CoolFace
Modelpublic

Mahmoud22/All-Train-data-F1

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes10downloads
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. -->

res

This model is a fine-tuned version of salti/AraElectra-base-finetuned-ARCD on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1732
  • —F1-macro: 0.6754

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: 8e-05
  • —trainbatchsize: 40
  • —evalbatchsize: 80
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 7
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossF1-macro
No log1.02290.51440.2375
No log2.04580.29740.3838
0.71753.06870.22680.6071
0.71754.09160.22060.5803
0.25365.011450.18160.6773
0.25366.013740.17130.6893
0.19327.016030.16950.6832

Framework versions

  • —Transformers 4.26.1
  • —Pytorch 1.13.0
  • —Datasets 2.1.0
  • —Tokenizers 0.13.2