metadata
license: apache-2.0
base_model: dadashzadeh/tiny-bert-Sentiment-persian
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-bert-Sentiment-persian
results: []
tiny-bert-Sentiment-persian
This model is a fine-tuned version of dadashzadeh/tiny-bert-Sentiment-persian on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6538
- Accuracy: 0.7287
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 22
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8279 | 1.0 | 2384 | 0.7849 | 0.6544 |
| 0.8218 | 2.0 | 4768 | 0.7674 | 0.6587 |
| 0.8155 | 3.0 | 7152 | 0.7421 | 0.6821 |
| 0.8037 | 4.0 | 9536 | 0.7378 | 0.6829 |
| 0.799 | 5.0 | 11920 | 0.7983 | 0.6324 |
| 0.7943 | 6.0 | 14304 | 0.7071 | 0.7015 |
| 0.7764 | 7.0 | 16688 | 0.7438 | 0.6756 |
| 0.7763 | 8.0 | 19072 | 0.7328 | 0.6829 |
| 0.7717 | 9.0 | 21456 | 0.7300 | 0.6825 |
| 0.7733 | 10.0 | 23840 | 0.6943 | 0.7106 |
| 0.7517 | 11.0 | 26224 | 0.6859 | 0.7210 |
| 0.7515 | 12.0 | 28608 | 0.6538 | 0.7287 |
| 0.7497 | 13.0 | 30992 | 0.6930 | 0.7084 |
| 0.7177 | 14.0 | 33376 | 0.7055 | 0.6972 |
| 0.734 | 15.0 | 35760 | 0.6893 | 0.7123 |
| 0.7247 | 16.0 | 38144 | 0.7026 | 0.7045 |
| 0.7317 | 17.0 | 40528 | 0.6711 | 0.7210 |
| 0.7145 | 18.0 | 42912 | 0.7192 | 0.6911 |
| 0.7136 | 19.0 | 45296 | 0.6951 | 0.7102 |
| 0.7159 | 20.0 | 47680 | 0.6776 | 0.7197 |
| 0.7278 | 21.0 | 50064 | 0.6814 | 0.7162 |
| 0.6952 | 22.0 | 52448 | 0.6829 | 0.7158 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1