JasperGrant's picture
Upload TFBertForMaskedLM
e887a36 verified
metadata
base_model: microsoft/graphcodebert-base
tags:
  - generated_from_keras_callback
model-index:
  - name: ASTBERT
    results: []

ASTBERT

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

  • Train Loss: 0.0535
  • Train Accuracy: 0.9866
  • Epoch: 9

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': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train Accuracy Epoch
0.3447 0.9442 0
0.2808 0.9495 1
0.2292 0.9551 2
0.1844 0.9609 3
0.1434 0.9676 4
0.1121 0.9735 5
0.0891 0.9784 6
0.0741 0.9819 7
0.0625 0.9845 8
0.0535 0.9866 9

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.10.0
  • Datasets 2.18.0
  • Tokenizers 0.13.3