bart-large-cnn-ing-extraction-e4

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: 2.6226
• Rouge1: 10.8186
• Rouge2: 4.3032
• Rougel: 10.7802
• Rougelsum: 10.7952
• Gen Len: 57.5739

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
0.6235	1.0	762	3.1458	14.9141	5.5712	14.7529	14.8292	57.6903
0.2435	2.0	1524	2.2255	6.4408	2.4546	6.4219	6.4393	57.2955
0.1467	3.0	2286	2.9673	9.9243	3.9008	9.932	9.9268	57.6506
0.0627	4.0	3048	2.6226	10.8186	4.3032	10.7802	10.7952	57.5739

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3