Hartunka's picture
End of training
e71efda verified
metadata
library_name: transformers
language:
  - en
base_model: Hartunka/tiny_bert_rand_20_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: tiny_bert_rand_20_v1_wnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE WNLI
          type: glue
          args: wnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.30985915492957744

tiny_bert_rand_20_v1_wnli

This model is a fine-tuned version of Hartunka/tiny_bert_rand_20_v1 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7453
  • Accuracy: 0.3099

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
0.7076 1.0 3 0.7453 0.3099
0.6916 2.0 6 0.7565 0.2817
0.6861 3.0 9 0.7788 0.2254
0.6797 4.0 12 0.8008 0.1408
0.6846 5.0 15 0.8252 0.1549
0.6773 6.0 18 0.8489 0.1408

Framework versions

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