fine_tuned_he_to_tanach

This model is a fine-tuned version of google/mt5-large on a dataset that contains verses from the Bible translated in modern Hebrew.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1