CoolFace
Modelpublic

jcunado/MiniLMv2-tagalog-fake-news

sourceHugging Faceupdated 1y 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. -->

results

This model is a fine-tuned version of nreimers/MiniLMv2-L6-H384-distilled-from-BERT-base on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2621
  • —F1: 0.9187
  • —Accuracy: 0.9189

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: 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: 50

Training results

Training LossEpochStepValidation LossF1Accuracy
No log1.0710.39620.86050.8607
0.50142.01420.28930.88310.8836
0.29463.02130.24240.89590.8960
0.29464.02840.21770.90220.9023
0.20425.03550.20530.93140.9314
0.17176.04260.18650.92720.9272
0.17177.04970.26210.91870.9189

Framework versions

  • —Transformers 4.52.4
  • —Pytorch 2.6.0+cu124
  • —Datasets 4.0.0
  • —Tokenizers 0.21.2