sdss-cnn

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1573
• Accuracy: 0.9505

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: 0.0001
• train_batch_size: 100
• eval_batch_size: 100
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	80	0.4954	0.8635
No log	2.0	160	0.2788	0.9055
No log	3.0	240	0.2239	0.9085
No log	4.0	320	0.1991	0.9325
No log	5.0	400	0.1954	0.94
No log	6.0	480	0.1854	0.9445
0.3543	7.0	560	0.1891	0.9375
0.3543	8.0	640	0.1777	0.943
0.3543	9.0	720	0.1780	0.9415
0.3543	10.0	800	0.1804	0.942
0.3543	11.0	880	0.1734	0.9475
0.3543	12.0	960	0.1689	0.947
0.2022	13.0	1040	0.1698	0.9445
0.2022	14.0	1120	0.1689	0.9405
0.2022	15.0	1200	0.1650	0.9475
0.2022	16.0	1280	0.1755	0.934
0.2022	17.0	1360	0.1635	0.944
0.2022	18.0	1440	0.1711	0.942
0.1836	19.0	1520	0.1604	0.9485
0.1836	20.0	1600	0.1595	0.95
0.1836	21.0	1680	0.1613	0.9475
0.1836	22.0	1760	0.1579	0.949
0.1836	23.0	1840	0.1593	0.946
0.1836	24.0	1920	0.1579	0.945
0.167	25.0	2000	0.1584	0.9495
0.167	26.0	2080	0.1573	0.9505
0.167	27.0	2160	0.1596	0.945
0.167	28.0	2240	0.1599	0.9435
0.167	29.0	2320	0.1565	0.9485
0.167	30.0	2400	0.1582	0.946
0.167	31.0	2480	0.1563	0.95
0.1568	32.0	2560	0.1563	0.95
0.1568	33.0	2640	0.1573	0.9495
0.1568	34.0	2720	0.1564	0.9465
0.1568	35.0	2800	0.1557	0.95
0.1568	36.0	2880	0.1554	0.949
0.1568	37.0	2960	0.1562	0.948
0.1515	38.0	3040	0.1555	0.948
0.1515	39.0	3120	0.1557	0.95
0.1515	40.0	3200	0.1559	0.9485

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3