|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: final_V2-bert-after-adding-new-words-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_V2-bert-after-adding-new-words-text-classification-model |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1494 |
|
- Accuracy: 0.9716 |
|
- F1: 0.8348 |
|
- Precision: 0.8317 |
|
- Recall: 0.8385 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.8136 | 0.11 | 50 | 1.7501 | 0.3470 | 0.1733 | 0.3034 | 0.1944 | |
|
| 0.9023 | 0.22 | 100 | 1.2121 | 0.5723 | 0.3083 | 0.3496 | 0.3189 | |
|
| 0.5924 | 0.33 | 150 | 0.9662 | 0.6667 | 0.3919 | 0.4265 | 0.4037 | |
|
| 0.4218 | 0.44 | 200 | 0.4848 | 0.8813 | 0.6427 | 0.6492 | 0.6413 | |
|
| 0.2025 | 0.55 | 250 | 0.3807 | 0.9021 | 0.6677 | 0.6538 | 0.6829 | |
|
| 0.1609 | 0.66 | 300 | 0.3360 | 0.9147 | 0.6763 | 0.6727 | 0.6822 | |
|
| 0.2035 | 0.76 | 350 | 0.3705 | 0.8991 | 0.6711 | 0.6589 | 0.6838 | |
|
| 0.1208 | 0.87 | 400 | 0.2140 | 0.9565 | 0.8218 | 0.8137 | 0.8323 | |
|
| 0.1313 | 0.98 | 450 | 0.6818 | 0.8704 | 0.6779 | 0.7179 | 0.6859 | |
|
| 0.1576 | 1.09 | 500 | 0.2508 | 0.9212 | 0.7443 | 0.7888 | 0.7311 | |
|
| 0.0593 | 1.2 | 550 | 0.2091 | 0.9552 | 0.8193 | 0.8179 | 0.8227 | |
|
| 0.0705 | 1.31 | 600 | 0.2010 | 0.9552 | 0.8154 | 0.8091 | 0.8225 | |
|
| 0.0637 | 1.42 | 650 | 0.1985 | 0.9573 | 0.8187 | 0.8115 | 0.8275 | |
|
| 0.0619 | 1.53 | 700 | 0.2306 | 0.9541 | 0.8241 | 0.8194 | 0.8301 | |
|
| 0.0582 | 1.64 | 750 | 0.2001 | 0.9609 | 0.8280 | 0.8250 | 0.8320 | |
|
| 0.1132 | 1.75 | 800 | 0.1439 | 0.9680 | 0.8324 | 0.8284 | 0.8367 | |
|
| 0.0416 | 1.86 | 850 | 0.1558 | 0.9680 | 0.8333 | 0.8301 | 0.8369 | |
|
| 0.0371 | 1.97 | 900 | 0.2242 | 0.9595 | 0.8280 | 0.8235 | 0.8345 | |
|
| 0.0428 | 2.07 | 950 | 0.1907 | 0.9617 | 0.8303 | 0.8262 | 0.8356 | |
|
| 0.0388 | 2.18 | 1000 | 0.1784 | 0.9658 | 0.8319 | 0.8266 | 0.8383 | |
|
| 0.0335 | 2.29 | 1050 | 0.1735 | 0.9675 | 0.8323 | 0.8266 | 0.8390 | |
|
| 0.0361 | 2.4 | 1100 | 0.1921 | 0.9636 | 0.8283 | 0.8219 | 0.8360 | |
|
| 0.0126 | 2.51 | 1150 | 0.2200 | 0.9614 | 0.8294 | 0.8274 | 0.8327 | |
|
| 0.003 | 2.62 | 1200 | 0.2251 | 0.9614 | 0.8296 | 0.8262 | 0.8346 | |
|
| 0.0029 | 2.73 | 1250 | 0.1750 | 0.9694 | 0.8348 | 0.8314 | 0.8388 | |
|
| 0.0137 | 2.84 | 1300 | 0.1775 | 0.9686 | 0.8345 | 0.8300 | 0.8397 | |
|
| 0.0184 | 2.95 | 1350 | 0.1860 | 0.9675 | 0.8337 | 0.8293 | 0.8391 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
