|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: final_V1-bert-text-classification-model |
|
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. --> |
|
|
|
# final_V1-bert-text-classification-model |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1649 |
|
- Accuracy: 0.9713 |
|
- F1: 0.8328 |
|
- Precision: 0.8290 |
|
- Recall: 0.8375 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.7173 | 0.11 | 50 | 1.7812 | 0.3445 | 0.1475 | 0.1755 | 0.1881 | |
|
| 0.9537 | 0.22 | 100 | 0.9779 | 0.7416 | 0.4399 | 0.4301 | 0.4701 | |
|
| 0.373 | 0.33 | 150 | 0.6741 | 0.8321 | 0.6187 | 0.6018 | 0.6423 | |
|
| 0.2625 | 0.44 | 200 | 0.3897 | 0.9070 | 0.6684 | 0.6503 | 0.6892 | |
|
| 0.2216 | 0.55 | 250 | 0.3971 | 0.9089 | 0.6670 | 0.6465 | 0.6920 | |
|
| 0.1583 | 0.66 | 300 | 0.3601 | 0.9029 | 0.6816 | 0.7957 | 0.6757 | |
|
| 0.1661 | 0.76 | 350 | 0.2266 | 0.9180 | 0.6950 | 0.7317 | 0.7019 | |
|
| 0.112 | 0.87 | 400 | 0.2525 | 0.9494 | 0.8020 | 0.7955 | 0.8132 | |
|
| 0.0857 | 0.98 | 450 | 0.2701 | 0.9459 | 0.8124 | 0.8060 | 0.8232 | |
|
| 0.1223 | 1.09 | 500 | 0.1781 | 0.9631 | 0.8281 | 0.8251 | 0.8319 | |
|
| 0.0641 | 1.2 | 550 | 0.2162 | 0.9552 | 0.8236 | 0.8229 | 0.8258 | |
|
| 0.0907 | 1.31 | 600 | 0.1486 | 0.9705 | 0.8351 | 0.8357 | 0.8346 | |
|
| 0.0738 | 1.42 | 650 | 0.1380 | 0.9696 | 0.8300 | 0.8276 | 0.8331 | |
|
| 0.0946 | 1.53 | 700 | 0.1577 | 0.9705 | 0.8357 | 0.8370 | 0.8345 | |
|
| 0.0476 | 1.64 | 750 | 0.1497 | 0.9707 | 0.8349 | 0.8337 | 0.8363 | |
|
| 0.0873 | 1.75 | 800 | 0.1722 | 0.9655 | 0.8318 | 0.8288 | 0.8353 | |
|
| 0.0487 | 1.86 | 850 | 0.1782 | 0.9647 | 0.8312 | 0.8283 | 0.8345 | |
|
| 0.0548 | 1.97 | 900 | 0.1610 | 0.9666 | 0.8336 | 0.8329 | 0.8346 | |
|
| 0.0492 | 2.07 | 950 | 0.1423 | 0.9688 | 0.8338 | 0.8287 | 0.8393 | |
|
| 0.0279 | 2.18 | 1000 | 0.1707 | 0.9669 | 0.8325 | 0.8287 | 0.8371 | |
|
| 0.0401 | 2.29 | 1050 | 0.1583 | 0.9688 | 0.8337 | 0.8300 | 0.8382 | |
|
| 0.0313 | 2.4 | 1100 | 0.1799 | 0.9647 | 0.8306 | 0.8274 | 0.8348 | |
|
| 0.025 | 2.51 | 1150 | 0.1661 | 0.9669 | 0.8320 | 0.8311 | 0.8335 | |
|
| 0.0043 | 2.62 | 1200 | 0.1933 | 0.9647 | 0.8305 | 0.8280 | 0.8339 | |
|
| 0.0115 | 2.73 | 1250 | 0.1570 | 0.9696 | 0.8328 | 0.8308 | 0.8352 | |
|
| 0.0198 | 2.84 | 1300 | 0.1538 | 0.9702 | 0.8340 | 0.8328 | 0.8355 | |
|
| 0.0085 | 2.95 | 1350 | 0.1591 | 0.9694 | 0.8337 | 0.8327 | 0.8351 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
