CoolFace
Modelpublic

NasimB/qed-log-rarity-seed

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes11downloads
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. -->

qed-log-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: 4.1244

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
6.35250.295005.3404
5.04840.5810004.9249
4.70920.8815004.6891
4.46581.1720004.5610
4.31161.4625004.4365
4.21671.7530004.3382
4.0922.0435004.2635
3.91842.3440004.2181
3.88632.6345004.1659
3.85032.9250004.1157
3.66383.2155004.1080
3.6093.560004.0860
3.5933.865004.0527
3.49934.0970004.0485
3.34134.3875004.0433
3.33094.6780004.0289
3.32344.9685004.0165
3.17895.2690004.0305
3.15525.5595004.0301
3.15295.84100004.0296

Framework versions

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