Update README.md

README.md

@@ -2,23 +2,43 @@
 license: mit
 base_model: roberta-base
 tags:
-- generated_from_trainer
+  - topic
+  - classification
+  - news
+  - roberta
 metrics:
 - accuracy
 - f1
 - precision
 - recall
+datasets:
+  - dstefa/New_York_Times_Topics
+widget:
+  - text: >-
+      Olympic champion Kostas Kederis today left hospital ahead of his date with IOC inquisitors claiming his innocence and vowing.
+    example_title: Analyst Update'
 model-index:
 - name: roberta-base_topic_classification_nyt_news
-  results: []
+  results:
+    - task:
+          name: Text Classification
+          type: text-classification
+      dataset:
+          name: New_York_Times_Topics
+          type: News
+      metrics:
+          - type: F1
+            name: F1
+            value: 0.910647
+          - type: accuracy
+            name: accuracy
+            value: 0.910615
+pipeline_tag: text-classification
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # roberta-base_topic_classification_nyt_news
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the NYT News dataset (https://www.kaggle.com/datasets/aryansingh0909/nyt-articles-21m-2000-present).
 It achieves the following results on the evaluation set:
 - Loss: 0.3797
 - Accuracy: 0.9094
@@ -34,9 +54,19 @@ More information needed
 
 More information needed
 
-## Training and evaluation data
+## Training data
+Training data was classified as follow:
 
-More information needed
+class |Description
+-|-
+0 |Sports
+1 |Arts, Culture, and Entertainment
+2 |Business and Finance
+3 |Health and Wellness
+4 |Lifestyle and Fashion
+5 |Science and Technology
+6 |Politics
+7 |Crime
 
 ## Training procedure
 
@@ -62,6 +92,39 @@ The following hyperparameters were used during training:
 | 0.1239        | 4.0   | 81920  | 0.3981          | 0.9117   | 0.9113 | 0.9114    | 0.9117 |
 | 0.1472        | 5.0   | 102400 | 0.4033          | 0.9137   | 0.9135 | 0.9134    | 0.9137 |
 
+### Model performances
+
+-|precision|recall|f1|support
+-|-|-|-|-
+Sports|0.97|0.98|0.97|6400
+Arts, Culture, and Entertainment|0.94|0.95|0.94|6400
+Business and Finance|0.85|0.84|0.84|6400
+Health and Wellness|0.90|0.93|0.91|6400
+Lifestyle and Fashion|0.95|0.95|0.95|6400
+Science and Technology|0.89|0.83|0.86|6400
+Politics|0.93|0.88|0.90|6400
+Crime|0.85|0.93|0.89|6400
+ | | | |
+accuracy|||0.91|51200
+macro avg|0.91|0.91|0.91|51200
+weighted avg|0.91|0.91|0.91|51200
+
+### How to use roberta-base_topic_classification_nyt_news with HuggingFace
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("dstefa/roberta-base_topic_classification_nyt_news")
+model = AutoModelForSequenceClassification.from_pretrained("dstefa/roberta-base_topic_classification_nyt_news")
+pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+
+text = "Kederis proclaims innocence Olympic champion Kostas Kederis today left hospital ahead of his date with IOC inquisitors claiming his innocence and vowing."
+pipe(text)
+
+[{'label': 'Sports', 'score': 0.9989326596260071}]
+
+```
 
 ### Framework versions