Hugging Face's logo

silpakanneganti
/
bert-medical-ner

Token Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
22
bert-medical-ner / README.md
silpakanneganti's picture
silpakanneganti
update model card README.md
3484623
preview code
|
raw
history blame
6.01 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-medical-ner
    results: []

bert-medical-ner

This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3023
  • Precision: 0.6627
  • Recall: 0.6985
  • F1: 0.6802
  • Accuracy: 0.7491

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: 2e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 71 1.8664 0.3387 0.4366 0.3815 0.5491
No log 2.0 142 1.3020 0.4581 0.5572 0.5028 0.6561
No log 3.0 213 1.1061 0.5318 0.6091 0.5678 0.6921
No log 4.0 284 0.9755 0.6177 0.6383 0.6278 0.7193
No log 5.0 355 0.9530 0.6071 0.6362 0.6213 0.7272
No log 6.0 426 0.8876 0.6456 0.6590 0.6523 0.7351
No log 7.0 497 0.8754 0.6674 0.6757 0.6715 0.7386
1.158 8.0 568 0.8472 0.6782 0.6923 0.6852 0.7491
1.158 9.0 639 0.8816 0.6573 0.6819 0.6694 0.7368
1.158 10.0 710 0.9035 0.6260 0.6299 0.6280 0.7184
1.158 11.0 781 0.9156 0.6573 0.6819 0.6694 0.7377
1.158 12.0 852 0.8764 0.6536 0.6944 0.6734 0.7456
1.158 13.0 923 0.9079 0.6673 0.6881 0.6776 0.7404
1.158 14.0 994 0.9278 0.6525 0.6715 0.6619 0.7351
0.4312 15.0 1065 0.9387 0.6755 0.6923 0.6838 0.7465
0.4312 16.0 1136 0.9396 0.6595 0.7006 0.6794 0.7482
0.4312 17.0 1207 0.9672 0.648 0.6736 0.6606 0.7351
0.4312 18.0 1278 0.9890 0.6719 0.7110 0.6909 0.7509
0.4312 19.0 1349 1.0124 0.6344 0.6819 0.6573 0.7368
0.4312 20.0 1420 1.0107 0.6564 0.7069 0.6807 0.7526
0.4312 21.0 1491 1.0036 0.6765 0.7131 0.6943 0.7632
0.2196 22.0 1562 1.0244 0.6744 0.7235 0.6981 0.7561
0.2196 23.0 1633 1.0668 0.6602 0.7027 0.6808 0.7430
0.2196 24.0 1704 1.1040 0.6667 0.7193 0.6920 0.7526
0.2196 25.0 1775 1.0959 0.6699 0.7173 0.6928 0.7553
0.2196 26.0 1846 1.0721 0.6765 0.7173 0.6963 0.7544
0.2196 27.0 1917 1.1114 0.6628 0.7069 0.6841 0.7553
0.2196 28.0 1988 1.1225 0.6429 0.6923 0.6667 0.7421
0.1279 29.0 2059 1.1149 0.6481 0.7006 0.6733 0.7588
0.1279 30.0 2130 1.1545 0.6660 0.7048 0.6848 0.7544
0.1279 31.0 2201 1.1645 0.6641 0.7152 0.6887 0.7535
0.1279 32.0 2272 1.2004 0.6523 0.6944 0.6727 0.7386
0.1279 33.0 2343 1.2030 0.6419 0.6819 0.6613 0.7404
0.1279 34.0 2414 1.2434 0.6726 0.7048 0.6883 0.7482
0.1279 35.0 2485 1.2795 0.6548 0.6902 0.6721 0.7412
0.0843 36.0 2556 1.2499 0.6772 0.7152 0.6957 0.7544
0.0843 37.0 2627 1.2545 0.6745 0.7152 0.6942 0.7535
0.0843 38.0 2698 1.2286 0.6680 0.6985 0.6829 0.75
0.0843 39.0 2769 1.2943 0.6601 0.6985 0.6788 0.7518
0.0843 40.0 2840 1.2713 0.6640 0.7027 0.6828 0.7535
0.0843 41.0 2911 1.2828 0.6510 0.6902 0.6700 0.7465
0.0843 42.0 2982 1.2830 0.6621 0.7048 0.6828 0.7509
0.0619 43.0 3053 1.2942 0.6621 0.6965 0.6788 0.75
0.0619 44.0 3124 1.2912 0.6752 0.7089 0.6917 0.7544
0.0619 45.0 3195 1.2631 0.6680 0.7069 0.6869 0.7579
0.0619 46.0 3266 1.2948 0.6647 0.7006 0.6822 0.7535
0.0619 47.0 3337 1.2829 0.6739 0.7131 0.6929 0.7570
0.0619 48.0 3408 1.2943 0.6602 0.7027 0.6808 0.75
0.0619 49.0 3479 1.2995 0.6562 0.6944 0.6747 0.7465
0.0514 50.0 3550 1.3023 0.6627 0.6985 0.6802 0.7491

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3