metadata
base_model: jinmang2/kpfbert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: model_y3_research_1
results: []
model_y3_research_1
This model is a fine-tuned version of jinmang2/kpfbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7692
- Accuracy: 0.6082
- F1: 0.5677
- Precision: 0.5728
- Recall: 0.5706
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: 5e-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_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.9518 | 1.0 | 97 | 1.0302 | 0.4167 | 0.2266 | 0.2376 | 0.3280 |
| 0.9191 | 2.0 | 194 | 0.9158 | 0.5833 | 0.5823 | 0.6203 | 0.6297 |
| 0.8298 | 3.0 | 291 | 0.8410 | 0.6042 | 0.5903 | 0.5987 | 0.5848 |
| 0.7093 | 4.0 | 388 | 1.1104 | 0.5208 | 0.5176 | 0.5135 | 0.5312 |
| 0.5994 | 5.0 | 485 | 1.3535 | 0.5521 | 0.5437 | 0.5691 | 0.5555 |
| 0.709 | 6.0 | 582 | 1.8616 | 0.5104 | 0.4892 | 0.4975 | 0.5019 |
| 0.2919 | 7.0 | 679 | 2.5441 | 0.5208 | 0.5174 | 0.5164 | 0.5340 |
| 0.1296 | 8.0 | 776 | 2.9520 | 0.5104 | 0.4975 | 0.5103 | 0.4931 |
| 0.0012 | 9.0 | 873 | 3.1406 | 0.5312 | 0.5182 | 0.5165 | 0.5209 |
| 0.0393 | 10.0 | 970 | 3.1606 | 0.5208 | 0.5109 | 0.5084 | 0.5142 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2