metadata

license: apache-2.0
tags:
  - generated_from_keras_callback
datasets:
  - disfl_qa
metrics:
  - validation_accuracy
model-index:
  - name: fintuned-bert-disfluency
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: disfl_qa
          type: disfl_qa
          args: disfl_qa
        metrics:
          - name: Validation Accuracy
            type: validation_accuracy
            value: 0.9795
widget:
  - text: I love football so much
    example_title: Non Disfluent
  - text: I love love football I like it
    example_title: Disfluent

fintuned-bert-disfluency

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.0814
Train Sparse Categorical Accuracy: 0.9795
Validation Loss: 0.0816
Validation Sparse Categorical Accuracy: 0.9795
Epoch: 2

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
0.1105	0.9694	0.0821	0.9800	0
0.0942	0.9759	0.0987	0.9765	1
0.0814	0.9795	0.0816	0.9795	2

Framework versions

Transformers 4.21.3
TensorFlow 2.8.2
Datasets 2.4.0
Tokenizers 0.12.1