uncased-clf-digimag_v2
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: 1.2940
- Accuracy: 0.6481
- F1: 0.6482
- Precision: 0.6531
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 | 1.1060 | 0.5199 | 0.4953 | 0.5440 |
| No log | 2.0 | 442 | 0.9657 | 0.6220 | 0.6234 | 0.6304 |
| 1.0805 | 3.0 | 663 | 0.9398 | 0.6583 | 0.6591 | 0.6626 |
| 1.0805 | 4.0 | 884 | 0.9883 | 0.6504 | 0.6511 | 0.6710 |
| 0.6186 | 5.0 | 1105 | 1.0283 | 0.6459 | 0.6456 | 0.6506 |
| 0.6186 | 6.0 | 1326 | 1.1060 | 0.6527 | 0.6503 | 0.6602 |
| 0.3377 | 7.0 | 1547 | 1.1505 | 0.6652 | 0.6642 | 0.6786 |
| 0.3377 | 8.0 | 1768 | 1.2264 | 0.6583 | 0.6569 | 0.6614 |
| 0.3377 | 9.0 | 1989 | 1.2719 | 0.6447 | 0.6448 | 0.6480 |
| 0.1804 | 10.0 | 2210 | 1.2940 | 0.6481 | 0.6482 | 0.6531 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.