distilbart-summarization-base-fulllayers

This model is a fine-tuned version of sshleifer/distilbart-xsum-6-6 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8165

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.1052	0.1882	500	2.0091
1.987	0.3764	1000	1.9407
1.9688	0.5645	1500	1.9045
1.9299	0.7527	2000	1.8716
1.9114	0.9409	2500	1.8527
1.72	1.1291	3000	1.8458
1.6935	1.3173	3500	1.8364
1.6997	1.5055	4000	1.8282
1.6546	1.6936	4500	1.8212
1.7309	1.8818	5000	1.8165

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0