multilabel-patent-classification – AI Model by zgurney | AlphaNeural AI

You can deploy this model and start earning money today!

zgurney/
multilabel-patent-classification

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

multilabel-patent-classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1331
Accuracy: 0.9524
Macro F1: 0.4905
Macro Precision: 0.6499
Macro Recall: 0.4196

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1	Macro Precision	Macro Recall
0.2546	1.0	942	0.1558	0.9444	0.3535	0.5197	0.2952
0.1449	2.0	1884	0.1374	0.9495	0.4241	0.6120	0.3595
0.1203	3.0	2826	0.1338	0.9514	0.4718	0.6542	0.4072
0.1038	4.0	3768	0.1325	0.9519	0.4867	0.6464	0.4175
0.0922	5.0	4710	0.1331	0.9524	0.4905	0.6499	0.4196

Framework versions

Transformers 4.48.0
Pytorch 2.2.2
Datasets 3.2.0
Tokenizers 0.21.0