bart-cnn-samsum-peft

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

• Loss: 0.1351

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
0.1088	1.0	148	0.1342
0.0754	2.0	296	0.1341
0.0947	3.0	444	0.1340
0.0982	4.0	592	0.1344
0.0704	5.0	740	0.1346
0.1018	6.0	888	0.1345
0.0904	7.0	1036	0.1341
0.091	8.0	1184	0.1346
0.0957	9.0	1332	0.1346
0.0785	10.0	1480	0.1345
0.104	11.0	1628	0.1348
0.1111	12.0	1776	0.1349
0.0839	13.0	1924	0.1350
0.0828	14.0	2072	0.1351
0.0925	15.0	2220	0.1351

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2