metadata
license: cc-by-nc-4.0
base_model: AIMH/mental-bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BERTForDetectingDepression-Twitter2015
results: []
BERTForDetectingDepression-Twitter2015
This model is a fine-tuned version of AIMH/mental-bert-base-cased on this dataset. It achieves the following results on the evaluation set:
- Loss: 0.5232
- Accuracy: 0.9276
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Eval Precision: 0.9206730769230769
Eval Recall: 0.9364303178484108
Eval Accuracy: 0.9275629220380601
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1.8919952478487808e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 36
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3347 | 1.0 | 3665 | 0.3384 | 0.9061 |
| 0.152 | 2.0 | 7330 | 0.4665 | 0.9227 |
| 0.0444 | 3.0 | 10995 | 0.5232 | 0.9276 |
| 0.0057 | 4.0 | 14660 | 0.5890 | 0.9269 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1