abdulelahagr's picture
further fine-tuning to parent-to-kids harassment specific examples
5ca7f15 verified
metadata
license: apache-2.0
base_model: abdulelahagr/harassment_lang_classifier
tags:
  - text-classification
  - generated_from_trainer
model-index:
  - name: harssment_classifier
    results: []

harssment_classifier

This model is a fine-tuned version of abdulelahagr/harassment_lang_classifier on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0014

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
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.1539 1.0 33 0.0038
0.0338 2.0 66 0.1293
0.0371 3.0 99 0.0028
0.0372 4.0 132 0.0646
0.0245 5.0 165 0.0017

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1