Hartunka's picture
End of training
32201a2 verified
metadata
library_name: transformers
language:
  - en
base_model: Hartunka/tiny_bert_rand_20_v2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
  - accuracy
model-index:
  - name: tiny_bert_rand_20_v2_cola
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0
          - name: Accuracy
            type: accuracy
            value: 0.6912751793861389

tiny_bert_rand_20_v2_cola

This model is a fine-tuned version of Hartunka/tiny_bert_rand_20_v2 on the GLUE COLA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6182
  • Matthews Correlation: 0.0
  • Accuracy: 0.6913

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 Matthews Correlation Accuracy
0.6153 1.0 34 0.6182 0.0 0.6913
0.601 2.0 68 0.6202 0.0 0.6913
0.5777 3.0 102 0.6294 -0.0041 0.6846
0.5335 4.0 136 0.6736 0.0676 0.6750
0.4924 5.0 170 0.6791 0.0717 0.6462
0.4569 6.0 204 0.7303 0.0557 0.6395

Framework versions

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