metadata
base_model: mavinsao/mi-roberta-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: mi-roberta-v2-finetuned-mental-illness
results: []
mi-roberta-v2-finetuned-mental-illness
This model is a fine-tuned version of mavinsao/mi-roberta-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4985
- Accuracy: 0.8802
- F1: 0.8805
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|---|
| 0.553 | 1.0 | 2633 | 0.4073 | 0.8708 | 0.8719 |
| 0.359 | 2.0 | 5266 | 0.3919 | 0.8775 | 0.8778 |
| 0.2753 | 3.0 | 7899 | 0.4312 | 0.8771 | 0.8777 |
| 0.2153 | 4.0 | 10532 | 0.4715 | 0.8798 | 0.8797 |
| 0.1753 | 5.0 | 13165 | 0.4985 | 0.8802 | 0.8805 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2