tobijen's picture
Training in progress epoch 5
69e1123
metadata
license: apache-2.0
base_model: distilgpt2
tags:
  - generated_from_keras_callback
model-index:
  - name: tobijen/distilgpt2_right_headings
    results: []

tobijen/distilgpt2_right_headings

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 2.5151
  • Validation Loss: 7.3029
  • Epoch: 5

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 Validation Loss Epoch
2.8208 6.9815 0
2.7172 7.0894 1
2.6835 7.1183 2
2.6252 7.2063 3
2.5612 7.2448 4
2.5151 7.3029 5

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.13.1
  • Tokenizers 0.13.3