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: 0.6672
- Accuracy: 0.7279
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: 20
- eval_batch_size: 20
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.696 | 1.0 | 1431 | 0.6928 | 0.7136 |
0.6826 | 2.0 | 2862 | 0.6893 | 0.7153 |
0.6737 | 3.0 | 4293 | 0.6620 | 0.7257 |
0.6801 | 4.0 | 5724 | 0.6579 | 0.7317 |
0.6682 | 5.0 | 7155 | 0.6662 | 0.7270 |
0.6756 | 6.0 | 8586 | 0.6672 | 0.7279 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1