Model-Darija-finetune

This model is a fine-tuned version of MBZUAI-Paris/Atlas-Chat-9B on the arrow dataset.

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 3407
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Use adafactor and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Framework versions

• Transformers 4.49.0
• Pytorch 2.1.0+cu121
• Datasets 3.4.1
• Tokenizers 0.21.1