metadata

base_model: aubmindlab/bert-large-arabertv02
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: arabert-sentiment-classification
    results: []

arabert-sentiment-classification

This model is a fine-tuned version of aubmindlab/bert-large-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7645
Macro F1: 0.7216
Accuracy: 0.7216

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: 32
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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	Macro F1	Accuracy
No log	1.0	249	1.0181	0.5867	0.5867
No log	2.0	498	0.7645	0.7216	0.7216

Framework versions

Transformers 4.34.0
Pytorch 1.12.0
Tokenizers 0.14.1