metadata
tags:
- generated_from_trainer
datasets:
- emotone_ar
metrics:
- accuracy
- f1
model-index:
- name: bert-base-arabic-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotone_ar
type: emotone_ar
config: default
split: train[:90%]
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7266401590457257
- name: F1
type: f1
value: 0.7258317874418239
bert-base-arabic-finetuned-emotion
This model is a fine-tuned version of asafaya/bert-base-arabic on the emotone_ar dataset. It achieves the following results on the evaluation set:
- Loss: 0.9079
- Accuracy: 0.7266
- F1: 0.7258
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.2471 | 1.0 | 142 | 0.8635 | 0.7078 | 0.6951 |
| 0.7906 | 2.0 | 284 | 0.8124 | 0.7266 | 0.7202 |
| 0.5983 | 3.0 | 426 | 0.8331 | 0.7336 | 0.7262 |
| 0.4615 | 4.0 | 568 | 0.8542 | 0.7266 | 0.7240 |
| 0.3573 | 5.0 | 710 | 0.8924 | 0.7286 | 0.7274 |
| 0.2969 | 6.0 | 852 | 0.9079 | 0.7266 | 0.7258 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2