CoolFace
Modelpublic

tuskbyte/yes_no_model

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes4downloads
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. -->

yesnomodel

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

  • —Loss: 0.0000

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: 5e-05
  • —trainbatchsize: 20
  • —evalbatchsize: 20
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 50
  • —num_epochs: 3

Training results

Training LossEpochStepValidation Loss
6.47780.2857105.2663
2.95440.5714201.8252
1.2670.8571300.7955
0.72491.1429400.3101
0.30311.4286500.0483
0.06061.7143600.0010
0.00492.0700.0001
0.00142.2857800.0001
0.00052.5714900.0000
0.00082.85711000.0000

Framework versions

  • —Transformers 4.41.2
  • —Pytorch 2.1.2
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1