hoanghoavienvo's picture
End of training
aee813d verified
metadata
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: roberta-base-detect-cheapfake-combined-train-test-contradict-5-5
    results: []

roberta-base-detect-cheapfake-combined-train-test-contradict-5-5

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4564
  • Accuracy: 0.87
  • F1: 0.8550

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-06
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.0 172 0.4396 0.8133 0.7565
No log 2.0 344 0.3395 0.8567 0.8401
0.1806 3.0 516 0.4137 0.8633 0.8417
0.1806 4.0 688 0.4293 0.8633 0.8441
0.1806 5.0 860 0.4564 0.87 0.8550

Framework versions

  • Transformers 4.37.0
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.1