---
license: cc-by-4.0
base_model: indiejoseph/bert-base-cantonese
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-suicide-detection-hk
  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. -->

# bert-suicide-detection-hk

This model is a fine-tuned version of [indiejoseph/bert-base-cantonese](https://huggingface.co/indiejoseph/bert-base-cantonese) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1071
- Accuracy: 0.9785

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.5169        | 0.0962 | 20   | 0.4365          | 0.8065   |
| 0.3487        | 0.1923 | 40   | 0.3232          | 0.8602   |
| 0.1785        | 0.2885 | 60   | 0.1470          | 0.9462   |
| 0.192         | 0.3846 | 80   | 0.1264          | 0.9570   |
| 0.0329        | 0.4808 | 100  | 0.1857          | 0.9570   |
| 0.1432        | 0.5769 | 120  | 0.2023          | 0.9247   |
| 0.3458        | 0.6731 | 140  | 0.1269          | 0.9677   |
| 0.234         | 0.7692 | 160  | 0.1510          | 0.9462   |
| 0.179         | 0.8654 | 180  | 0.1102          | 0.9677   |
| 0.1873        | 0.9615 | 200  | 0.1140          | 0.9570   |
| 0.1519        | 1.0577 | 220  | 0.2102          | 0.9462   |
| 0.0453        | 1.1538 | 240  | 0.3150          | 0.9247   |
| 0.0341        | 1.25   | 260  | 0.1401          | 0.9570   |
| 0.0316        | 1.3462 | 280  | 0.1634          | 0.9677   |
| 0.1082        | 1.4423 | 300  | 0.1069          | 0.9785   |
| 0.0954        | 1.5385 | 320  | 0.0819          | 0.9785   |
| 0.0472        | 1.6346 | 340  | 0.1686          | 0.9677   |
| 0.1563        | 1.7308 | 360  | 0.0379          | 0.9785   |
| 0.1812        | 1.8269 | 380  | 0.1218          | 0.9677   |
| 0.1276        | 1.9231 | 400  | 0.0785          | 0.9892   |
| 0.0772        | 2.0192 | 420  | 0.0788          | 0.9892   |
| 0.0022        | 2.1154 | 440  | 0.1028          | 0.9570   |
| 0.0011        | 2.2115 | 460  | 0.1562          | 0.9570   |
| 0.076         | 2.3077 | 480  | 0.1219          | 0.9785   |
| 0.0012        | 2.4038 | 500  | 0.1159          | 0.9570   |
| 0.1572        | 2.5    | 520  | 0.0987          | 0.9785   |
| 0.0359        | 2.5962 | 540  | 0.1208          | 0.9785   |
| 0.0737        | 2.6923 | 560  | 0.0974          | 0.9785   |
| 0.1555        | 2.7885 | 580  | 0.1363          | 0.9785   |
| 0.0928        | 2.8846 | 600  | 0.0681          | 0.9785   |
| 0.0008        | 2.9808 | 620  | 0.0611          | 0.9677   |
| 0.0606        | 3.0769 | 640  | 0.0979          | 0.9785   |
| 0.0693        | 3.1731 | 660  | 0.0768          | 0.9677   |
| 0.0005        | 3.2692 | 680  | 0.0925          | 0.9677   |
| 0.0006        | 3.3654 | 700  | 0.0922          | 0.9677   |
| 0.0005        | 3.4615 | 720  | 0.0907          | 0.9677   |
| 0.0004        | 3.5577 | 740  | 0.0923          | 0.9677   |
| 0.056         | 3.6538 | 760  | 0.0906          | 0.9570   |
| 0.0006        | 3.75   | 780  | 0.0913          | 0.9785   |
| 0.056         | 3.8462 | 800  | 0.1173          | 0.9785   |
| 0.0005        | 3.9423 | 820  | 0.1341          | 0.9785   |
| 0.0004        | 4.0385 | 840  | 0.1199          | 0.9785   |
| 0.0004        | 4.1346 | 860  | 0.1161          | 0.9785   |
| 0.0003        | 4.2308 | 880  | 0.1156          | 0.9785   |
| 0.0385        | 4.3269 | 900  | 0.0859          | 0.9785   |
| 0.0028        | 4.4231 | 920  | 0.0961          | 0.9785   |
| 0.0003        | 4.5192 | 940  | 0.1021          | 0.9785   |
| 0.0014        | 4.6154 | 960  | 0.1071          | 0.9785   |
| 0.0003        | 4.7115 | 980  | 0.1089          | 0.9785   |
| 0.0003        | 4.8077 | 1000 | 0.1082          | 0.9785   |
| 0.0576        | 4.9038 | 1020 | 0.1066          | 0.9785   |
| 0.0003        | 5.0    | 1040 | 0.1071          | 0.9785   |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1