metadata
license: cc-by-4.0
base_model: indiejoseph/bert-base-cantonese
tags:
- generated_from_trainer
model-index:
- name: bert-suicide-detection-hk
results: []
bert-suicide-detection-hk
This model is a fine-tuned version of indiejoseph/bert-base-cantonese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0004
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 |
|---|---|---|---|
| 0.2689 | 0.4630 | 50 | 0.0547 |
| 0.106 | 0.9259 | 100 | 0.0343 |
| 0.0657 | 1.3889 | 150 | 0.0187 |
| 0.0465 | 1.8519 | 200 | 0.0005 |
| 0.026 | 2.3148 | 250 | 0.0180 |
| 0.0069 | 2.7778 | 300 | 0.0005 |
| 0.0105 | 3.2407 | 350 | 0.0012 |
| 0.0003 | 3.7037 | 400 | 0.0029 |
| 0.0023 | 4.1667 | 450 | 0.0004 |
| 0.0002 | 4.6296 | 500 | 0.0004 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1