Modelpublic

steve202608/distilbert-base-uncased-finetuned-emotion

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes5downloads

Model Card

distilbert-base-uncased-finetuned-emotion

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: 0.1922
—Accuracy: 0.9365
—F1: 0.9364

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
—trainbatchsize: 128
—evalbatchsize: 128
—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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.0338	1.0	125	0.4268	0.8755	0.8667
0.2848	2.0	250	0.2057	0.928	0.9285
0.1571	3.0	375	0.1687	0.9355	0.9360
0.1195	4.0	500	0.1462	0.935	0.9356
0.0995	5.0	625	0.1474	0.9345	0.9346
0.0829	6.0	750	0.1498	0.936	0.9362
0.0758	7.0	875	0.1517	0.9335	0.9333
0.0649	8.0	1000	0.1571	0.935	0.9351
0.0536	9.0	1125	0.1622	0.9385	0.9383
0.0453	10.0	1250	0.1678	0.937	0.9370
0.0400	11.0	1375	0.1752	0.938	0.9380
0.0354	12.0	1500	0.1839	0.938	0.9379
0.0295	13.0	1625	0.1868	0.938	0.9378
0.0279	14.0	1750	0.1912	0.9365	0.9369
0.0271	15.0	1875	0.1942	0.9385	0.9383
0.0212	16.0	2000	0.1922	0.9365	0.9364

Framework versions

—Transformers 5.13.1
—Pytorch 2.11.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2