arincon's picture
arincon/ia-detection-tiny-random-gptj
2c40f8a
metadata
tags:
  - generated_from_trainer
datasets:
  - autextification2023
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: ia-detection-tiny-random-gptj
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: autextification2023
          type: autextification2023
          config: detection_en
          split: train
          args: detection_en
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.633198973983144
          - name: F1
            type: f1
            value: 0.7005683517798384
          - name: Precision
            type: precision
            value: 0.6022888003086023
          - name: Recall
            type: recall
            value: 0.8371760500446828

ia-detection-tiny-random-gptj

This model is a fine-tuned version of ydshieh/tiny-random-gptj-for-sequence-classification on the autextification2023 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7313
  • Accuracy: 0.6332
  • F1: 0.7006
  • Precision: 0.6023
  • Recall: 0.8372

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.6038 1.0 3808 0.5362 0.7309 0.7270 0.7294 0.7246
0.5303 2.0 7616 0.5109 0.7465 0.7358 0.7592 0.7139
0.4588 3.0 11424 0.5258 0.7424 0.7568 0.7097 0.8106
0.4459 4.0 15232 0.5137 0.7477 0.7428 0.7491 0.7366
0.3586 5.0 19040 0.5062 0.7572 0.7452 0.7745 0.7180
0.4072 6.0 22848 0.5264 0.7539 0.7565 0.7407 0.7730

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.13.3