raygx's picture
Finetuned raygx/GPT2-Nepali-Casual-LM model for generating Covid-News; 10 Epochs
5bf5ede
|
raw
history blame
1.6 kB
metadata
tags:
  - generated_from_keras_callback
model-index:
  - name: Covid-News-Headline-Generator
    results: []

Covid-News-Headline-Generator

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 6.2848
  • Validation Loss: 6.4997
  • 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
7.9127 7.4885 0
7.2651 7.2848 1
7.0688 7.1212 2
6.9180 6.9791 3
6.7836 6.8700 4
6.6663 6.7885 5
6.5613 6.7219 6
6.4627 6.6263 7
6.3710 6.5719 8
6.2848 6.4997 9

Framework versions

  • Transformers 4.28.1
  • TensorFlow 2.11.0
  • Datasets 2.1.0
  • Tokenizers 0.13.3