Edit model card

distilbert-scam-classification-fine-tuned-elder

This model is a fine-tuned version of BothBosu/distilbert-scam-classification-v1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6626
  • Accuracy: 0.925
  • Precision: 0.8889
  • Recall: 0.9412
  • F1: 0.9143

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: 0.004
  • train_batch_size: 64
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.0 6.6667 20 1.8102 0.9 0.8421 0.9412 0.8889
0.0 13.3333 40 1.7751 0.9 0.8421 0.9412 0.8889
0.0 20.0 60 1.7390 0.9 0.8421 0.9412 0.8889
0.0 26.6667 80 1.7140 0.925 0.8889 0.9412 0.9143
0.0 33.3333 100 1.7016 0.925 0.8889 0.9412 0.9143
0.0 40.0 120 1.6990 0.925 0.8889 0.9412 0.9143
0.0 46.6667 140 1.6819 0.925 0.8889 0.9412 0.9143
0.0 53.3333 160 1.6602 0.925 0.8889 0.9412 0.9143
0.0 60.0 180 1.6626 0.925 0.8889 0.9412 0.9143
0.0 66.6667 200 1.6626 0.925 0.8889 0.9412 0.9143

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
5
Safetensors
Model size
67M params
Tensor type
F32
·

Finetuned from