Modelpublic

Arifaa/distilbert-base-uncased-lora-text-classification

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes12downloads

Model Card

distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.0886
—Accuracy: {'accuracy': 0.885}

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: 0.001
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.4321	{'accuracy': 0.87}
0.4477	2.0	500	0.4713	{'accuracy': 0.863}
0.4477	3.0	750	0.5655	{'accuracy': 0.877}
0.2184	4.0	1000	0.6685	{'accuracy': 0.872}
0.2184	5.0	1250	0.7549	{'accuracy': 0.889}
0.0709	6.0	1500	1.0147	{'accuracy': 0.885}
0.0709	7.0	1750	0.9756	{'accuracy': 0.878}
0.024	8.0	2000	1.0414	{'accuracy': 0.885}
0.024	9.0	2250	1.0876	{'accuracy': 0.886}
0.0053	10.0	2500	1.0886	{'accuracy': 0.885}

Framework versions

—PEFT 0.7.1
—Transformers 4.36.1
—Pytorch 2.1.0+cu121
—Datasets 2.14.7
—Tokenizers 0.15.0