Modelpublic

gates04/Structured-NF4-KD-SD-NID

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes2downloads

Model Card

Structured-NF4-KD-SD-NID

This model is a fine-tuned version of gates04/Structured-NF4-KD-NID on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.0167
—Accuracy: 0.9922
—Precision: 0.9797
—Recall: 0.9349
—F1 score: 0.9446

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
—trainbatchsize: 300
—evalbatchsize: 300
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 5
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 score
0.0297	1.0	3960	0.0223	0.9912	0.9325	0.9155	0.9185
0.0217	2.0	7920	0.0196	0.9917	0.9754	0.9261	0.9335
0.0166	3.0	11880	0.0186	0.9917	0.9786	0.9275	0.9354
0.0158	4.0	15840	0.0170	0.9921	0.9774	0.9354	0.9442
0.0129	5.0	19800	0.0167	0.9922	0.9797	0.9349	0.9446

Framework versions

—Transformers 4.50.0
—Pytorch 2.6.0+cu124
—Datasets 3.5.0
—Tokenizers 0.21.1