gpt2.shak / README.md
jchwenger's picture
gpt2.shak
7a69728
metadata
license: mit
base_model: gpt2
tags:
  - generated_from_trainer
datasets:
  - tiny_shakespeare
model-index:
  - name: gpt2.shak
    results: []

gpt2.shak

This model is a fine-tuned version of gpt2 on the tiny_shakespeare dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1852

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:

  • learning_rate: 3e-05
  • train_batch_size: 3
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
3.3259 1.0 98 3.2194
3.3527 2.0 196 3.2017
3.1783 3.0 294 3.1900
3.2653 4.0 392 3.1863
3.2787 5.0 490 3.1852

Framework versions

  • Transformers 4.35.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.7
  • Tokenizers 0.14.1