README.md

metadata

datasets:
  - amazon_polarity
base_model: prajjwal1/bert-tiny
model-index:
  - name: amazon_polarity
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: amazon_polarity
          type: sentiment
          args: default
        metrics:
          - type: accuracy
            value: 0.942
            name: Accuracy
          - type: loss
            value: 0.153
            name: Loss
          - type: f1
            value: 0.94
            name: F1

tinybert-sentiment-amazon

This model is a fine-tuned version of bert-tiny on amazon-polarity dataset. It achieves the following results on the evaluation set:

• Loss: 0.153
• Accuracy: 0.942
• F1_score: 0.940

Model description

TinyBERT is 7.5 times smaller and 9.4 times faster on inference compared to its teacher BERT model (while DistilBERT is 40% smaller and 1.6 times faster than BERT). This model was trained using the entire dataset (3.6M of samples) in constrast to the distilbert model which was trained on only 10% of the dataset.

Intended uses & limitations

While this model may not be as accurate as the distilbert model, its performance should be enough for most use cases.

from transformers import pipeline

# Create the pipeline
sentiment_classifier = pipeline('text-classification', model='AdamCodd/tinybert-sentiment-amazon')

# Now you can use the pipeline to classify emotions
result = sentiment_classifier("This product doesn't fit me at all.")
print(result)
#[{'label': 'negative', 'score': 0.9969743490219116}]

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 1270
• optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 150
• num_epochs: 1
• weight_decay: 0.01

Framework versions

• Transformers 4.35.0
• Pytorch lightning 2.1.0
• Tokenizers 0.14.1

If you want to support me, you can here.