YuvarajK-g25ait2054/distilbert-goodreads-genres

DistilBERT Goodreads Genre Classification

Model Details

Developed by: Yuvaraj K
Model type: DistilBERT for Sequence Classification
Language: English
Finetuned from: distilbert-base-cased
Training platform: Kaggle GPU
Experiment tracking: Weights & Biases

Model Description

This model is a fine-tuned DistilBERT transformer model for classifying Goodreads book reviews into genre categories.

The model was trained as part of an MLOps assignment to demonstrate an end-to-end machine learning workflow including:

• Kaggle GPU training
• experiment tracking with Weights & Biases
• model versioning with Hugging Face Hub
• reproducible project management with GitHub

DistilBERT was selected because it is lightweight, faster than full BERT, and suitable for free GPU environments while maintaining strong classification performance.

---

Training Results

Metric	Score
Accuracy	0.7950
F1 Score	0.7957
Eval Loss	1.1663

---

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "YuvarajK-g25ait2054/distilbert-goodreads-genres"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "This book was amazing and full of suspense."

inputs = tokenizer(text, return_tensors="pt", truncation=True)

outputs = model(**inputs)
prediction = torch.argmax(outputs.logits, dim=1)

print(prediction)

---

Training Configuration

• Epochs: 3
• Batch Size: 16
• Learning Rate: 3e-5
• Weight Decay: 0.01
• Warmup Steps: 100

---

Intended Use

This model is intended for educational demonstration of MLOps workflows and text classification tasks.

---

Limitations

• Trained on a limited assignment dataset
• Performance may vary on unseen review domains
• Not intended for production deployment without further validation