README.md

metadata

widget:
  - text: Felix dog i [MASK] i går.
base_model: KBLab/bert-base-swedish-cased
tags:
  - generated_from_trainer
datasets:
  - ChangeIsKey/kubhist2
metrics:
  - accuracy
model-index:
  - name: test-mlm
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: ChangeIsKey/kubhist2
          type: ChangeIsKey/kubhist2
          config: all
          split: train[:5%]
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.49963541184895327

test-mlm

This model is a fine-tuned version of KBLab/bert-base-swedish-cased on the ChangeIsKey/kubhist2 dataset. It achieves the following results on the evaluation set:

• Loss: 2.8883
• Accuracy: 0.4996

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-05
• train_batch_size: 128
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.33.1
• Pytorch 1.12.0
• Datasets 2.14.5
• Tokenizers 0.13.3