Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ metrics:
|
|
| 10 |
model-index:
|
| 11 |
- name: roberta-finetuned-WebClassification
|
| 12 |
results: []
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# roberta-finetuned-WebClassification
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 0.3473
|
| 23 |
- Accuracy: 0.9504
|
|
@@ -27,15 +28,31 @@ It achieves the following results on the evaluation set:
|
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## Intended uses & limitations
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
## Training and evaluation data
|
| 37 |
|
| 38 |
-
|
| 39 |
|
| 40 |
## Training procedure
|
| 41 |
|
|
@@ -71,4 +88,4 @@ The following hyperparameters were used during training:
|
|
| 71 |
- Transformers 4.16.2
|
| 72 |
- Pytorch 1.9.1
|
| 73 |
- Datasets 1.18.4
|
| 74 |
-
- Tokenizers 0.11.6
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: roberta-finetuned-WebClassification
|
| 12 |
results: []
|
| 13 |
+
pipeline_tag: text-classification
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 18 |
|
| 19 |
# roberta-finetuned-WebClassification
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [Web Classification Dataset](https://www.kaggle.com/datasets/hetulmehta/website-classification).
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.3473
|
| 24 |
- Accuracy: 0.9504
|
|
|
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
| 31 |
+
The model classifies websites into the following categories:
|
| 32 |
+
- "0": "Adult",
|
| 33 |
+
- "1": "Business/Corporate",
|
| 34 |
+
- "2": "Computers and Technology",
|
| 35 |
+
- "3": "E-Commerce",
|
| 36 |
+
- "4": "Education",
|
| 37 |
+
- "5": "Food",
|
| 38 |
+
- "6": "Forums",
|
| 39 |
+
- "7": "Games",
|
| 40 |
+
- "8": "Health and Fitness",
|
| 41 |
+
- "9": "Law and Government",
|
| 42 |
+
- "10": "News",
|
| 43 |
+
- "11": "Photography",
|
| 44 |
+
- "12": "Social Networking and Messaging",
|
| 45 |
+
- "13": "Sports",
|
| 46 |
+
- "14": "Streaming Services",
|
| 47 |
+
- "15": "Travel"
|
| 48 |
|
| 49 |
## Intended uses & limitations
|
| 50 |
|
| 51 |
+
Web classification in English (for now).
|
| 52 |
|
| 53 |
## Training and evaluation data
|
| 54 |
|
| 55 |
+
Trained and tested on a 80/20 split of the [Web Classification Dataset](https://www.kaggle.com/datasets/hetulmehta/website-classification).
|
| 56 |
|
| 57 |
## Training procedure
|
| 58 |
|
|
|
|
| 88 |
- Transformers 4.16.2
|
| 89 |
- Pytorch 1.9.1
|
| 90 |
- Datasets 1.18.4
|
| 91 |
+
- Tokenizers 0.11.6
|