CoolFace
Modelpublic

Realgon/N_roberta_imdb_padding0model

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes13downloads
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. -->

Nrobertaimdb_padding0model

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

  • Loss: 0.5120
  • Accuracy: 0.9528

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: 20

Training results

Training LossEpochStepValidation LossAccuracy
0.20591.015630.19260.9406
0.16632.031260.16610.9497
0.10243.046890.22610.9503
0.06914.062520.26160.9494
0.0435.078150.35410.9466
0.04316.093780.30300.9522
0.02477.0109410.35010.9482
0.02998.0125040.37230.9478
0.029.0140670.35300.9496
0.020410.0156300.38360.9458
0.014411.0171930.34710.9505
0.009512.0187560.36960.9504
0.008713.0203190.38770.9487
0.007814.0218820.44870.9504
0.005615.0234450.46570.9512
0.003216.0250080.50040.9502
0.004117.0265710.48630.9525
0.003618.0281340.48330.9516
0.019.0296970.50140.9523
0.000120.0312600.51200.9528

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3