|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scam-alert-distil-roberta |
|
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. --> |
|
|
|
# scam-alert-distil-roberta |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co./distilbert/distilroberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1213 |
|
- Accuracy: 0.9861 |
|
- F1: 0.9860 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.1577 | 100 | 0.0852 | 0.9861 | 0.9860 | |
|
| No log | 0.3155 | 200 | 0.0690 | 0.9861 | 0.9858 | |
|
| No log | 0.4732 | 300 | 0.0965 | 0.9841 | 0.9842 | |
|
| No log | 0.6309 | 400 | 0.1015 | 0.9821 | 0.9818 | |
|
| No log | 0.7886 | 500 | 0.0629 | 0.9861 | 0.9859 | |
|
| No log | 0.9464 | 600 | 0.0788 | 0.9841 | 0.9839 | |
|
| No log | 1.1041 | 700 | 0.0500 | 0.9880 | 0.9880 | |
|
| No log | 1.2618 | 800 | 0.0778 | 0.9880 | 0.9879 | |
|
| No log | 1.4196 | 900 | 0.0657 | 0.9880 | 0.9879 | |
|
| No log | 1.5773 | 1000 | 0.1129 | 0.9841 | 0.9837 | |
|
| No log | 1.7350 | 1100 | 0.1038 | 0.9880 | 0.9879 | |
|
| No log | 1.8927 | 1200 | 0.0861 | 0.9880 | 0.9879 | |
|
| No log | 2.0505 | 1300 | 0.1047 | 0.9841 | 0.9841 | |
|
| No log | 2.2082 | 1400 | 0.0858 | 0.9900 | 0.9899 | |
|
| No log | 2.3659 | 1500 | 0.0936 | 0.9880 | 0.9879 | |
|
| No log | 2.5237 | 1600 | 0.0936 | 0.9861 | 0.9859 | |
|
| No log | 2.6814 | 1700 | 0.0909 | 0.9861 | 0.9859 | |
|
| No log | 2.8391 | 1800 | 0.1143 | 0.9841 | 0.9842 | |
|
| No log | 2.9968 | 1900 | 0.0902 | 0.9880 | 0.9881 | |
|
| No log | 3.1546 | 2000 | 0.0979 | 0.9841 | 0.9840 | |
|
| No log | 3.3123 | 2100 | 0.0977 | 0.9861 | 0.9860 | |
|
| No log | 3.4700 | 2200 | 0.0987 | 0.9861 | 0.9860 | |
|
| No log | 3.6278 | 2300 | 0.1016 | 0.9861 | 0.9860 | |
|
| No log | 3.7855 | 2400 | 0.1170 | 0.9861 | 0.9858 | |
|
| No log | 3.9432 | 2500 | 0.1106 | 0.9861 | 0.9859 | |
|
| 0.0267 | 4.1009 | 2600 | 0.1202 | 0.9861 | 0.9861 | |
|
| 0.0267 | 4.2587 | 2700 | 0.1207 | 0.9841 | 0.9841 | |
|
| 0.0267 | 4.4164 | 2800 | 0.1208 | 0.9841 | 0.9841 | |
|
| 0.0267 | 4.5741 | 2900 | 0.1215 | 0.9841 | 0.9841 | |
|
| 0.0267 | 4.7319 | 3000 | 0.1216 | 0.9841 | 0.9841 | |
|
| 0.0267 | 4.8896 | 3100 | 0.1215 | 0.9841 | 0.9841 | |
|
| 0.0267 | 5.0473 | 3200 | 0.1350 | 0.9861 | 0.9861 | |
|
| 0.0267 | 5.2050 | 3300 | 0.1165 | 0.9880 | 0.9880 | |
|
| 0.0267 | 5.3628 | 3400 | 0.1166 | 0.9880 | 0.9880 | |
|
| 0.0267 | 5.5205 | 3500 | 0.1167 | 0.9880 | 0.9880 | |
|
| 0.0267 | 5.6782 | 3600 | 0.1168 | 0.9880 | 0.9880 | |
|
| 0.0267 | 5.8360 | 3700 | 0.1212 | 0.9861 | 0.9860 | |
|
| 0.0267 | 5.9937 | 3800 | 0.1213 | 0.9861 | 0.9860 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
