87 | 950 | 0.0218 |
|
| 66 |
-
| 0.0217 | 0.91 | 1000 | 0.0214 |
|
| 67 |
-
| 0.0217 | 0.96 | 1050 | 0.0216 |
|
| 68 |
-
| 0.0217 | 1.0 | 1100 | 0.0217 |
|
| 69 |
-
| 0.0217 | 1.05 | 1150 | 0.0217 |
|
| 70 |
-
| 0.0217 | 1.09 | 1200 | 0.0215 |
|
| 71 |
-
| 0.0217 | 1.14 | 1250 | 0.0216 |
|
| 72 |
-
| 0.0217 | 1.18 | 1300 | 0.0215 |
|
| 73 |
-
| 0.0217 | 1.23 | 1350 | 0.0217 |
|
| 74 |
-
| 0.0217 | 1.28 | 1400 | 0.0217 |
|
| 75 |
-
| 0.0217 | 1.32 | 1450 | 0.0221 |
|
| 76 |
-
| 0.0219 | 1.37 | 1500 | 0.0220 |
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0212
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
+
| No log | 0.05 | 50 | 0.0213 |
|
| 48 |
+
| No log | 0.09 | 100 | 0.0213 |
|
| 49 |
+
| No log | 0.14 | 150 | 0.0213 |
|
| 50 |
+
| No log | 0.18 | 200 | 0.0216 |
|
| 51 |
+
| No log | 0.23 | 250 | 0.0214 |
|
| 52 |
+
| No log | 0.27 | 300 | 0.0212 |
|
| 53 |
+
| No log | 0.32 | 350 | 0.0214 |
|
| 54 |
+
| No log | 0.36 | 400 | 0.0212 |
|
| 55 |
+
| No log | 0.41 | 450 | 0.0218 |
|
| 56 |
+
| 0.0219 | 0.46 | 500 | 0.0219 |
|
| 57 |
+
| 0.0219 | 0.5 | 550 | 0.0214 |
|
| 58 |
+
| 0.0219 | 0.55 | 600 | 0.0216 |
|
| 59 |
+
| 0.0219 | 0.59 | 650 | 0.0217 |
|
| 60 |
+
| 0.0219 | 0.64 | 700 | 0.0214 |
|
| 61 |
+
| 0.0219 | 0.68 | 750 | 0.0214 |
|
| 62 |
+
| 0.0219 | 0.73 | 800 | 0.0214 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|