metadata
library_name: peft
license: mit
base_model: djangodevloper/bert-base-sa-mental-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: mental-BERT_depression
results: []
mental-BERT_depression
This model is a fine-tuned version of djangodevloper/bert-base-sa-mental-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5075
- Accuracy: 0.7845
- Precision: 0.7873
- Recall: 0.7845
- F1: 0.7829
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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7931 | 1.0 | 969 | 0.5411 | 0.7683 | 0.7716 | 0.7683 | 0.7665 |
| 0.5491 | 2.0 | 1938 | 0.5121 | 0.7821 | 0.7844 | 0.7821 | 0.7806 |
| 0.5221 | 3.0 | 2907 | 0.5075 | 0.7845 | 0.7873 | 0.7845 | 0.7829 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0