cdc_influenza_bart_large_cnn

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

• Loss: 0.1632
• Rouge1: 0.536
• Rouge2: 0.408
• Rougel: 0.4456
• Rougelsum: 0.4456
• Gen Len: 83.0

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: 32
• eval_batch_size: 32
• 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	1	0.2147	0.525	0.3844	0.4633	0.4633	77.5
No log	2.0	2	0.1895	0.5407	0.4076	0.4735	0.4735	79.25
No log	3.0	3	0.1725	0.5407	0.4037	0.4542	0.4542	80.25
No log	4.0	4	0.1632	0.536	0.408	0.4456	0.4456	83.0

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2