metadata
library_name: transformers
license: apache-2.0
base_model: hfl/chinese-bert-wwm-ext
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner_model_output
results: []
ner_model_output
This model is a fine-tuned version of hfl/chinese-bert-wwm-ext on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3016
- Precision: 0.9999
- Recall: 0.9999
- F1: 0.9999
- Accuracy: 1.0000
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3032 | 1.0 | 6200 | 0.3026 | 0.9995 | 0.9996 | 0.9995 | 0.9997 |
| 0.3031 | 2.0 | 12400 | 0.3018 | 0.9999 | 0.9999 | 0.9999 | 1.0000 |
| 0.3025 | 3.0 | 18600 | 0.3017 | 0.9999 | 0.9999 | 0.9999 | 1.0000 |
| 0.3024 | 4.0 | 24800 | 0.3017 | 0.9999 | 0.9999 | 0.9999 | 1.0000 |
| 0.3019 | 5.0 | 31000 | 0.3016 | 0.9999 | 0.9999 | 0.9999 | 1.0000 |
| 0.3034 | 6.0 | 37200 | 0.3016 | 0.9999 | 0.9999 | 0.9999 | 1.0000 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1