CoolFace
Modelpublic

NereuS28/BERT1bert-base-uncased-finetuned-cola

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes12downloads
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. -->

BERT1bert-base-uncased-finetuned-cola

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

  • —Loss: 0.9198
  • —Matthews Correlation: 0.6092

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: 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 LossEpochStepValidation LossMatthews Correlation
0.52071.05350.42040.5622
0.33622.010700.47680.5804
0.2113.016050.56270.5963
0.16564.021400.75330.5867
0.1165.026750.95140.5806
0.07646.032100.91980.6092
0.06357.037451.19090.5449
0.04168.042801.16070.5743
0.0329.048151.30350.5756
0.014310.053501.30990.5887

Framework versions

  • —Transformers 4.40.2
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1