Modelpublic

ankitb10/question_classification_model

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes5downloads

Model Card

questionclassificationmodel

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

—Loss: 0.0141
—Accuracy: 1.0

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: 2
—evalbatchsize: 2
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0644	0.5	5	1.1973	0.0
1.1768	1.0	10	1.1003	0.0
1.0388	1.5	15	0.9396	1.0
0.9709	2.0	20	0.8235	1.0
1.0193	2.5	25	0.7088	1.0
0.7945	3.0	30	0.5735	1.0
0.9431	3.5	35	0.4812	1.0
0.7091	4.0	40	0.4083	1.0
0.7901	4.5	45	0.3773	1.0
0.7049	5.0	50	0.2875	1.0
0.5757	5.5	55	0.2608	1.0
0.6503	6.0	60	0.2752	1.0
0.6157	6.5	65	0.2288	1.0
0.4012	7.0	70	0.1577	1.0
0.5781	7.5	75	0.1294	1.0
0.2576	8.0	80	0.1047	1.0
0.5107	8.5	85	0.0842	1.0
0.1516	9.0	90	0.0711	1.0
0.2649	9.5	95	0.0581	1.0
0.2855	10.0	100	0.0485	1.0
0.2232	10.5	105	0.0401	1.0
0.2213	11.0	110	0.0344	1.0
0.2809	11.5	115	0.0299	1.0
0.0889	12.0	120	0.0268	1.0
0.0933	12.5	125	0.0244	1.0
0.2543	13.0	130	0.0225	1.0
0.1446	13.5	135	0.0204	1.0
0.2565	14.0	140	0.0188	1.0
0.1347	14.5	145	0.0179	1.0
0.1464	15.0	150	0.0172	1.0
0.0365	15.5	155	0.0165	1.0
0.2711	16.0	160	0.0159	1.0
0.1889	16.5	165	0.0155	1.0
0.0336	17.0	170	0.0152	1.0
0.1712	17.5	175	0.0149	1.0
0.0366	18.0	180	0.0146	1.0
0.1819	18.5	185	0.0144	1.0
0.0353	19.0	190	0.0142	1.0
0.092	19.5	195	0.0142	1.0
0.0991	20.0	200	0.0141	1.0

Framework versions

—Transformers 4.40.0
—Pytorch 2.2.2
—Datasets 2.19.1
—Tokenizers 0.19.1