DeBERTa-v3-XSmall Sentiment Analysis Model

Model Overview

This model is a fine-tuned version of agentlans/deberta-v3-xsmall-zyda-2 optimized for sentiment analysis on Twitter data. It achieves the following results on the evaluation set:

• Loss: 0.0656
• MSE: 0.0656

Dataset

The model was trained on the Twitter Sentiment Meta-Analysis Dataset.

Dataset Description

This dataset contains sentiment analysis results for English tweets collected between September 2009 and January 2010. The tweets were processed and analyzed using 10 different sentiment classifiers, with the final sentiment score derived from principal component analysis (PCA).

• Source: Cheng-Caverlee-Lee Twitter Scrape (Sept 2009 - Jan 2010)
• Size: 138,690 tweets
• Language: English only (filtered using langdetect)

Usage

Here's an example of how to use the model for sentiment prediction:

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Load model and tokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_name = "agentlans/deberta-v3-xsmall-zyda-2-sentiment"
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=1).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Function to perform inference
def predict_score(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True).to(device)
    with torch.no_grad():
        logits = model(**inputs).logits
    return logits.item()

# Example usage
input_text = "I accidentally the whole thing. Is that bad?"
score = predict_score(input_text)
print(f"Predicted score: {score}")

Example Outputs

Training Procedure

Hyperparameters

• Learning rate: 5e-05
• Train batch size: 64
• Eval batch size: 8
• Seed: 42
• Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
• LR scheduler: Linear
• Number of epochs: 3.0

Training Results

Framework Versions

• Transformers: 4.46.3
• PyTorch: 2.5.1+cu124
• Datasets: 3.1.0
• Tokenizers: 0.20.3