metadata
license: apache-2.0
base_model: sharif-dal/dal-bert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: dal-bert-finetuned-sentiment_classifier(binary)
results: []
widget:
- text: اه این غذا خیلی آشغاله!
dal-bert-finetuned-emotion
This model is a fine-tuned version of sharif-dal/dal-bert on snappfood's comments dataset.
- 0 -> Positive sentiment
- 1 -> Negative sentiment
It achieves the following results on the evaluation set:
- Loss: 0.2893
- Accuracy: 0.8821
- F1: 0.8820
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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3131 | 1.0 | 1086 | 0.2859 | 0.8810 | 0.8808 |
| 0.2506 | 2.0 | 2172 | 0.2893 | 0.8821 | 0.8820 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2