CoolFace
Modelpublic

Realgon/left_padding10model

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes24downloads
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. -->

left_padding10model

This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:

  • Accuracy: 0.9334
  • Loss: 0.5739

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: 2e-05
  • trainbatchsize: 16
  • evalbatchsize: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lrschedulertype: linear
  • num_epochs: 10

Training results

Training LossEpochStepAccuracyValidation Loss
0.15491.015630.91980.3020
0.07782.031260.93160.2819
0.09313.046890.92550.2931
0.05384.062520.93070.3606
0.03035.078150.93140.4229
0.01066.093780.93040.5013
0.01257.0109410.93160.4994
0.01128.0125040.93290.5481
0.01299.0140670.93270.5440
0.010.0156300.93340.5739

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0+cu117
  • Datasets 2.14.6
  • Tokenizers 0.14.1