Hugging Face's logo

ABrinkmann
/
bert-finetuned-ner-10epochs

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bert-finetuned-ner-10epochs / README.md
ABrinkmann's picture
ABrinkmann
update model card README.md
04c94ba
preview code
|
raw
history blame contribute delete
2.35 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner-10epochs
    results: []

bert-finetuned-ner-10epochs

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

  • Loss: 0.0895
  • Precision: 0.9167
  • Recall: 0.9546
  • F1: 0.9352
  • Accuracy: 0.9888

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0061 1.0 2261 0.0961 0.8813 0.9436 0.9114 0.9869
0.0241 2.0 4522 0.0566 0.9001 0.9502 0.9245 0.9878
0.02 3.0 6783 0.0560 0.9010 0.9528 0.9261 0.9879
0.0169 4.0 9044 0.0519 0.9045 0.9539 0.9285 0.9884
0.0129 5.0 11305 0.0621 0.9073 0.9568 0.9314 0.9886
0.009 6.0 13566 0.0623 0.9123 0.9451 0.9284 0.9883
0.0078 7.0 15827 0.0727 0.9145 0.9473 0.9306 0.9886
0.0056 8.0 18088 0.0806 0.9134 0.9535 0.9330 0.9882
0.0034 9.0 20349 0.0856 0.9103 0.9546 0.9319 0.9886
0.003 10.0 22610 0.0895 0.9167 0.9546 0.9352 0.9888

Framework versions

  • Transformers 4.30.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3