god / README.md
dfsaab's picture
update model card README.md
0738264
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wikitext
model-index:
  - name: god
    results: []

god

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

  • eval_loss: 4.4818
  • eval_runtime: 13.363
  • eval_samples_per_second: 144.429
  • eval_steps_per_second: 18.11
  • step: 0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.0+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3