metadata
library_name: transformers
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-fa-uncased-augmented-WithTokens
results: []
bert-fa-uncased-augmented-WithTokens
This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4364
- Accuracy: 0.8259
- F1: 0.8255
- Precision: 0.8272
- Recall: 0.8249
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6041 | 1.0 | 986 | 0.4246 | 0.8174 | 0.8158 | 0.8160 | 0.8157 |
| 0.3503 | 2.0 | 1972 | 0.4364 | 0.8259 | 0.8255 | 0.8272 | 0.8249 |
| 0.2176 | 3.0 | 2958 | 0.5571 | 0.8248 | 0.8231 | 0.8260 | 0.8230 |
| 0.1321 | 4.0 | 3944 | 0.7621 | 0.8134 | 0.8120 | 0.8136 | 0.8117 |
Framework versions
- Transformers 4.55.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4