CoolFace
Modelpublic

ekiprop/SST-2-GLoRA-p40-seed63

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes3downloads
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. -->

SST-2-GLoRA-p40-seed63

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

  • —Loss: 0.1909
  • —Accuracy: 0.9392

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: 0.0003
  • —trainbatchsize: 32
  • —evalbatchsize: 32
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 1

Training results

Training LossEpochStepValidation LossAccuracy
0.38380.09502000.22850.9197
0.29470.19004000.21160.9266
0.260.28506000.20000.9232
0.23740.38008000.22640.9323
0.23510.475110000.21880.9243
0.22490.570112000.21030.9346
0.22710.665114000.19820.9300
0.22470.760116000.19560.9312
0.2220.855118000.19090.9392
0.20450.950120000.18810.9392

Framework versions

  • —PEFT 0.16.0
  • —Transformers 4.54.1
  • —Pytorch 2.5.1+cu121
  • —Datasets 4.0.0
  • —Tokenizers 0.21.4