metadata

license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: ukzash1/bert_fineTuned
    results:
      - task:
          type: sequence-classification
        dataset:
          name: glue
          type: cola
        metrics:
          - name: Validation Accuracy
            type: Accuracy
            value: 0.8207
        source:
          name: Hugging Face Model Hub
          url: https://huggingface.co/ukzash1/bert_fineTuned
widget:
  - text: I liked this movie
    output:
      - label: Acceptable
        score: 0.8
      - label: Not Acceptable
        score: 0.2
  - text: This not is bad
    output:
      - label: Acceptable
        score: 0.2
      - label: Not Acceptable
        score: 0.8
library_name: transformers
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-classification

ukzash1/bert_fineTuned

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

Train Loss: 0.3426
Train Accuracy: 0.8555
Validation Loss: 0.4083
Validation Accuracy: 0.8198
Epoch: 1

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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.5409	0.7317	0.5398	0.7756	0
0.3426	0.8555	0.4083	0.8198	1

Framework versions

Transformers 4.38.2
TensorFlow 2.13.0
Datasets 2.20.0
Tokenizers 0.15.2