metadata
license: gpl-3.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-chinese-finetuned-ner_0220_J_ORIDATA_FULL_NOMOD
results: []
bert-base-chinese-finetuned-ner_0220_J_ORIDATA_FULL_NOMOD
This model is a fine-tuned version of ckiplab/bert-base-chinese-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3786
- Precision: 0.9357
- Recall: 0.9657
- F1: 0.9504
- Accuracy: 0.9577
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: 2
- eval_batch_size: 2
- 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 |
---|---|---|---|---|---|---|---|
0.0925 | 1.0 | 5358 | 0.2337 | 0.9246 | 0.9655 | 0.9446 | 0.9554 |
0.0787 | 2.0 | 10716 | 0.2506 | 0.9208 | 0.9588 | 0.9394 | 0.9525 |
0.0606 | 3.0 | 16074 | 0.2914 | 0.9309 | 0.9621 | 0.9462 | 0.9537 |
0.0543 | 4.0 | 21432 | 0.2792 | 0.9248 | 0.9633 | 0.9437 | 0.9553 |
0.056 | 5.0 | 26790 | 0.3064 | 0.9332 | 0.9645 | 0.9486 | 0.9563 |
0.0384 | 6.0 | 32148 | 0.3317 | 0.9347 | 0.9632 | 0.9487 | 0.9564 |
0.0265 | 7.0 | 37506 | 0.3340 | 0.9342 | 0.9667 | 0.9502 | 0.9568 |
0.03 | 8.0 | 42864 | 0.3460 | 0.9363 | 0.9641 | 0.9500 | 0.9558 |
0.0192 | 9.0 | 48222 | 0.3649 | 0.9357 | 0.9651 | 0.9501 | 0.9576 |
0.0117 | 10.0 | 53580 | 0.3786 | 0.9357 | 0.9657 | 0.9504 | 0.9577 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.13.0+cu117
- Datasets 2.8.0
- Tokenizers 0.12.1