README.md

metadata

license: mit
datasets:
  - dair-ai/emotion
language:
  - en
library_name: transformers
widget:
  - text: I am so happy with the results!
  - text: I am so pissed with the results!
tags:
  - debarta
  - debarta-xlarge
  - emotions-classifier

Emotion-X: Fine-tuned DeBERTa-Xlarge Based Emotion Detection

This is a fine-tuned version of microsoft/deberta-xlarge-mnli for emotion detection on the dair-ai/emotion dataset.

Overview

Emotion-X is a state-of-the-art emotion detection model fine-tuned from Microsoft's DeBERTa-Xlarge model. Designed to accurately classify text into one of six emotional categories, Emotion-X leverages the robust capabilities of DeBERTa and fine-tunes it on a comprehensive emotion dataset, ensuring high accuracy and reliability.

Model Details

• Model Name: AnkitAI/deberta-xlarge-base-emotions-classifier
• Base Model: microsoft/deberta-xlarge-mnli
• Dataset: dair-ai/emotion
• Fine-tuning: This model was fine-tuned for emotion detection with a classification head for six emotional categories (anger, disgust, fear, joy, sadness, surprise).

Training

The model was trained using the following parameters:

• Learning Rate: 2e-5
• Batch Size: 4
• Weight Decay: 0.01
• Evaluation Strategy: Epoch

Training Details

• Evaluation Loss: 0.0858
• Evaluation Runtime: 110070.6349 seconds
• Evaluation Samples/Second: 78.495
• Evaluation Steps/Second: 2.453
• Training Loss: 0.1049
• Evaluation Accuracy: 94.6%
• Evaluation Precision: 94.8%
• Evaluation Recall: 94.5%
• Evaluation F1 Score: 94.7%

Usage

You can use this model directly with the Hugging Face transformers library:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name = "AnkitAI/deberta-xlarge-base-emotions-classifier"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Example usage
def predict_emotion(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
    outputs = model(**inputs)
    logits = outputs.logits
    predictions = logits.argmax(dim=1)
    return predictions

text = "I'm so happy with the results!"
emotion = predict_emotion(text)
print("Detected Emotion:", emotion)

Emotion Labels

• Anger
• Disgust
• Fear
• Joy
• Sadness
• Surprise

Model Card Data

Parameter	Value
Model Name	microsoft/deberta-xlarge-mnli
Training Dataset	dair-ai/emotion
Learning Rate	2e-5
Per Device Train Batch Size	4
Evaluation Strategy	Epoch
Best Model Accuracy	94.6%

License

This model is licensed under the MIT License.