lens-2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5324
• Accuracy: 0.545

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0399	1.0	100	2.1707	0.52
0.069	2.0	200	2.2835	0.52
0.0631	3.0	300	2.5655	0.5
0.0667	4.0	400	2.1765	0.55
0.0055	5.0	500	2.4217	0.535
0.0087	6.0	600	2.3678	0.545
0.0492	7.0	700	2.4301	0.535
0.0049	8.0	800	2.3669	0.545
0.0091	9.0	900	2.5554	0.5
0.016	10.0	1000	2.4330	0.545
0.0345	11.0	1100	2.3653	0.575
0.1143	12.0	1200	2.5124	0.54
0.2871	13.0	1300	2.3495	0.555
0.1154	14.0	1400	2.2519	0.56
0.1388	15.0	1500	2.4013	0.54
0.1445	16.0	1600	2.3764	0.535
0.1094	17.0	1700	2.5227	0.5
0.0884	18.0	1800	2.4164	0.55
0.156	19.0	1900	2.4202	0.555
0.0055	20.0	2000	2.5324	0.545

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1