Hugging Face's logo

lekhnathrijal
/
bert-question-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files Community
bert-question-classifier / README.md
lekhnathrijal's picture
lekhnathrijal
ai-research-lab/bert-question-classifier
fc939d3 verified
preview code
|
raw
history blame contribute delete
4.23 kB
metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - precision
  - f1
model-index:
  - name: bert-question-classifier
    results: []

bert-question-classifier

This model is a fine-tuned version of google-bert/bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0746
  • Accuracy: 0.9807
  • Recall: 0.8925
  • Precision: 0.8909
  • F1: 0.8917

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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • 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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy Recall Precision F1
No log 0.1770 100 5.0786 0.8950 0.5327 0.4279 0.4746
No log 0.3540 200 4.3278 0.9257 0.5783 0.5838 0.5810
No log 0.5310 300 3.6620 0.9411 0.6940 0.6612 0.6772
No log 0.7080 400 3.1590 0.9515 0.7420 0.7211 0.7314
4.1504 0.8850 500 2.5666 0.9580 0.7770 0.7580 0.7674
4.1504 1.0619 600 2.1826 0.9638 0.7987 0.7954 0.7970
4.1504 1.2389 700 1.9754 0.9666 0.8168 0.8094 0.8131
4.1504 1.4159 800 1.8447 0.9686 0.8372 0.8151 0.8260
4.1504 1.5929 900 1.6676 0.9706 0.8457 0.8283 0.8369
2.012 1.7699 1000 1.5743 0.9728 0.8510 0.8450 0.8480
2.012 1.9469 1100 1.4473 0.9749 0.8641 0.8556 0.8598
2.012 2.1239 1200 1.4000 0.9749 0.8641 0.8551 0.8596
2.012 2.3009 1300 1.3287 0.9772 0.8764 0.8688 0.8726
2.012 2.4779 1400 1.2995 0.9770 0.8773 0.8659 0.8715
1.3018 2.6549 1500 1.2397 0.9778 0.8793 0.8724 0.8759
1.3018 2.8319 1600 1.2059 0.9786 0.8857 0.8753 0.8805
1.3018 3.0088 1700 1.1763 0.9790 0.8857 0.8798 0.8828
1.3018 3.1858 1800 1.1744 0.9786 0.8816 0.8788 0.8802
1.3018 3.3628 1900 1.1356 0.9793 0.8869 0.8818 0.8843
0.9668 3.5398 2000 1.1365 0.9791 0.8857 0.8806 0.8832
0.9668 3.7168 2100 1.1084 0.9796 0.8872 0.8838 0.8855
0.9668 3.8938 2200 1.0939 0.9800 0.8892 0.8864 0.8878
0.9668 4.0708 2300 1.0974 0.9796 0.8881 0.8834 0.8857
0.9668 4.2478 2400 1.0786 0.9802 0.8916 0.8864 0.8890
0.7915 4.4248 2500 1.0766 0.9803 0.8910 0.8881 0.8896
0.7915 4.6018 2600 1.0746 0.9807 0.8925 0.8909 0.8917
0.7915 4.7788 2700 1.0686 0.9803 0.8910 0.8887 0.8898
0.7915 4.9558 2800 1.0637 0.9802 0.8907 0.8873 0.8890

Framework versions

  • Transformers 4.48.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0