CoolFace
Modelpublic

NasimB/cbt-raqrity-log-rarity-no-cut

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes28downloads
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-raqrity-log-rarity-no-cut

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

  • —Loss: 4.1043

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
6.34080.295005.3424
5.030.5810004.9271
4.70510.8715004.6877
4.43981.1720004.5455
4.30081.4625004.4279
4.19491.7530004.3274
4.06822.0435004.2525
3.88582.3340004.2063
3.86892.6245004.1532
3.82392.9150004.1073
3.6343.2155004.0988
3.58163.560004.0685
3.57143.7965004.0351
3.48164.0870004.0318
3.31564.3775004.0283
3.30814.6680004.0139
3.30034.9585004.0043
3.15215.2490004.0154
3.13485.5495004.0132
3.1295.83100004.0129

Framework versions

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