bart-base-carvia_nlc2cmd_BART

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

• Loss: 0.0000
• Rouge1: 88.8889
• Rouge2: 85.7143
• Rougel: 88.8889
• Rougelsum: 88.8889
• Gen Len: 20.0

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: 5e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.004	1.0	1625	0.0000	88.8889	85.7143	88.8889	88.8889	20.0
0.0028	2.0	3250	0.0000	98.0519	97.4952	98.0519	98.0444	20.0
0.0014	3.0	4875	0.0000	88.8889	85.7143	88.8889	88.8889	20.0
0.0	4.0	6500	0.0000	88.8889	85.7143	88.8889	88.8889	20.0
0.0	5.0	8125	0.0000	88.8889	85.7143	88.8889	88.8889	20.0

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.3
• Tokenizers 0.13.3