|
--- |
|
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: 0.1498 |
|
- Accuracy: 0.9713 |
|
- F1: 0.8341 |
|
- Precision: 0.8330 |
|
- Recall: 0.8356 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.6252 | 0.11 | 50 | 1.7120 | 0.3451 | 0.1545 | 0.2382 | 0.1762 | |
|
| 0.7857 | 0.22 | 100 | 0.7296 | 0.8209 | 0.4973 | 0.4815 | 0.5166 | |
|
| 0.2986 | 0.33 | 150 | 0.5358 | 0.8830 | 0.6565 | 0.6402 | 0.6744 | |
|
| 0.2612 | 0.44 | 200 | 0.4678 | 0.9035 | 0.6704 | 0.6621 | 0.6795 | |
|
| 0.153 | 0.55 | 250 | 0.4325 | 0.9065 | 0.6648 | 0.6446 | 0.6879 | |
|
| 0.2274 | 0.66 | 300 | 0.3498 | 0.8969 | 0.6440 | 0.6237 | 0.6677 | |
|
| 0.1449 | 0.76 | 350 | 0.4254 | 0.8964 | 0.6885 | 0.8012 | 0.6895 | |
|
| 0.1695 | 0.87 | 400 | 0.3484 | 0.9248 | 0.7301 | 0.7857 | 0.7208 | |
|
| 0.1206 | 0.98 | 450 | 0.3075 | 0.9218 | 0.7351 | 0.7586 | 0.7279 | |
|
| 0.1142 | 1.09 | 500 | 0.2241 | 0.9467 | 0.8063 | 0.7964 | 0.8218 | |
|
| 0.0642 | 1.2 | 550 | 0.2527 | 0.9491 | 0.8159 | 0.8106 | 0.8239 | |
|
| 0.0935 | 1.31 | 600 | 0.1961 | 0.9601 | 0.8216 | 0.8270 | 0.8173 | |
|
| 0.0755 | 1.42 | 650 | 0.1290 | 0.9691 | 0.8272 | 0.8348 | 0.8201 | |
|
| 0.108 | 1.53 | 700 | 0.1712 | 0.9612 | 0.8215 | 0.8311 | 0.8130 | |
|
| 0.0667 | 1.64 | 750 | 0.1449 | 0.9716 | 0.8354 | 0.8371 | 0.8338 | |
|
| 0.0925 | 1.75 | 800 | 0.1193 | 0.9721 | 0.8345 | 0.8353 | 0.8337 | |
|
| 0.0769 | 1.86 | 850 | 0.1477 | 0.9675 | 0.8299 | 0.8270 | 0.8334 | |
|
| 0.0558 | 1.97 | 900 | 0.1988 | 0.9606 | 0.8239 | 0.8194 | 0.8299 | |
|
| 0.0379 | 2.07 | 950 | 0.1546 | 0.9694 | 0.8319 | 0.8300 | 0.8340 | |
|
| 0.0358 | 2.18 | 1000 | 0.1871 | 0.9655 | 0.8295 | 0.8283 | 0.8312 | |
|
| 0.0248 | 2.29 | 1050 | 0.1631 | 0.9661 | 0.8303 | 0.8278 | 0.8333 | |
|
| 0.0412 | 2.4 | 1100 | 0.1688 | 0.9658 | 0.8283 | 0.8235 | 0.8340 | |
|
| 0.0096 | 2.51 | 1150 | 0.1726 | 0.9661 | 0.8316 | 0.8297 | 0.8342 | |
|
| 0.0025 | 2.62 | 1200 | 0.1808 | 0.9653 | 0.8300 | 0.8261 | 0.8348 | |
|
| 0.0074 | 2.73 | 1250 | 0.1697 | 0.9677 | 0.8323 | 0.8291 | 0.8360 | |
|
| 0.028 | 2.84 | 1300 | 0.1630 | 0.9705 | 0.8359 | 0.8344 | 0.8377 | |
|
| 0.0292 | 2.95 | 1350 | 0.1743 | 0.9696 | 0.8352 | 0.8341 | 0.8366 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
