bert-base-uncased-emotion
Model description:
Bert is a Transformer Bidirectional Encoder based Architecture trained on MLM(Mask Language Modeling) objective
bert-base-uncased finetuned on the emotion dataset using HuggingFace Trainer with below training parameters
learning rate 2e-5,
batch size 64,
num_train_epochs=8,
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 |
How to Use the model:
from transformers import pipeline
classifier = pipeline("text-classification",model='bhadresh-savani/bert-base-uncased-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': 0.0005138228880241513},
{'label': 'joy', 'score': 0.9972520470619202},
{'label': 'love', 'score': 0.0007443308713845909},
{'label': 'anger', 'score': 0.0007404946954920888},
{'label': 'fear', 'score': 0.00032938539516180754},
{'label': 'surprise', 'score': 0.0004197491507511586}
]]
"""
Dataset:
Training procedure
Colab Notebook follow the above notebook by changing the model name from distilbert to bert
Eval results
{
'test_accuracy': 0.9405,
'test_f1': 0.9405920712282673,
'test_loss': 0.15769127011299133,
'test_runtime': 10.5179,
'test_samples_per_second': 190.152,
'test_steps_per_second': 3.042
}