|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: mental/mental-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: mental_roberta_suicide |
|
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. --> |
|
|
|
# mental_roberta_suicide |
|
|
|
This model is a fine-tuned version of [mental/mental-roberta-base](https://huggingface.co/mental/mental-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5994 |
|
- Accuracy: 0.7446 |
|
- F1: 0.7487 |
|
- Precision: 0.7368 |
|
- Recall: 0.7609 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 7 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.6934 | 0.97 | 25 | 0.6934 | 0.5 | 0.0 | 0.0 | 0.0 | |
|
| 0.691 | 1.98 | 51 | 0.6905 | 0.5 | 0.0213 | 0.5 | 0.0109 | |
|
| 0.6866 | 2.99 | 77 | 0.6666 | 0.6522 | 0.5493 | 0.78 | 0.4239 | |
|
| 0.6427 | 4.0 | 103 | 0.5652 | 0.7174 | 0.7011 | 0.7439 | 0.6630 | |
|
| 0.5594 | 4.97 | 128 | 0.5586 | 0.7228 | 0.6982 | 0.7662 | 0.6413 | |
|
| 0.521 | 5.98 | 154 | 0.5405 | 0.7283 | 0.7283 | 0.7283 | 0.7283 | |
|
| 0.4097 | 6.8 | 175 | 0.5994 | 0.7446 | 0.7487 | 0.7368 | 0.7609 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
