bart-cnn-samsum-peft

This model is a fine-tuned version of facebook/bart-large-cnn on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 0.4334

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.4513	1.0	37	0.5301
0.45	2.0	74	0.5104
0.4505	3.0	111	0.4969
0.4882	4.0	148	0.4857
0.4246	5.0	185	0.4759
0.386	6.0	222	0.4672
0.3959	7.0	259	0.4599
0.4179	8.0	296	0.4536
0.427	9.0	333	0.4480
0.3997	10.0	370	0.4435
0.4041	11.0	407	0.4400
0.4021	12.0	444	0.4371
0.3551	13.0	481	0.4351
0.3619	14.0	518	0.4338
0.3768	15.0	555	0.4334

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1