Electra-base-emotion
Model description:
Model Performance Comparision on Emotion Dataset from Twitter:
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: