Terjman-Large

This is a translation model from English to Moroccan darija. It is a finetuned version of "Helsinki-NLP/opus-mt-tc-big-en-ar" on the "BounharAbdelaziz/English-to-Moroccan-Darija" dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 96
• eval_batch_size: 96
• seed: 42
• warmup_ratio: 0.03
• gradient_accumulation_steps: 2
• total_train_batch_size: 182
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Framework versions

• Transformers 4.39.2
• Pytorch 2.2.2+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2