gokulsrinivasagan's picture
End of training
45d2d04 verified
metadata
library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/distilbert_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert_lda_20_v1_book_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6985294117647058
          - name: F1
            type: f1
            value: 0.8062992125984252

distilbert_lda_20_v1_book_mrpc

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_20_v1_book on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5723
  • Accuracy: 0.6985
  • F1: 0.8063
  • Combined Score: 0.7524

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 F1 Combined Score
0.6229 1.0 15 0.5869 0.6887 0.8013 0.7450
0.5861 2.0 30 0.5723 0.6985 0.8063 0.7524
0.5298 3.0 45 0.5742 0.6961 0.7847 0.7404
0.4213 4.0 60 0.6085 0.7279 0.8076 0.7678
0.3198 5.0 75 0.7630 0.7426 0.8298 0.7862
0.3685 6.0 90 0.6738 0.7304 0.8063 0.7684
0.1999 7.0 105 1.1241 0.7083 0.8232 0.7658

Framework versions

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