Update README.md

README.md

@@ -35,17 +35,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-cased-finetuned
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the https://huggingface.co/datasets/cmunhozc/usa_news_en train dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the [usa_news_en train dataset](https://huggingface.co/datasets/cmunhozc/usa_news_en).
 It achieves the following results on the evaluation set:
 - Loss: 0.0900
 - Accuracy: 0.9800
 
 ## Model description
  
-The fine-tuned model corresponds to a binary classification model that determines whether two English news headlines are related or not related. In the following paper *{News Gathering: Leveraging Transformers to
-Rank News}* it can find more details. To utilize the fine-tuned model, you can follow the steps outlined below:
+The fine-tuned model corresponds to a binary classification model that determines whether two English news headlines are related or not related. In the following paper **{News Gathering: Leveraging Transformers to
+Rank News}** it can find more details. To utilize the fine-tuned model, you can follow the steps outlined below:
 
-``` 
+```python 
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 from transformers import Trainer
 
@@ -55,6 +55,8 @@ model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 ### 2. Dataset:
+def preprocess_fctn(examples):
+  return tokenizer(examples["sentence1"], examples["sentence2"], truncation=True)
 ...
 encoded_dataset = dataset.map(preprocess_fctn, batched=True, load_from_cache_file=False)
 ...
@@ -75,7 +77,7 @@ predictions = trainer_hf.predict(encoded_dataset["validation"])
 acc_val  = metric.compute(predictions=np.argmax(predictions.predictions,axis=1).tolist(), references=predictions.label_ids)['accuracy']
 ```
 Finally, with the classification above model, you can follow the steps below to generate the news ranking.
-- For each news article in the https://huggingface.co/datasets/cmunhozc/google_news_en dataset positioned as the first element in a pair, retrieve all corresponding pairs from the dataset.
+- For each news article in the [google_news_en train dataset](https://huggingface.co/datasets/cmunhozc/google_news_en) dataset positioned as the first element in a pair, retrieve all corresponding pairs from the dataset.
 - Employing pair encoders, rank the news articles that occupy the second position in each pair, determining their relevance to the first article.
 - Organize each list generated by the encoders based on the probabilities obtained for the relevance class.
 
@@ -85,7 +87,7 @@ More information needed
 
 ## Training, evaluation and test data
 
-The training data is sourced from the *train* split in https://huggingface.co/datasets/cmunhozc/usa_news_en, and a similar procedure is applied for the *validation* set. In the case of testing, the initial segment for the text classification model is derived from the *test_1* and *test_2* splits. As for the ranking model, the test dataset from https://huggingface.co/datasets/cmunhozc/google_news_en is utilized
+The training data is sourced from the *train* split in [usa_news_en train dataset](https://huggingface.co/datasets/cmunhozc/usa_news_en), and a similar procedure is applied for the *validation* set. In the case of testing, the initial segment for the text classification model is derived from the *test_1* and *test_2* splits. As for the ranking model, the test dataset from [google_news_en train dataset](https://huggingface.co/datasets/cmunhozc/google_news_en) is utilized
 
 ## Training procedure