You can deploy this model and start earning money today!

3NTRPY-13/
bart-cnn-samsum-finetuned-lora

Name: bart-cnn-samsum-finetuned-lora
Availability: InStock

peft

safetensors

generated_from_trainer

3NTRPY-13/bart-cnn-samsum-finetuned

adapter

mit

Views

No views yet

bart-cnn-samsum-finetuned-lora

This model is a fine-tuned version of 3NTRPY-13/bart-cnn-samsum-finetuned on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1291

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.1181	1.0	74	0.1313
0.0938	2.0	148	0.1310
0.0863	3.0	222	0.1308
0.0969	4.0	296	0.1305
0.0995	5.0	370	0.1303
0.0874	6.0	444	0.1302
0.0869	7.0	518	0.1301
0.0817	8.0	592	0.1298
0.092	9.0	666	0.1291
0.0785	10.0	740	0.1293
0.0748	11.0	814	0.1293
0.1041	12.0	888	0.1292
0.0669	13.0	962	0.1290
0.0794	14.0	1036	0.1291
0.0727	15.0	1110	0.1291

Framework versions

PEFT 0.15.2
Transformers 4.49.0
Pytorch 2.5.1
Datasets 3.3.2
Tokenizers 0.21.0

3NTRPY-13/bart-cnn-samsum-finetuned-lora

bart-cnn-samsum-finetuned-lora

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

3NTRPY-13/
bart-cnn-samsum-finetuned-lora