mrm8488/bert-tiny-finetuned-enron-spam-detection

BERT-Tiny fine-tuned on Enron Spam Detection

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 (aka BERT-Tiny) on an SetFit/enron_spam for Spam Dectection downstream task.

It achieves the following results on the evaluation set:

• Loss: 0.0593
• Precision: 0.9851
• Recall: 0.9871
• Accuracy: 0.986
• F1: 0.9861

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	Accuracy	F1
0.1125	1.0	1983	0.0797	0.9839	0.9692	0.9765	0.9765
0.061	2.0	3966	0.0618	0.9822	0.9861	0.984	0.9842
0.0486	3.0	5949	0.0593	0.9851	0.9871	0.986	0.9861
0.048	4.0	7932	0.0588	0.9870	0.9821	0.9845	0.9846

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.1