metadata
tags:
- generated_from_trainer
datasets:
- peoples_daily_ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-chinese-people-daily
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: peoples_daily_ner
type: peoples_daily_ner
config: peoples_daily_ner
split: validation
args: peoples_daily_ner
metrics:
- name: Precision
type: precision
value: 0.8608247422680413
- name: Recall
type: recall
value: 0.8608247422680413
- name: F1
type: f1
value: 0.8608247422680413
- name: Accuracy
type: accuracy
value: 0.9852778800147222
bert-finetuned-ner-chinese-people-daily
This model is a fine-tuned version of bert-base-chinese on the peoples_daily_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0604
- Precision: 0.8608
- Recall: 0.8608
- F1: 0.8608
- Accuracy: 0.9853
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 131 | 0.0753 | 0.6955 | 0.7887 | 0.7391 | 0.9764 |
| No log | 2.0 | 262 | 0.0588 | 0.7971 | 0.8505 | 0.8229 | 0.9840 |
| No log | 3.0 | 393 | 0.0604 | 0.8608 | 0.8608 | 0.8608 | 0.9853 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3