da-sentiment / README.md
mirfan899's picture
update model card README.md
684214d
|
raw
history blame
1.89 kB
metadata
license: cc-by-4.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: da-sentiment
    results: []

da-sentiment

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

  • Loss: 0.2554
  • Accuracy: 0.9392

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: 3e-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

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 46 0.2599 0.9171
No log 2.0 92 0.2205 0.9254
No log 3.0 138 0.2175 0.9309
No log 4.0 184 0.2114 0.9309
No log 5.0 230 0.2509 0.9337
No log 6.0 276 0.2510 0.9309
No log 7.0 322 0.2412 0.9392
No log 8.0 368 0.2540 0.9392
No log 9.0 414 0.2535 0.9392
No log 10.0 460 0.2554 0.9392

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2