cdc_influenza_bart-base-cnn

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: 0.5155
• Rouge1: 0.3829
• Rouge2: 0.3086
• Rougel: 0.3623
• Rougelsum: 0.3576
• 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: 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	2	0.8120	0.308	0.2272	0.2723	0.2758	20.0
No log	2.0	4	0.6427	0.3473	0.2635	0.3179	0.3189	20.0
No log	3.0	6	0.5496	0.3925	0.3203	0.3671	0.3642	20.0
No log	4.0	8	0.5155	0.3829	0.3086	0.3623	0.3576	20.0

Framework versions

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