CoolFace
Modelpublic

yemen2016/Arabic-MARBERT-dialect-Identification-City-Model

sourceHugging Faceupdated 2y 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. -->

Arabic-MARBERT-dialect-Identification-City-Model

This model is a fine-tuned version of Ammar-alhaj-ali/arabic-MARBERT-dialect-identification-city on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.8911
  • —F1-score: 0.5786

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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossF1-score
No log1.04421.59550.4477
1.89112.08841.60040.5083
1.30563.013261.53840.5537
0.9894.017681.75600.5450
0.75265.022101.80350.5572
0.57656.026521.89530.5764
0.47997.030942.30150.5486
0.36298.035362.73640.5368
0.36299.039782.84160.5442
0.27710.044202.89110.5786
0.219611.048623.27720.5304
0.165612.053043.12060.5394
0.155513.057463.46000.5447
0.131514.061883.43780.5445
0.103915.066303.52470.5409
0.079616.070723.63590.5419
0.068317.075143.67230.5339
0.068318.079563.68080.5435
0.056719.083983.76770.5307
0.038220.088403.81210.5306

Framework versions

  • —Transformers 4.40.0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.19.0
  • —Tokenizers 0.19.1