bert-swe-skills-ner / README.md
RJuro's picture
update model card README.md
6d8b52d
|
raw
history blame
1.29 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: bert-swe-skills-ner
    results: []

bert-swe-skills-ner

This model is a fine-tuned version of KB/bert-base-swedish-cased on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.0410
  • eval_precision: 0.7989
  • eval_recall: 0.8142
  • eval_f1: 0.8065
  • eval_accuracy: 0.9856
  • eval_runtime: 2.9896
  • eval_samples_per_second: 101.352
  • eval_steps_per_second: 12.711
  • epoch: 5.0
  • step: 190

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: 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: 10

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3