joe5campbell's picture
add model
8af918e
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: Horovod_Tweet_Sentiment_1k_3eps
    results: []

Horovod_Tweet_Sentiment_1k_3eps

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: 0.6961535
  • Train Accuracy: 0.49375
  • Validation Loss: 0.6676211
  • Validation Accuracy: 0.64375
  • 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', 'clipnorm': 1.0, 'learning_rate': 0.0003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train Accuracy Validation Loss Validation Accuracy Epoch
0.717013 0.46562502 0.73462963 0.515625 0
0.70586157 0.5078125 0.6937375 0.484375 1
0.6961535 0.49375 0.6676211 0.64375 2

Framework versions

  • Transformers 4.17.0
  • TensorFlow 2.6.0
  • Tokenizers 0.11.6