Modelpublic

TirkNork/laptop_sentence_classfication_BERT

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes6downloads

Model Card

laptopsentenceclassfication_BERT

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

—Loss: 0.8406
—Accuracy: 0.8769

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
No log	1.0	25	0.4663	0.8077
No log	2.0	50	0.4100	0.8308
No log	3.0	75	0.4531	0.8615
No log	4.0	100	0.4976	0.8846
No log	5.0	125	0.6578	0.8385
No log	6.0	150	0.5496	0.8923
No log	7.0	175	0.5331	0.9
No log	8.0	200	0.6781	0.8538
No log	9.0	225	0.7478	0.8538
No log	10.0	250	0.8248	0.8462
No log	11.0	275	0.6933	0.8846
No log	12.0	300	0.7508	0.8846
No log	13.0	325	0.7998	0.8846
No log	14.0	350	0.8110	0.8846
No log	15.0	375	0.8330	0.8846
No log	16.0	400	0.8348	0.8692
No log	17.0	425	0.8406	0.8692
No log	18.0	450	0.8381	0.8615
No log	19.0	475	0.8391	0.8769
0.0826	20.0	500	0.8406	0.8769

Framework versions

—Transformers 4.29.2
—Pytorch 2.0.1+cu118
—Datasets 2.12.0
—Tokenizers 0.13.3