Hugging Face's logo

mpalaval
/
bert-ner-3

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bert-ner-3 / README.md
mpalaval's picture
mpalaval
Training complete
457b77f
preview code
|
raw
history blame contribute delete
2.33 kB
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-ner-3
    results: []

bert-ner-3

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: 0.5646
  • Precision: 0.1708
  • Recall: 0.4296
  • F1: 0.2444
  • Accuracy: 0.8849

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
No log 1.0 211 0.3086 0.1551 0.2612 0.1946 0.9151
No log 2.0 422 0.3039 0.1730 0.3608 0.2339 0.9091
0.3957 3.0 633 0.3823 0.1396 0.3608 0.2013 0.8904
0.3957 4.0 844 0.4147 0.1592 0.3780 0.2240 0.8862
0.1085 5.0 1055 0.4257 0.1785 0.3814 0.2432 0.8963
0.1085 6.0 1266 0.5030 0.1575 0.4055 0.2269 0.8797
0.1085 7.0 1477 0.5427 0.1509 0.3883 0.2173 0.8784
0.0488 8.0 1688 0.5601 0.1673 0.4467 0.2434 0.8775
0.0488 9.0 1899 0.5518 0.1707 0.4124 0.2414 0.8880
0.0243 10.0 2110 0.5646 0.1708 0.4296 0.2444 0.8849

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1