metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Q3-PHQ
results: []
Q3-PHQ
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6063
- Accuracy: 0.69
- Mcc: 0.2901
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: 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 | Mcc |
|---|---|---|---|---|---|
| No log | 1.0 | 51 | 0.6793 | 0.635 | 0.0 |
| No log | 2.0 | 102 | 0.6683 | 0.5925 | 0.2198 |
| No log | 3.0 | 153 | 0.6685 | 0.6525 | 0.1651 |
| No log | 4.0 | 204 | 0.6108 | 0.675 | 0.2395 |
| No log | 5.0 | 255 | 0.6063 | 0.69 | 0.2901 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1