metadata
widget:
- text: I feel lonely. I'm not sure if I will be fine. But I'm trying.
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned-roberta-depression
results: []
finetuned-roberta-depression
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1580
- Accuracy: 0.969
Model description
- Label 0: Non-Depressive
- Label 1: Depressive
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 188 | 0.1907 | 0.965 |
| No log | 2.0 | 376 | 0.1912 | 0.966 |
| 0.1711 | 3.0 | 564 | 0.1580 | 0.969 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0