README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - sms_spam
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert-base-uncased-finetuned-spam
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: sms_spam
          type: sms_spam
          config: plain_text
          split: train
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9883408071748879
          - name: F1
            type: f1
            value: 0.9882535196626446

distilbert-base-uncased-finetuned-spam

This model is a fine-tuned version of distilbert-base-uncased on the sms_spam dataset. It achieves the following results on the evaluation set:

• Loss: 0.0370
• Accuracy: 0.9883
• F1: 0.9883

Model description

More information needed

Label Key

• LABEL_1 = SPAM
• LABEL_0 = HAM

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.174	1.0	70	0.0444	0.9865	0.9866
0.0303	2.0	140	0.0370	0.9883	0.9883

Framework versions

• Transformers 4.27.1
• Pytorch 2.0.0
• Datasets 2.10.1
• Tokenizers 0.13.2