hoanghoavienvo's picture
End of training
49974c3 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-2-8
    results: []

roberta-base-detect-cheapfake-combined-train-test-contradict-2-8

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

  • Loss: 0.5226
  • Accuracy: 0.835
  • F1: 0.8156

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 1.0 163 0.7064 0.64 0.5385
No log 2.0 326 0.5252 0.765 0.7662
No log 3.0 489 0.4988 0.82 0.8269
0.1701 4.0 652 0.6552 0.77 0.7125
0.1701 5.0 815 0.5226 0.835 0.8156

Framework versions

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