roberta-base_topic_classification_nyt_news

roberta-base_topic_classification_nyt_news

This model is a fine-tuned version of roberta-base on the NYT News dataset, which contains 256,000 news titles from articles published from 2000 to the present (https://www.kaggle.com/datasets/aryansingh0909/nyt-articles-21m-2000-present). It achieves the following results on the test set of 51200 cases:

• Accuracy: 0.91
• F1: 0.91
• Precision: 0.91
• Recall: 0.91

Training data

Training data was classified as follow:

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Model performance

How to use roberta-base_topic_classification_nyt_news with HuggingFace

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

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2