nbbert_NCS / README.md
yemen2016's picture
End of training
d28cc1a verified
|
raw
history blame
1.89 kB
metadata
license: cc-by-4.0
base_model: NbAiLab/nb-bert-base
tags:
  - generated_from_trainer
model-index:
  - name: nbbert_NCS
    results: []

nbbert_NCS

This model is a fine-tuned version of NbAiLab/nb-bert-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4645
  • F1-score: 0.7958

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
0.5085 1.0 504 0.4645 0.7958
0.4027 2.0 1008 0.4524 0.7897
0.2655 3.0 1512 0.5993 0.7929
0.1758 4.0 2016 0.8533 0.7890
0.1048 5.0 2520 1.0830 0.7757
0.0536 6.0 3024 1.2138 0.7876
0.0438 7.0 3528 1.3657 0.7818
0.0162 8.0 4032 1.4657 0.7843
0.0151 9.0 4536 1.5118 0.7850
0.0086 10.0 5040 1.5580 0.7814

Framework versions

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