mbart-en-ne-sentence-translation

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9597
• Bleu: 48.1358
• Gen Len: 9.3

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.9421	1.0	7	1.7883	10.4307	9.1
1.5462	2.0	14	1.3980	7.5693	7.5
1.0467	3.0	21	0.9333	45.1288	9.4
0.4864	4.0	28	0.9698	48.1358	9.3
0.4757	5.0	35	0.9597	48.1358	9.3

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1