bart-base-finetuned-xsum

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: 1.1690
• Rouge1: 16.5953
• Rouge2: 12.3097
• Rougel: 15.9007
• Rougelsum: 16.4053
• Bleu-1: 0.0062
• Bleu-2: 0.0057
• Bleu-3: 0.0054
• Bleu-4: 0.0052
• 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: 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	Rouge1	Rouge2	Rougel	Rougelsum	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Gen Len
2.3294	1.0	28600	1.1690	16.5953	12.3097	15.9007	16.4053	0.0062	0.0057	0.0054	0.0052	20.0

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3