metadata

base_model: aubmindlab/bert-base-arabertv02-twitter
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: AraBert-Arabic-Sentiment-Analysis
    results: []
license: apache-2.0
language:
  - ar
library_name: transformers

AraBert-Arabic-Sentiment-Analysis

This model is a fine-tuned version of AraBERT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5327
Macro F1: 0.6543
Accuracy: 0.8003

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: 16
eval_batch_size: 128
seed: 25
gradient_accumulation_steps: 2
total_train_batch_size: 32
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	497	0.5337	0.6219	0.7967
0.6177	2.0	994	0.5327	0.6543	0.8003

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Tokenizers 0.15.2