metadata
library_name: transformers
license: apache-2.0
base_model: dadashzadeh/roberta-sentiment-persian
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Bert-Sentiment-Fa
results: []
Bert-Sentiment-Fa
This model is a fine-tuned version of dadashzadeh/roberta-sentiment-persian on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3240
- Accuracy: 0.8375
- F1: 0.8225
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: 8
- eval_batch_size: 8
- 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 | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 270 | 0.6400 | 0.8292 | 0.8140 |
| 0.256 | 2.0 | 540 | 0.8620 | 0.8083 | 0.7919 |
| 0.256 | 3.0 | 810 | 0.9867 | 0.8375 | 0.8239 |
| 0.1045 | 4.0 | 1080 | 1.0124 | 0.8375 | 0.8213 |
| 0.1045 | 5.0 | 1350 | 1.0423 | 0.825 | 0.8135 |
| 0.0397 | 6.0 | 1620 | 1.3452 | 0.8292 | 0.8136 |
| 0.0397 | 7.0 | 1890 | 1.1964 | 0.8333 | 0.8192 |
| 0.0119 | 8.0 | 2160 | 1.3196 | 0.8292 | 0.8140 |
| 0.0119 | 9.0 | 2430 | 1.3148 | 0.8292 | 0.8138 |
| 0.0043 | 10.0 | 2700 | 1.3240 | 0.8375 | 0.8225 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1