Hartunka's picture
End of training
69e2d76 verified
metadata
library_name: transformers
language:
  - en
base_model: Hartunka/bert_base_km_20_v2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_km_20_v2_sst2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE SST2
          type: glue
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7981651376146789

bert_base_km_20_v2_sst2

This model is a fine-tuned version of Hartunka/bert_base_km_20_v2 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4388
  • Accuracy: 0.7982

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: 256
  • eval_batch_size: 256
  • seed: 10
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4155 1.0 264 0.4388 0.7982
0.2288 2.0 528 0.5246 0.7913
0.1668 3.0 792 0.6084 0.7936
0.1248 4.0 1056 0.6475 0.7947
0.0928 5.0 1320 0.7931 0.7798
0.0692 6.0 1584 0.8769 0.7924

Framework versions

  • Transformers 4.50.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.21.1