metadata
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased-clf-persiannews
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: war_intent_detection_fa
results: []
war_intent_detection_fa
This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased-clf-persiannews on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1913
- Accuracy: 0.9300
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.6751 | 1.0 | 805 | 0.2832 | 0.8974 |
| 0.2366 | 2.0 | 1610 | 0.2369 | 0.9146 |
| 0.2047 | 3.0 | 2415 | 0.1981 | 0.9271 |
| 0.1752 | 4.0 | 3220 | 0.2019 | 0.9287 |
| 0.1565 | 5.0 | 4025 | 0.2046 | 0.9220 |
| 0.1515 | 6.0 | 4830 | 0.2037 | 0.9271 |
| 0.1468 | 7.0 | 5635 | 0.1975 | 0.9282 |
| 0.1341 | 8.0 | 6440 | 0.1982 | 0.9284 |
| 0.1345 | 9.0 | 7245 | 0.1939 | 0.9293 |
| 0.135 | 10.0 | 8050 | 0.1913 | 0.9300 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1