Modelpublic

manu02/distilbert-base-uncased-lora-text-classification

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

0likes14downloads

Model Card

distilbert-base-uncased-lora-text-classification

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

—Loss: 0.9717
—Accuracy: {'accuracy': 0.872}

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: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.3489	{'accuracy': 0.864}
0.4170	2.0	500	0.5439	{'accuracy': 0.856}
0.4170	3.0	750	0.4622	{'accuracy': 0.895}
0.1997	4.0	1000	0.6808	{'accuracy': 0.88}
0.1997	5.0	1250	0.8102	{'accuracy': 0.878}
0.0662	6.0	1500	0.8642	{'accuracy': 0.892}
0.0662	7.0	1750	0.9038	{'accuracy': 0.88}
0.0103	8.0	2000	0.9522	{'accuracy': 0.87}
0.0103	9.0	2250	0.9865	{'accuracy': 0.878}
0.0066	10.0	2500	0.9717	{'accuracy': 0.872}

Framework versions

—PEFT 0.18.1
—Transformers 5.0.0
—Pytorch 2.10.0+cu130
—Datasets 4.5.0
—Tokenizers 0.22.2