CoolFace
Modelpublic

NasimB/open_subtitles-rarity-seed

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes9downloads
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. -->

open_subtitles-rarity-seed

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

  • —Loss: 4.1682

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: 0.0005
  • —trainbatchsize: 64
  • —evalbatchsize: 64
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 1000
  • —num_epochs: 6
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
6.41990.35005.3681
5.11610.6110004.9701
4.78410.9115004.7418
4.51961.2220004.5972
4.3871.5225004.4915
4.27771.8330004.3846
4.11052.1335004.3262
3.99812.4440004.2709
3.95342.7445004.2104
3.87553.0550004.1790
3.67893.3555004.1529
3.67713.6660004.1294
3.65423.9665004.0885
3.43224.2770004.1019
3.41194.5775004.0906
3.40044.8880004.0777
3.29025.1885004.0884
3.2275.4990004.0850
3.22635.7995004.0849

Framework versions

  • —Transformers 4.26.1
  • —Pytorch 1.11.0+cu113
  • —Datasets 2.13.0
  • —Tokenizers 0.13.3