albert-fa-zwnj-base-v2-finetuned-bmd-20241021-LOSO-section-out1
This model is a fine-tuned version of HooshvareLab/albert-fa-zwnj-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1964
- Accuracy: 0.3103
- F1: 0.2745
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: 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.1384 | 1.0 | 14 | 1.2494 | 0.3448 | 0.1768 |
| 1.1313 | 2.0 | 28 | 1.0923 | 0.3103 | 0.1724 |
| 0.9349 | 3.0 | 42 | 1.2456 | 0.3448 | 0.2468 |
| 0.6109 | 4.0 | 56 | 1.3296 | 0.2069 | 0.1970 |
| 0.3213 | 5.0 | 70 | 1.4808 | 0.3793 | 0.3711 |
| 0.1212 | 6.0 | 84 | 1.9444 | 0.2414 | 0.2352 |
| 0.0406 | 7.0 | 98 | 2.6696 | 0.4138 | 0.3814 |
| 0.0239 | 8.0 | 112 | 2.6279 | 0.2759 | 0.2705 |
| 0.005 | 9.0 | 126 | 3.0941 | 0.3103 | 0.2745 |
| 0.0041 | 10.0 | 140 | 3.1964 | 0.3103 | 0.2745 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1