Update README.md
Browse files
README.md
CHANGED
@@ -13,26 +13,20 @@ pipeline_tag: text-classification
|
|
13 |
|
14 |
This is a text classification model based on DistilBERT. It has been fine-tuned on the ecommerce_reviews_with_language_drift dataset.
|
15 |
|
16 |
-
## Model Description
|
17 |
-
|
18 |
-
Provide a detailed description of your model here. Explain what the model does, how it was trained, and any specific considerations.
|
19 |
-
|
20 |
## Intended Use
|
21 |
|
22 |
-
|
23 |
|
24 |
## Training Data
|
25 |
|
26 |
-
|
27 |
|
28 |
## Evaluation
|
29 |
|
30 |
-
|
31 |
|
32 |
## Example Usage
|
33 |
|
34 |
-
Provide a code snippet showing how to use the model. This helps users quickly understand how to implement it.
|
35 |
-
|
36 |
```python
|
37 |
from transformers import pipeline
|
38 |
|
|
|
13 |
|
14 |
This is a text classification model based on DistilBERT. It has been fine-tuned on the ecommerce_reviews_with_language_drift dataset.
|
15 |
|
|
|
|
|
|
|
|
|
16 |
## Intended Use
|
17 |
|
18 |
+
The model is used for classifying product reviews in text format. The probable outputs are 'positive', 'negative' and 'neutral'.
|
19 |
|
20 |
## Training Data
|
21 |
|
22 |
+
The arize-ai/ecommerce_reviews_with_language_drift dataset was used for training. Only the 'text' and 'label' columns were used. The training dataset contains 8k rows out of which 34.1% are labeled 'positive', 33.4 % are labeled 'negative' and 32.5% are labeled 'neutral'. So it is a balanced dataset.
|
23 |
|
24 |
## Evaluation
|
25 |
|
26 |
+
The model was fine tuned based on the F1 score for 50 epochs. The best score obtained was 0.67.
|
27 |
|
28 |
## Example Usage
|
29 |
|
|
|
|
|
30 |
```python
|
31 |
from transformers import pipeline
|
32 |
|