lora-legal-model – AI Model by Fatma5000 | AlphaNeural AI

You can deploy this model and start earning money today!

Fatma5000/
lora-legal-model

like

0

generated_from_trainer

whyredfire/legal-bart-summarizer

Views

No views yet

lora-legal-model

This model is a fine-tuned version of whyredfire/legal-bart-summarizer on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.7279

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: 0.0002
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: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.9086	1.0	139	1.8359
1.8636	2.0	278	1.8032
1.8433	3.0	417	1.7853
1.8446	4.0	556	1.7663
1.8203	5.0	695	1.7571
1.7915	6.0	834	1.7483
1.766	7.0	973	1.7323
1.7766	8.0	1112	1.7329
1.7505	9.0	1251	1.7283
1.7757	10.0	1390	1.7279

Framework versions

PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1