Hugging Face's logo

gokulsrinivasagan
/
distilbert_lda_100_v1_book_stsb

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
distilbert_lda_100_v1_book_stsb / README.md
gokulsrinivasagan's picture
gokulsrinivasagan
End of training
1cbc8df verified
preview code
|
raw
history blame contribute delete
3.21 kB
metadata
library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/distilbert_lda_100_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - spearmanr
model-index:
  - name: distilbert_lda_100_v1_book_stsb
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE STSB
          type: glue
          args: stsb
        metrics:
          - name: Spearmanr
            type: spearmanr
            value: 0.8014167289188371

distilbert_lda_100_v1_book_stsb

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_100_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7981
  • Pearson: 0.8060
  • Spearmanr: 0.8014
  • Combined Score: 0.8037

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 OptimizerNames.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 Pearson Spearmanr Combined Score
3.1376 1.0 23 2.3444 0.1800 0.1657 0.1729
1.571 2.0 46 1.4977 0.6469 0.6552 0.6511
1.0298 3.0 69 0.9940 0.7483 0.7462 0.7472
0.8795 4.0 92 1.0649 0.7622 0.7710 0.7666
0.6951 5.0 115 1.5036 0.7508 0.7848 0.7678
0.5558 6.0 138 0.9067 0.7878 0.7914 0.7896
0.4306 7.0 161 0.8333 0.8051 0.8039 0.8045
0.3592 8.0 184 0.9582 0.7967 0.7975 0.7971
0.2847 9.0 207 1.0402 0.7929 0.7954 0.7942
0.2689 10.0 230 0.7981 0.8060 0.8014 0.8037
0.2368 11.0 253 0.8628 0.8101 0.8083 0.8092
0.2088 12.0 276 1.0529 0.7991 0.8011 0.8001
0.1912 13.0 299 0.8878 0.8011 0.8013 0.8012
0.1618 14.0 322 0.8757 0.7959 0.7943 0.7951
0.1557 15.0 345 0.8971 0.8001 0.7979 0.7990

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.2.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.1