bart-large-cnn-1000-sum-pad-early-tfidf1

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: 0.8527
• Rouge1: 24.6303
• Rouge2: 11.0396
• Rougel: 19.1384
• Rougelsum: 20.94
• Gen Len: 67.84

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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.3304	1.0	1000	0.7234	25.9428	12.5482	21.0784	23.6041	64.68
0.1502	2.0	2000	0.8527	24.6303	11.0396	19.1384	20.94	67.84

Framework versions

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