Hartunka's picture
End of training
88a8826 verified
metadata
library_name: transformers
language:
  - en
base_model: Hartunka/bert_base_rand_50_v2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_rand_50_v2_qnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QNLI
          type: glue
          args: qnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6423210690097017

bert_base_rand_50_v2_qnli

This model is a fine-tuned version of Hartunka/bert_base_rand_50_v2 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6291
  • Accuracy: 0.6423

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
0.6614 1.0 410 0.6422 0.6244
0.6209 2.0 820 0.6291 0.6423
0.5531 3.0 1230 0.6537 0.6346
0.4498 4.0 1640 0.7286 0.6456
0.3341 5.0 2050 0.7747 0.6467
0.2345 6.0 2460 1.0803 0.6409
0.1664 7.0 2870 1.2036 0.6449

Framework versions

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