metadata

library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: ModernBERT-ar-base-small4
    results: []

ModernBERT-ar-base-tiny

This model was trained on Fineweb2 Ar sample dataset. The tokenizer was also trained using the same dataset.
See sample code (usage and training) and initial post
Updated: Jan. 12, 2025.

Model description

ModernBERT Arabic (MLM) experiment.

Intended uses & limitations

Educational and explorational uses only. Limited data, not fully trained.

Training and evaluation data

Evaluation on 5% of the data, uses 2 GPUs.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 12
eval_batch_size: 12
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 24
total_eval_batch_size: 24
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 50000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.49.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0