metadata
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased-clf-digimag
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
model-index:
- name: uncased-clf-digimag_v3
results: []
uncased-clf-digimag_v3
This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased-clf-digimag on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2930
- Accuracy: 0.6481
- F1: 0.6481
- Precision: 0.6526
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| No log | 1.0 | 221 | 1.1058 | 0.5199 | 0.4953 | 0.5440 |
| No log | 2.0 | 442 | 0.9655 | 0.6220 | 0.6234 | 0.6304 |
| 1.0805 | 3.0 | 663 | 0.9397 | 0.6583 | 0.6591 | 0.6626 |
| 1.0805 | 4.0 | 884 | 0.9880 | 0.6515 | 0.6522 | 0.6720 |
| 0.6186 | 5.0 | 1105 | 1.0279 | 0.6459 | 0.6457 | 0.6510 |
| 0.6186 | 6.0 | 1326 | 1.1051 | 0.6527 | 0.6503 | 0.6595 |
| 0.3378 | 7.0 | 1547 | 1.1496 | 0.6640 | 0.6632 | 0.6776 |
| 0.3378 | 8.0 | 1768 | 1.2252 | 0.6583 | 0.6569 | 0.6614 |
| 0.3378 | 9.0 | 1989 | 1.2706 | 0.6459 | 0.6459 | 0.6492 |
| 0.1804 | 10.0 | 2210 | 1.2930 | 0.6481 | 0.6481 | 0.6526 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2