metadata
library_name: transformers
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased
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 HooshvareLab/bert-fa-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1484
- Accuracy: 0.8417
- F1: 0.8524
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 68 | 0.5099 | 0.8042 | 0.8062 |
| No log | 2.0 | 136 | 0.6354 | 0.8083 | 0.8079 |
| No log | 3.0 | 204 | 0.6376 | 0.8458 | 0.8575 |
| No log | 4.0 | 272 | 0.8837 | 0.8292 | 0.8373 |
| No log | 5.0 | 340 | 0.9432 | 0.8167 | 0.8335 |
| No log | 6.0 | 408 | 0.9680 | 0.8125 | 0.8128 |
| No log | 7.0 | 476 | 0.8569 | 0.8292 | 0.8402 |
| 0.1247 | 8.0 | 544 | 1.0439 | 0.8542 | 0.8628 |
| 0.1247 | 9.0 | 612 | 1.0181 | 0.8375 | 0.8451 |
| 0.1247 | 10.0 | 680 | 1.0169 | 0.8458 | 0.8556 |
| 0.1247 | 11.0 | 748 | 1.1128 | 0.8292 | 0.8348 |
| 0.1247 | 12.0 | 816 | 1.1325 | 0.8333 | 0.8382 |
| 0.1247 | 13.0 | 884 | 1.1458 | 0.85 | 0.8622 |
| 0.1247 | 14.0 | 952 | 1.1439 | 0.85 | 0.8622 |
| 0.0062 | 15.0 | 1020 | 1.1484 | 0.8417 | 0.8524 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1