CoolFace
Modelpublic

Zagusan/Wikibot-3001

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes12downloads
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. -->

Wikibot-3001

This model is a fine-tuned version of gpt2 on the mapama247/wikihow_es dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9422

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: 16
  • evalbatchsize: 32
  • seed: 42
  • distributed_type: tpu
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lrschedulertype: linear
  • num_epochs: 12

Training results

Training LossEpochStepValidation Loss
2.74321.059502.6109
2.35562.0119002.3059
2.18723.0178502.1738
2.08914.0238002.0990
2.03065.0297502.0579
1.99756.0357002.0395
1.99097.059502.0208
1.89248.0119001.9678
1.82819.0178501.9422
1.837610.059501.9576
1.780211.0119001.9212
1.746512.0178501.8996

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3