bart-large-cnn-finetuned-new-100-pad-early

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: 0.9543
• Rouge1: 21.8858
• Rouge2: 8.1444
• Rougel: 16.5751
• Rougelsum: 19.163
• Gen Len: 66.8

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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	100	0.8692	20.2714	6.206	16.3362	18.7117	66.4
No log	2.0	200	0.9543	21.8858	8.1444	16.5751	19.163	66.8

Framework versions

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