|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: criminal-case-classifier1 |
|
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. --> |
|
|
|
# criminal-case-classifier1 |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8530 |
|
- Accuracy: 0.5077 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 300 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9563 | 0.31 | 10 | 1.1314 | 0.3385 | |
|
| 1.1275 | 0.62 | 20 | 1.0607 | 0.4769 | |
|
| 1.0692 | 0.94 | 30 | 1.0871 | 0.2923 | |
|
| 1.0717 | 1.25 | 40 | 1.1759 | 0.4154 | |
|
| 1.0113 | 1.56 | 50 | 1.1322 | 0.3538 | |
|
| 0.8463 | 1.88 | 60 | 1.1809 | 0.3846 | |
|
| 0.8573 | 2.19 | 70 | 1.0676 | 0.4154 | |
|
| 0.8711 | 2.5 | 80 | 1.0690 | 0.3846 | |
|
| 0.809 | 2.81 | 90 | 1.1253 | 0.4154 | |
|
| 0.7148 | 3.12 | 100 | 1.0913 | 0.4769 | |
|
| 0.5847 | 3.44 | 110 | 1.0920 | 0.5077 | |
|
| 0.5486 | 3.75 | 120 | 1.0597 | 0.5538 | |
|
| 0.5184 | 4.06 | 130 | 1.1016 | 0.4769 | |
|
| 0.2637 | 4.38 | 140 | 1.1908 | 0.4923 | |
|
| 0.3562 | 4.69 | 150 | 1.0238 | 0.5385 | |
|
| 0.3292 | 5.0 | 160 | 1.1011 | 0.5692 | |
|
| 0.1333 | 5.31 | 170 | 1.3049 | 0.5385 | |
|
| 0.1256 | 5.62 | 180 | 1.2819 | 0.5538 | |
|
| 0.1415 | 5.94 | 190 | 1.4929 | 0.5231 | |
|
| 0.0942 | 6.25 | 200 | 1.5290 | 0.5538 | |
|
| 0.0548 | 6.56 | 210 | 1.4844 | 0.5538 | |
|
| 0.0457 | 6.88 | 220 | 1.6174 | 0.5077 | |
|
| 0.0226 | 7.19 | 230 | 1.6499 | 0.5538 | |
|
| 0.032 | 7.5 | 240 | 1.7371 | 0.5077 | |
|
| 0.0158 | 7.81 | 250 | 1.8099 | 0.5385 | |
|
| 0.0244 | 8.12 | 260 | 1.9706 | 0.4769 | |
|
| 0.0134 | 8.44 | 270 | 1.8825 | 0.5231 | |
|
| 0.0117 | 8.75 | 280 | 1.8414 | 0.5077 | |
|
| 0.0111 | 9.06 | 290 | 1.8478 | 0.5077 | |
|
| 0.0107 | 9.38 | 300 | 1.8530 | 0.5077 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
