CoolFace
Modelpublic

NasimB/cbt-guten-log-rarity-all-no-cut-mixed

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes21downloads
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. -->

cbt-guten-log-rarity-all-no-cut-mixed

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

  • —Loss: 4.3188

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
6.69370.295005.6332
5.34750.5810005.1998
4.99240.8715004.9522
4.72251.1720004.8038
4.5651.4625004.6827
4.44791.7530004.5721
4.33592.0435004.4944
4.13362.3340004.4442
4.10412.6245004.3954
4.0632.9150004.3376
3.87573.2155004.3348
3.80253.560004.3031
3.78863.7965004.2700
3.70124.0870004.2676
3.52184.3775004.2626
3.51664.6680004.2503
3.50124.9585004.2361
3.35765.2490004.2482
3.32655.5495004.2487
3.32295.83100004.2470

Framework versions

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