Hartunka's picture
End of training
83c7277 verified
metadata
library_name: transformers
language:
  - en
base_model: Hartunka/bert_base_rand_10_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_rand_10_v1_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6679210740439382

bert_base_rand_10_v1_mnli

This model is a fine-tuned version of Hartunka/bert_base_rand_10_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7815
  • Accuracy: 0.6679

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
0.9793 1.0 1534 0.9059 0.5710
0.8721 2.0 3068 0.8626 0.6047
0.7892 3.0 4602 0.8121 0.6435
0.7112 4.0 6136 0.8098 0.6464
0.6397 5.0 7670 0.7899 0.6647
0.5684 6.0 9204 0.8457 0.6695
0.4954 7.0 10738 0.8743 0.6684
0.4255 8.0 12272 0.9793 0.6591
0.3614 9.0 13806 1.1505 0.6596
0.3036 10.0 15340 1.2117 0.6593

Framework versions

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