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: 0.4345
- Accuracy: 0.8627
- F1: 0.8098
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-06
- train_batch_size: 16
- eval_batch_size: 64
- 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 | 143 | 0.6861 | 0.7412 | 0.6297 |
| No log | 2.0 | 286 | 0.4557 | 0.8510 | 0.7951 |
| No log | 3.0 | 429 | 0.3941 | 0.8627 | 0.8116 |
| 0.5612 | 4.0 | 572 | 0.3894 | 0.8627 | 0.8081 |
| 0.5612 | 5.0 | 715 | 0.4092 | 0.8588 | 0.8071 |
| 0.5612 | 6.0 | 858 | 0.3987 | 0.8627 | 0.8077 |
| 0.2275 | 7.0 | 1001 | 0.4105 | 0.8784 | 0.8264 |
| 0.2275 | 8.0 | 1144 | 0.4192 | 0.8627 | 0.8071 |
| 0.2275 | 9.0 | 1287 | 0.4305 | 0.8667 | 0.8113 |
| 0.2275 | 10.0 | 1430 | 0.4345 | 0.8627 | 0.8098 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1