fine-tuned-sentiment-model

Model Details

• Base Model: distilbert-base-uncased
• Task: Text Classification (Sentiment Analysis)
• Dataset: stanfordnlp/imdb
• Fine-tuning Method: Full Fine-tuning
• Training samples: 5000
• Epochs: 3
• Batch Size: 8
• Learning Rate: {LEARNING_RATE}

Model Description

<!-- Provide a longer summary of what this model is. -->

Fine-tuned distilbert-base-uncased for Sentiment Analysis

This model is a fine-tuned version of distilbert-base-uncased on the stanfordnlp/imdb dataset.

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch

Load model and tokenizer

tokenizer = AutoTokenizer.from_pretrained("{HF_REPO_NAME}") model = AutoModelForSequenceClassification.from_pretrained("{HF_REPO_NAME}")

Example usage

text = "This movie is amazing! I really enjoyed watching it." inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)

with torch.no_grad(): outputs = model(**inputs) predictions = torch.nn.functional.softmax(outputs.logits, dim=-1) predicted_class = torch.argmax(predictions, dim=-1).item() confidence = torch.max(predictions).item()

0 = negative, 1 = positive

sentiment = "positive" if predicted_class == 1 else "negative" print(f"Sentiment: {{sentiment}} (confidence: {{confidence:.3f}})")

Training Details

• Optimizer: AdamW

• Weight Decay: 0.01

• Warmup Steps: 500

• Mixed Precision: {"Enabled" if torch.cuda.is_available() else "Disabled"}

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

• https://huggingface.co/datasets/stanfordnlp/imdb

Intended Use

This model is intended for sentiment analysis of English text. It classifies text into two categories:

• 0: Negative sentiment

• 1: Positive sentiment

Limitations

• Trained primarily on movie reviews → may not generalize to other domains

• Weak on neutral/mixed sentiment

• Designed for English text only

Training Infrastructure

• Platform: Google Colab

• GPU: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else "CPU"}

• Framework: PyTorch + Transformers

Summary

============================================================ FINE-TUNING COMPLETED SUCCESSFULLY!

Training Summary:

• Model: distilbert-base-uncased
• Task: classification
• Method: Full Fine-tuning
• Dataset: stanfordnlp/imdb
• Training samples: 5000
• Epochs: 3
• Batch size: 8

Your Model:

• Repository: imrgurmeet/fine-tuned-sentiment-model
• URL: https://huggingface.co/imrgurmeet/fine-tuned-sentiment-model
• Local path: ./fine-tuned-model

Next Steps:

1. Test your model on new data
2. Share it with the community
3. Use it in your applications
4. Continue fine-tuning if needed

Usage in your code:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("imrgurmeet/fine-tuned-sentiment-model") model = AutoModelForSequenceClassification.from_pretrained("imrgurmeet/fine-tuned-sentiment-model")

text = "Your text here" inputs = tokenizer(text, return_tensors="pt") outputs = model(**inputs) prediction = torch.nn.functional.softmax(outputs.logits, dim=-1)

============================================================ Happy fine-tuning! Your model is ready to use!

COMPLETE INFERENCE CODE FOR FINE-TUNED MODEL

• SIMPLE VERSION:

  from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch

• Load once

  tokenizer = AutoTokenizer.from_pretrained("imrgurmeet/fine-tuned-sentiment-model") model = AutoModelForSequenceClassification.from_pretrained("imrgurmeet/fine-tuned-sentiment-model")

• Use anywhere:

  def analyze(text): inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True) with torch.no_grad(): outputs = model(**inputs) prediction = torch.argmax(outputs.logits, dim=-1).item() return "positive" if prediction == 1 else "negative"

• Test it:

  print(analyze("I love this!")) # positive print(analyze("This is terrible!")) # negative print(analyze("It's okay")) # positive or negative