mbart-large-50-en-es-translation-lr-1e-05-weight-decay-0.01

This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9547
• Bleu: 45.0896
• Rouge: {'rouge1': 0.7050843983318068, 'rouge2': 0.5221826018405332, 'rougeL': 0.6843669248955093, 'rougeLsum': 0.6845499780252107}

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: 1e-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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge
1.4571	1.0	4500	1.0262	41.9188	{'rouge1': 0.6701489298042851, 'rouge2': 0.4850120961190509, 'rougeL': 0.6479081216501843, 'rougeLsum': 0.6480345623292922}
0.889	2.0	9000	0.9559	44.3378	{'rouge1': 0.6920481616267358, 'rouge2': 0.5087283264258592, 'rougeL': 0.6709294966142768, 'rougeLsum': 0.6710449317682404}
0.7134	3.0	13500	0.9416	44.9705	{'rouge1': 0.7026762914671131, 'rouge2': 0.5192700210995049, 'rougeL': 0.6817974408692513, 'rougeLsum': 0.6819680202609157}
0.6098	4.0	18000	0.9547	45.1741	{'rouge1': 0.7051668954804624, 'rouge2': 0.5222186626492409, 'rougeL': 0.6844002112351866, 'rougeLsum': 0.6845851183829141}

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4.dev0
• Tokenizers 0.13.3