franfj's picture
End of training
78d73c4
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: media-bias-ukraine-dataset-all-minus-ukraine-removed
    results: []

media-bias-ukraine-dataset-all-minus-ukraine-removed

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

  • Loss: 2.9273
  • F1: 0.2174

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: 2e-05
  • 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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss F1
0.0857 1.0 138 2.3587 0.1003
0.003 2.0 276 2.6847 0.0840
0.0167 3.0 414 2.8767 0.1619
0.0022 4.0 552 2.3012 0.1862
0.0019 5.0 690 2.7714 0.1961
0.001 6.0 828 2.7623 0.2015
0.6706 7.0 966 2.8243 0.1980
0.2259 8.0 1104 2.7106 0.2151
0.0013 9.0 1242 2.9273 0.2174
0.0116 10.0 1380 2.9458 0.2101

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1
  • Datasets 2.10.1
  • Tokenizers 0.13.2