CoolFace
Modelpublic

sarasarasara/albert-fa-zwnj-base-v2-finetuned-bmd-20241021-LOSO-section-out1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes5downloads
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. -->

albert-fa-zwnj-base-v2-finetuned-bmd-20241021-LOSO-section-out1

This model is a fine-tuned version of HooshvareLab/albert-fa-zwnj-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 3.1964
  • —Accuracy: 0.3103
  • —F1: 0.2745

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
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossAccuracyF1
1.13841.0141.24940.34480.1768
1.13132.0281.09230.31030.1724
0.93493.0421.24560.34480.2468
0.61094.0561.32960.20690.1970
0.32135.0701.48080.37930.3711
0.12126.0841.94440.24140.2352
0.04067.0982.66960.41380.3814
0.02398.01122.62790.27590.2705
0.0059.01263.09410.31030.2745
0.004110.01403.19640.31030.2745

Framework versions

  • —Transformers 4.45.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.20.1