CoolFace
Modelpublic

votaquangnhat/vietnamese-poem-hustgpt2-namchu

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes27downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

vietnamese-poem-hustgpt2-namchu

This model is a fine-tuned version of NlpHUST/gpt2-vietnamese on phamson02/vietnamese-poetry-corpus. It achieves the following results on the evaluation set:

  • —Loss: 3.6570

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
3.86771.020373.8531
3.75342.040743.7680
3.68823.061113.7256
3.62294.081483.7001
3.56615.0101853.6829
3.55356.0122223.6715
3.51467.0142593.6635
3.5058.0162963.6602
3.49339.0183333.6578
3.462810.0203703.6570

Framework versions

  • —Transformers 4.47.1
  • —Pytorch 2.5.1+cu121
  • —Tokenizers 0.21.0