metadata
license: apache-2.0
base_model: alex-miller/ODABert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: cva-quant-weighted-classifier
results: []
cva-quant-weighted-classifier
This model is a fine-tuned version of alex-miller/ODABert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5278
- Accuracy: 0.8214
- F1: 0.8148
- Precision: 0.7857
- Recall: 0.8462
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-06
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6851 | 1.0 | 7 | 0.6688 | 0.5 | 0.5882 | 0.4762 | 0.7692 |
| 0.6626 | 2.0 | 14 | 0.6466 | 0.6786 | 0.7097 | 0.6111 | 0.8462 |
| 0.6353 | 3.0 | 21 | 0.6255 | 0.75 | 0.7586 | 0.6875 | 0.8462 |
| 0.6157 | 4.0 | 28 | 0.6029 | 0.7857 | 0.7857 | 0.7333 | 0.8462 |
| 0.5949 | 5.0 | 35 | 0.5822 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
| 0.5808 | 6.0 | 42 | 0.5638 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
| 0.5585 | 7.0 | 49 | 0.5493 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
| 0.5464 | 8.0 | 56 | 0.5376 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
| 0.5326 | 9.0 | 63 | 0.5304 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
| 0.5236 | 10.0 | 70 | 0.5278 | 0.8214 | 0.8148 | 0.7857 | 0.8462 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1