davidliu1110's picture
End of training
694d848
|
raw
history blame
1.62 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-base-chinese-david-ner
    results: []

bert-base-chinese-david-ner

This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2217
  • Precision: 0.8020
  • Recall: 0.8379
  • F1: 0.8196
  • Accuracy: 0.9471

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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.2487 1.4 500 0.2446 0.8138 0.8138 0.8138 0.9417
0.0668 2.8 1000 0.2217 0.8020 0.8379 0.8196 0.9471

Framework versions

  • Transformers 4.29.0.dev0
  • Pytorch 1.10.1+cu113
  • Datasets 2.11.0
  • Tokenizers 0.13.3