Modelpublic

jasonsheih/bert-base-uncased-finetuned-vr-comfort-2125

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face

0likes9downloads

Model Card

bert-base-uncased-finetuned-vr-comfort-2125

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

—Loss: 1.0440
—Accuracy: 0.8431
—F1: 0.8437

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: 16
—evalbatchsize: 16
—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	F1
0.7159	1.0	157	0.6408	0.7401	0.6612
0.5559	2.0	314	0.5362	0.7952	0.7684
0.362	3.0	471	0.5135	0.8204	0.8132
0.1918	4.0	628	0.6109	0.8407	0.8388
0.1192	5.0	785	0.6947	0.8347	0.8316
0.0661	6.0	942	0.7843	0.8455	0.8467
0.0507	7.0	1099	0.9312	0.8168	0.8271
0.0406	8.0	1256	0.8616	0.8467	0.8488
0.0268	9.0	1413	0.8403	0.8443	0.8478
0.0251	10.0	1570	0.8662	0.8467	0.8472
0.0188	11.0	1727	0.9418	0.8563	0.8530
0.0195	12.0	1884	0.9541	0.8479	0.8469
0.0172	13.0	2041	0.9372	0.8407	0.8413
0.0142	14.0	2198	0.9883	0.8491	0.8469
0.0156	15.0	2355	1.0150	0.8419	0.8428
0.0138	16.0	2512	1.0035	0.8479	0.8466
0.013	17.0	2669	1.0909	0.8299	0.8355
0.0115	18.0	2826	1.0278	0.8515	0.8490
0.0107	19.0	2983	1.0419	0.8431	0.8437
0.0101	20.0	3140	1.0440	0.8431	0.8437

Framework versions

—Transformers 4.13.0
—Pytorch 1.11.0
—Datasets 1.16.1
—Tokenizers 0.10.3