gpt2-wikitext2 / README.md
who-does's picture
End of training
d1ae993 verified
metadata
license: mit
base_model: gpt2
tags:
  - generated_from_trainer
model-index:
  - name: gpt2-wikitext2
    results: []

gpt2-wikitext2

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

  • Loss: 6.3155

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
6.768 1.0 1125 6.6438
6.413 2.0 2250 6.3919
6.2563 3.0 3375 6.3155

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.17.1
  • Tokenizers 0.15.2