Amarsanaa1525's picture
End of training
ed6c4a9
metadata
language:
  - mn
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-multilingual-cased-ner-demo
    results: []

bert-multilingual-cased-ner-demo

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

  • Loss: 0.1471
  • Precision: 0.9148
  • Recall: 0.9229
  • F1: 0.9188
  • Accuracy: 0.9759

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: 16
  • eval_batch_size: 32
  • 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
0.1743 1.0 477 0.0992 0.8649 0.8914 0.8780 0.9695
0.0848 2.0 954 0.0900 0.8822 0.9010 0.8915 0.9719
0.0557 3.0 1431 0.1110 0.8848 0.9001 0.8924 0.9699
0.0411 4.0 1908 0.1061 0.8993 0.9140 0.9066 0.9744
0.0298 5.0 2385 0.1130 0.8923 0.9147 0.9034 0.9732
0.0207 6.0 2862 0.1197 0.9078 0.9176 0.9127 0.9756
0.0144 7.0 3339 0.1372 0.9053 0.9180 0.9116 0.9742
0.0088 8.0 3816 0.1401 0.9080 0.9195 0.9137 0.9746
0.0066 9.0 4293 0.1442 0.9100 0.9216 0.9158 0.9753
0.0054 10.0 4770 0.1471 0.9148 0.9229 0.9188 0.9759

Framework versions

  • Transformers 4.35.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1