|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: final_V1-roberta-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-roberta-text-classification-model |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2641 |
|
- Accuracy: 0.9502 |
|
- F1: 0.8186 |
|
- Precision: 0.8164 |
|
- Recall: 0.8225 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.6615 | 0.11 | 50 | 1.5503 | 0.3199 | 0.1016 | 0.2599 | 0.1518 | |
|
| 0.6244 | 0.22 | 100 | 0.7198 | 0.7692 | 0.4656 | 0.4593 | 0.4818 | |
|
| 0.3344 | 0.33 | 150 | 0.4852 | 0.8893 | 0.6484 | 0.6264 | 0.6733 | |
|
| 0.2596 | 0.44 | 200 | 0.5277 | 0.8805 | 0.6398 | 0.6124 | 0.6748 | |
|
| 0.2173 | 0.55 | 250 | 0.4417 | 0.8849 | 0.6577 | 0.6421 | 0.6750 | |
|
| 0.2393 | 0.66 | 300 | 0.5221 | 0.8707 | 0.6511 | 0.6361 | 0.6684 | |
|
| 0.2229 | 0.76 | 350 | 0.4997 | 0.8928 | 0.6602 | 0.6410 | 0.6814 | |
|
| 0.1482 | 0.87 | 400 | 0.5111 | 0.8983 | 0.6409 | 0.6131 | 0.6810 | |
|
| 0.1831 | 0.98 | 450 | 0.4251 | 0.8827 | 0.6827 | 0.7149 | 0.6957 | |
|
| 0.1882 | 1.09 | 500 | 0.4130 | 0.9043 | 0.6805 | 0.7998 | 0.6878 | |
|
| 0.1182 | 1.2 | 550 | 0.4513 | 0.9076 | 0.6973 | 0.7703 | 0.7004 | |
|
| 0.101 | 1.31 | 600 | 0.3402 | 0.9221 | 0.7040 | 0.8097 | 0.7036 | |
|
| 0.0749 | 1.42 | 650 | 0.1566 | 0.9658 | 0.8229 | 0.8350 | 0.8122 | |
|
| 0.1294 | 1.53 | 700 | 0.1586 | 0.9675 | 0.8336 | 0.8327 | 0.8346 | |
|
| 0.046 | 1.64 | 750 | 0.2010 | 0.9604 | 0.8264 | 0.8211 | 0.8334 | |
|
| 0.0833 | 1.75 | 800 | 0.1707 | 0.9647 | 0.8285 | 0.8244 | 0.8330 | |
|
| 0.0759 | 1.86 | 850 | 0.1625 | 0.9664 | 0.8278 | 0.8285 | 0.8271 | |
|
| 0.0459 | 1.97 | 900 | 0.1831 | 0.9620 | 0.8258 | 0.8200 | 0.8328 | |
|
| 0.0726 | 2.07 | 950 | 0.1753 | 0.9625 | 0.8279 | 0.8287 | 0.8276 | |
|
| 0.0369 | 2.18 | 1000 | 0.1871 | 0.9650 | 0.8300 | 0.8252 | 0.8362 | |
|
| 0.0456 | 2.29 | 1050 | 0.1524 | 0.9683 | 0.8320 | 0.8278 | 0.8367 | |
|
| 0.0371 | 2.4 | 1100 | 0.1857 | 0.9631 | 0.8280 | 0.8219 | 0.8353 | |
|
| 0.0106 | 2.51 | 1150 | 0.1850 | 0.9661 | 0.8318 | 0.8274 | 0.8370 | |
|
| 0.0173 | 2.62 | 1200 | 0.2055 | 0.9647 | 0.8310 | 0.8259 | 0.8374 | |
|
| 0.036 | 2.73 | 1250 | 0.1699 | 0.9694 | 0.8311 | 0.8267 | 0.8358 | |
|
| 0.0176 | 2.84 | 1300 | 0.1780 | 0.9691 | 0.8325 | 0.8274 | 0.8382 | |
|
| 0.0444 | 2.95 | 1350 | 0.1918 | 0.9672 | 0.8319 | 0.8275 | 0.8371 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|