mbart-large-cc25-ge-en-to-hi

This model is a fine-tuned version of facebook/mbart-large-cc25 on the hindi_english_machine_translation dataset. It achieves the following results on the evaluation set:

• Loss: 1.3397
• Bleu: 4.5974
• Gen Len: 66.244

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.4602	1.0	135739	1.3397	4.5974	66.244

Framework versions

• Transformers 4.19.1
• Pytorch 1.11.0+cu102
• Datasets 1.18.0
• Tokenizers 0.12.1