Edit model card

guma/distilgpt2-finetuned-shakespeare

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

  • Train Loss: 3.1769
  • Validation Loss: 3.5116
  • Epoch: 19

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
4.2136 3.8303 0
3.8997 3.6993 1
3.7790 3.6344 2
3.7061 3.5923 3
3.6476 3.5653 4
3.6003 3.5513 5
3.5578 3.5360 6
3.5204 3.5277 7
3.4843 3.5171 8
3.4514 3.5117 9
3.4194 3.5048 10
3.3903 3.5040 11
3.3627 3.5006 12
3.3332 3.5006 13
3.3052 3.5019 14
3.2772 3.5051 15
3.2514 3.5043 16
3.2249 3.5026 17
3.2019 3.5129 18
3.1769 3.5116 19

Framework versions

  • Transformers 4.22.2
  • TensorFlow 2.8.2
  • Datasets 2.5.2
  • Tokenizers 0.12.1
Downloads last month
4
Inference API
This model can be loaded on Inference API (serverless).