bart-large-cnn-finetuned-weaksup-1000-pad-early-new

This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4896
• Rouge1: 29.4505
• Rouge2: 14.4038
• Rougel: 23.1757
• Rougelsum: 26.3813
• Gen Len: 66.55

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.154	1.0	1000	0.4255	27.2971	12.4331	20.851	23.9583	66.64
0.0806	2.0	2000	0.4896	29.4505	14.4038	23.1757	26.3813	66.55

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2
• Datasets 1.18.3
• Tokenizers 0.11.0