Electra-base-emotion

Model description:

Model Performance Comparision on Emotion Dataset from Twitter:

Model	Accuracy	F1 Score	Test Sample per Second
Distilbert-base-uncased-emotion	93.8	93.79	398.69
Bert-base-uncased-emotion	94.05	94.06	190.152
Roberta-base-emotion	93.95	93.97	195.639
Albert-base-v2-emotion	93.6	93.65	182.794
Electra-base-emotion	91.95	91.90	472.72

How to Use the model:

from transformers import pipeline
classifier = pipeline("text-classification",model='bhadresh-savani/electra-base-emotion', return_all_scores=True)
prediction = classifier("I love using transformers. The best part is wide range of support and its easy to use", )
print(prediction)

"""
Output:
[[
{'label': 'sadness', 'score': 0.0006792712374590337}, 
{'label': 'joy', 'score': 0.9959300756454468}, 
{'label': 'love', 'score': 0.0009452480007894337}, 
{'label': 'anger', 'score': 0.0018055217806249857}, 
{'label': 'fear', 'score': 0.00041110432357527316}, 
{'label': 'surprise', 'score': 0.0002288572577526793}
]]
"""

Dataset:

Twitter-Sentiment-Analysis.

Training procedure

Colab Notebook

Eval results

{
 'epoch': 8.0,
 'eval_accuracy': 0.9195,
 'eval_f1': 0.918975455617076,
 'eval_loss': 0.3486028015613556,
 'eval_runtime': 4.2308,
 'eval_samples_per_second': 472.726,
 'eval_steps_per_second': 7.564
 }

Reference:

• Natural Language Processing with Transformer By Lewis Tunstall, Leandro von Werra, Thomas Wolf