bart-stats-extract

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: 0.3450
• Rouge1: 62.188
• Rouge2: 51.5988
• Rougel: 55.8383
• Rougelsum: 58.4919
• Gen Len: 90.4286

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
No log	1.0	4	1.0447	51.2166	37.2933	44.8635	47.5954	74.0
No log	2.0	8	0.5919	55.0964	43.0158	49.4166	51.4412	92.2857
No log	3.0	12	0.4159	60.2619	48.694	54.0969	54.9467	95.1429
No log	4.0	16	0.3450	62.188	51.5988	55.8383	58.4919	90.4286

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3