bart-large-cnn-finetuned-roundup-2-4

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: 1.0908
• Rouge1: 51.9961
• Rouge2: 32.3963
• Rougel: 32.1774
• Rougelsum: 50.1033
• Gen Len: 141.0

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	167	1.2152	52.234	33.1104	33.308	49.5516	142.0
No log	2.0	334	1.1054	52.7096	33.4698	33.9595	49.8736	140.3333
1.0437	3.0	501	1.0796	51.699	32.4255	34.0294	49.5276	141.7143
1.0437	4.0	668	1.0908	51.9961	32.3963	32.1774	50.1033	141.0

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1