metadata

license: apache-2.0
tags:
  - generated_from_keras_callback
base_model: distilbert-base-uncased
model-index:
  - name: Zaib/distilbert-base-uncased-finetuned-cola
    results: []

Zaib/distilbert-base-uncased-finetuned-cola

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

Train Loss: 0.5343
Validation Loss: 0.5940
Train Matthews Correlation: 0.2397
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 195, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Matthews Correlation	Epoch
0.6018	0.5886	0.0	0
0.5643	0.5950	0.0796	1
0.5343	0.5940	0.2397	2

Framework versions

Transformers 4.20.1
TensorFlow 2.8.2
Datasets 2.3.2
Tokenizers 0.12.1