---
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-chinese-david-ner
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert-base-chinese-david-ner

This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0588
- Precision: 0.9447
- Recall: 0.9479
- F1: 0.9463
- Accuracy: 0.9861

## 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: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.9539        | 0.09  | 100  | 0.4089          | 0.2768    | 0.2401 | 0.2571 | 0.8587   |
| 0.2552        | 0.18  | 200  | 0.1580          | 0.7110    | 0.7746 | 0.7415 | 0.9493   |
| 0.1586        | 0.27  | 300  | 0.1327          | 0.7357    | 0.8448 | 0.7865 | 0.9569   |
| 0.1322        | 0.35  | 400  | 0.1132          | 0.7820    | 0.8652 | 0.8215 | 0.9637   |
| 0.1171        | 0.44  | 500  | 0.1135          | 0.8522    | 0.8618 | 0.8570 | 0.9681   |
| 0.1           | 0.53  | 600  | 0.1008          | 0.8280    | 0.8720 | 0.8494 | 0.9685   |
| 0.0925        | 0.62  | 700  | 0.0983          | 0.8519    | 0.8924 | 0.8717 | 0.9730   |
| 0.0932        | 0.71  | 800  | 0.0720          | 0.8775    | 0.9003 | 0.8888 | 0.9771   |
| 0.0846        | 0.8   | 900  | 0.0754          | 0.8879    | 0.9060 | 0.8969 | 0.9766   |
| 0.0719        | 0.88  | 1000 | 0.0834          | 0.8713    | 0.8969 | 0.8839 | 0.9766   |
| 0.0854        | 0.97  | 1100 | 0.0710          | 0.8970    | 0.9173 | 0.9071 | 0.9795   |
| 0.0582        | 1.06  | 1200 | 0.0900          | 0.8760    | 0.8958 | 0.8858 | 0.9736   |
| 0.0487        | 1.15  | 1300 | 0.0880          | 0.9027    | 0.9241 | 0.9133 | 0.9795   |
| 0.0554        | 1.24  | 1400 | 0.0612          | 0.9132    | 0.9298 | 0.9214 | 0.9822   |
| 0.0423        | 1.33  | 1500 | 0.0686          | 0.8958    | 0.9253 | 0.9103 | 0.9805   |
| 0.0532        | 1.41  | 1600 | 0.0663          | 0.9070    | 0.9275 | 0.9171 | 0.9812   |
| 0.0433        | 1.5   | 1700 | 0.0644          | 0.9270    | 0.9343 | 0.9306 | 0.9833   |
| 0.0486        | 1.59  | 1800 | 0.0613          | 0.9099    | 0.9264 | 0.9181 | 0.9820   |
| 0.0528        | 1.68  | 1900 | 0.0601          | 0.9201    | 0.9264 | 0.9233 | 0.9842   |
| 0.0382        | 1.77  | 2000 | 0.0667          | 0.9172    | 0.9287 | 0.9229 | 0.9835   |
| 0.0517        | 1.86  | 2100 | 0.0607          | 0.9260    | 0.9354 | 0.9307 | 0.9835   |
| 0.0455        | 1.94  | 2200 | 0.0591          | 0.9147    | 0.9354 | 0.9250 | 0.9830   |
| 0.0377        | 2.03  | 2300 | 0.0679          | 0.9238    | 0.9332 | 0.9285 | 0.9828   |
| 0.0239        | 2.12  | 2400 | 0.0604          | 0.9246    | 0.9445 | 0.9345 | 0.9851   |
| 0.0237        | 2.21  | 2500 | 0.0700          | 0.9233    | 0.9411 | 0.9321 | 0.9838   |
| 0.0233        | 2.3   | 2600 | 0.0639          | 0.9201    | 0.9388 | 0.9294 | 0.9835   |
| 0.0196        | 2.39  | 2700 | 0.0589          | 0.9352    | 0.9479 | 0.9415 | 0.9864   |
| 0.0259        | 2.47  | 2800 | 0.0617          | 0.9337    | 0.9411 | 0.9374 | 0.9856   |
| 0.0244        | 2.56  | 2900 | 0.0609          | 0.9379    | 0.9411 | 0.9395 | 0.9855   |
| 0.0231        | 2.65  | 3000 | 0.0653          | 0.9383    | 0.9479 | 0.9431 | 0.9859   |
| 0.0326        | 2.74  | 3100 | 0.0588          | 0.9447    | 0.9479 | 0.9463 | 0.9861   |
| 0.0313        | 2.83  | 3200 | 0.0552          | 0.9446    | 0.9456 | 0.9451 | 0.9871   |
| 0.0227        | 2.92  | 3300 | 0.0517          | 0.9394    | 0.9479 | 0.9436 | 0.9871   |
| 0.0244        | 3.0   | 3400 | 0.0588          | 0.9259    | 0.9479 | 0.9368 | 0.9855   |
| 0.0205        | 3.09  | 3500 | 0.0607          | 0.9224    | 0.9422 | 0.9322 | 0.9857   |
| 0.0181        | 3.18  | 3600 | 0.0601          | 0.9266    | 0.9434 | 0.9349 | 0.9856   |
| 0.0097        | 3.27  | 3700 | 0.0649          | 0.9360    | 0.9434 | 0.9397 | 0.9854   |
| 0.0137        | 3.36  | 3800 | 0.0662          | 0.9372    | 0.9468 | 0.9420 | 0.9851   |
| 0.0131        | 3.45  | 3900 | 0.0657          | 0.9353    | 0.9502 | 0.9427 | 0.9858   |
| 0.0119        | 3.53  | 4000 | 0.0639          | 0.9373    | 0.9479 | 0.9426 | 0.9860   |
| 0.0189        | 3.62  | 4100 | 0.0625          | 0.9371    | 0.9456 | 0.9414 | 0.9858   |
| 0.0179        | 3.71  | 4200 | 0.0609          | 0.9385    | 0.9502 | 0.9443 | 0.9860   |
| 0.0111        | 3.8   | 4300 | 0.0609          | 0.9362    | 0.9479 | 0.9420 | 0.9864   |
| 0.0102        | 3.89  | 4400 | 0.0607          | 0.9383    | 0.9479 | 0.9431 | 0.9860   |
| 0.0166        | 3.98  | 4500 | 0.0606          | 0.9395    | 0.9490 | 0.9442 | 0.9859   |


### Framework versions

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