danskbert_NC / README.md
yemen2016's picture
End of training
b58aa7b verified
metadata
license: cc-by-4.0
base_model: vesteinn/DanskBERT
tags:
  - generated_from_trainer
model-index:
  - name: danskbert_NC
    results: []

danskbert_NC

This model is a fine-tuned version of vesteinn/DanskBERT on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2840
  • F1-score: 0.9059

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss F1-score
No log 1.0 40 0.4096 0.7540
No log 2.0 80 0.3319 0.8725
No log 3.0 120 0.2840 0.9059
No log 4.0 160 0.3596 0.8825
No log 5.0 200 0.3770 0.8660
No log 6.0 240 0.3415 0.8923
No log 7.0 280 0.3858 0.8991
No log 8.0 320 0.4248 0.8856
No log 9.0 360 0.4699 0.8790
No log 10.0 400 0.4744 0.8856

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1