gokulsrinivasagan's picture
End of training
7fa3345 verified
metadata
library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_lda_20_v1_book_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8117371847030106

bert_base_lda_20_v1_book_mnli

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_20_v1_book on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4779
  • Accuracy: 0.8117

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
0.6384 1.0 1534 0.5400 0.7887
0.4424 2.0 3068 0.4842 0.8124
0.3282 3.0 4602 0.5306 0.8087
0.2371 4.0 6136 0.5695 0.8162
0.1756 5.0 7670 0.6396 0.8067
0.1332 6.0 9204 0.7668 0.8105
0.1049 7.0 10738 0.7943 0.8101

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.0
  • Tokenizers 0.20.3