|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-base-cased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: bert-base-cased-finetuned-ner3 |
|
|
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-cased-finetuned-ner3 |
|
|
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1625 |
|
|
- Precision: 0.7903 |
|
|
- Recall: 0.8291 |
|
|
- F1: 0.8092 |
|
|
- Accuracy: 0.9569 |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 4 |
|
|
- 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: cosine |
|
|
- lr_scheduler_warmup_steps: 1000 |
|
|
- num_epochs: 9 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.2932 | 0.5 | 4750 | 0.2719 | 0.6321 | 0.7644 | 0.6919 | 0.9309 | |
|
|
| 0.2262 | 1.0 | 9500 | 0.2197 | 0.7089 | 0.7873 | 0.7460 | 0.9418 | |
|
|
| 0.2037 | 1.5 | 14250 | 0.2017 | 0.7331 | 0.7982 | 0.7643 | 0.9454 | |
|
|
| 0.1758 | 2.0 | 19000 | 0.1851 | 0.7634 | 0.8050 | 0.7836 | 0.9499 | |
|
|
| 0.1699 | 2.5 | 23750 | 0.1910 | 0.7624 | 0.8091 | 0.7850 | 0.9510 | |
|
|
| 0.1643 | 3.0 | 28500 | 0.1894 | 0.7641 | 0.8125 | 0.7875 | 0.9509 | |
|
|
| 0.1523 | 3.5 | 33250 | 0.1829 | 0.7574 | 0.8136 | 0.7845 | 0.9502 | |
|
|
| 0.153 | 4.0 | 38000 | 0.1667 | 0.7794 | 0.8150 | 0.7968 | 0.9544 | |
|
|
| 0.1445 | 4.5 | 42750 | 0.1745 | 0.7838 | 0.8179 | 0.8005 | 0.9545 | |
|
|
| 0.1419 | 5.0 | 47500 | 0.1773 | 0.7877 | 0.8195 | 0.8033 | 0.9534 | |
|
|
| 0.137 | 5.5 | 52250 | 0.1635 | 0.7880 | 0.8211 | 0.8042 | 0.9567 | |
|
|
| 0.1298 | 6.0 | 57000 | 0.1611 | 0.7837 | 0.8243 | 0.8035 | 0.9560 | |
|
|
| 0.133 | 6.5 | 61750 | 0.1595 | 0.7908 | 0.8281 | 0.8090 | 0.9564 | |
|
|
| 0.1264 | 7.0 | 66500 | 0.1640 | 0.7941 | 0.8263 | 0.8099 | 0.9567 | |
|
|
| 0.1341 | 7.5 | 71250 | 0.1626 | 0.7894 | 0.8286 | 0.8085 | 0.9571 | |
|
|
| 0.1292 | 8.0 | 76000 | 0.1627 | 0.7902 | 0.8286 | 0.8090 | 0.9569 | |
|
|
| 0.1291 | 8.5 | 80750 | 0.1620 | 0.7902 | 0.8293 | 0.8093 | 0.9570 | |
|
|
| 0.1235 | 9.0 | 85500 | 0.1625 | 0.7903 | 0.8291 | 0.8092 | 0.9569 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.50.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.4.1 |
|
|
- Tokenizers 0.21.1 |
|
|
|
