bart-cnn-samsum-peft

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: 0.0894

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: 5e-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
0.1055	1.0	74	0.1344
0.0941	2.0	148	0.1314
0.1007	3.0	222	0.1292
0.0683	4.0	296	0.1195
0.0647	5.0	370	0.1081
0.0628	6.0	444	0.1015
0.0611	7.0	518	0.0992
0.0502	8.0	592	0.0957
0.045	9.0	666	0.0920
0.0512	10.0	740	0.0931
0.0465	11.0	814	0.0926
0.0478	12.0	888	0.0902
0.0517	13.0	962	0.0902
0.0441	14.0	1036	0.0896
0.0484	15.0	1110	0.0894

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Tokenizers 0.15.1