Minata's picture
update model card README.md
2b9dc66
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: plbart-base-finetuned-detection-bad-good-ut
    results: []

plbart-base-finetuned-detection-bad-good-ut

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

  • Loss: 0.3264
  • Accuracy: 0.826

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6958 0.09 100 0.7097 0.532
0.6358 0.18 200 0.4519 0.759
0.4083 0.27 300 0.3793 0.789
0.3863 0.36 400 0.3827 0.797
0.3581 0.44 500 0.3392 0.81
0.3395 0.53 600 0.3546 0.8
0.3336 0.62 700 0.3297 0.827
0.353 0.71 800 0.3645 0.803
0.3628 0.8 900 0.3400 0.824
0.3227 0.89 1000 0.3264 0.826
0.3521 0.98 1100 0.3227 0.823
0.3556 1.07 1200 0.3211 0.821
0.3243 1.16 1300 0.3296 0.812
0.3201 1.24 1400 0.3395 0.832
0.3127 1.33 1500 0.3365 0.83
0.3267 1.42 1600 0.3376 0.828
0.3046 1.51 1700 0.3316 0.82
0.2903 1.6 1800 0.3418 0.835
0.3062 1.69 1900 0.3300 0.84
0.3034 1.78 2000 0.3327 0.838
0.2828 1.87 2100 0.3342 0.825
0.3119 1.96 2200 0.3319 0.833

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.10.0
  • Tokenizers 0.13.2