guntaksa/AG-News-distilbert1

Model Card for Model ID

<This model is a fine-tuned version ofdistilbert-base-uncased on the AG News dataset for 4-class topic text classification. It was tracked via Weights & Biases (W&B) as part of an MLOps assignment>

Model Details

Model Description

This model is a lightweight text classifier built by fine-tuning DistilBERT. It maps input articles or paragraphs to one of four designated news categories: World, Sports, Business, or Sci/Tech.

• Developed by: Sandeep (Group 13 / IIT Jodhpur)
• Model type: Transformer-based Sequence Classification (DistilBERT)
• Language(s) (NLP): English
• License: Apache-2.0 (Inherited from base DistilBERT model)
• Finetuned from model: distilbert-base-uncased

Model Sources [optional]

• Repository: GitHub - Group13-assignment-ML-OPS
• Tracking Logs: Weights & Biases Workspace

Uses

Direct Use

This model is intended to be used directly for classifying short-to-medium length English text fragments into one of four specific categories:

• 0: World
• 1: Sports
• 2: Business
• 3: Sci/Tech

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

The model will not perform optimally on languages other than English or text tasks outside the predefined AG News categories (e.g., sentiment analysis, generation, or fine-grained entities).

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model. from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch

Define target labels

id2label = {"0": "World", "1": "Sports", "2": "Business", "3": "Sci/Tech"}

Load model and tokenizer

model_name = "your-hf-username/your-model-id" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForSequenceClassification.from_pretrained(model_name)

Sample text classification

text = "The team won the championship match in extra innings." inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=128)

with torch.no_grad(): logits = model(**inputs).logits predicted_class_id = logits.argmax().item()

print("Predicted Category:", id2label[str(predicted_class_id)])

[More Information Needed]

Training Details

Training Data

The model was trained using the dataset repository Recurrent/prepared_data_mlops2.

Train Examples: 120,000 rows

Test (Validation) Examples: 7,600 rows

Preprocessing: Inputs were tokenized and clipped to a maximum sequence length of 128 tokens. [More Information Needed]

Training Procedure

Hyperparameters The following configuration details apply to the primary model run (run-v1):

Learning Rate: 2e-5

Train Batch Size: 16

Eval Batch Size: 32

Epochs: 3

Weight Decay: 0.01

Evaluation Strategy: Evaluated at the end of every epoch

Best Model Selection: Loaded best model weights at the end based on the highest F1 score.

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

Evaluation performed on the independent evaluation split yielded the following final metrics:

Final Accuracy: 93.99%

Final F1 Score: 0.9399

Final Evaluation Loss: 0.4236 [More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: Kaggle Environment — 2x NVIDIA Tesla T4 GPUs
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]