metadata
tags:
- generated_from_trainer
datasets:
- sem_eval_2018_task_1
metrics:
- f1
- accuracy
base_model: aubmindlab/bert-large-arabertv02-twitter
model-index:
- name: arabert-emotions-classification
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: sem_eval_2018_task_1
type: sem_eval_2018_task_1
config: subtask5.arabic
split: validation
args: subtask5.arabic
metrics:
- type: f1
value: 0.7189952904238618
name: F1
- type: accuracy
value: 0.2717948717948718
name: Accuracy
arabert-emotions-classification
This model is a fine-tuned version of aubmindlab/bert-large-arabertv02-twitter on the sem_eval_2018_task_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2636
- F1: 0.7190
- Roc Auc: 0.8061
- Accuracy: 0.2718
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 114 | 0.3055 | 0.6653 | 0.7674 | 0.2462 |
| No log | 2.0 | 228 | 0.2776 | 0.6987 | 0.7887 | 0.2701 |
| No log | 3.0 | 342 | 0.2680 | 0.7062 | 0.7943 | 0.2769 |
| No log | 4.0 | 456 | 0.2644 | 0.7140 | 0.8032 | 0.2718 |
| 0.2701 | 5.0 | 570 | 0.2636 | 0.7190 | 0.8061 | 0.2718 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3