mbart-large-50-finetuned-ua-gec-2.0

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: 0.4067
• Rouge1: 18.2963
• Rouge2: 10.2365
• Rougel: 18.2593
• Rougelsum: 18.2759
• Gen Len: 28.6533

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.2043	1.0	2020	0.3299	18.4389	10.2365	18.3963	18.4009	28.6513
0.1058	2.0	4040	0.3667	18.2963	10.2365	18.2593	18.2759	28.6207
0.0585	3.0	6060	0.4067	18.2963	10.2365	18.2593	18.2759	28.6533

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3