lens-1

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: 1.1819
• Accuracy: 0.57

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-06
• train_batch_size: 4
• eval_batch_size: 4
• 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
0.5087	1.0	200	1.1273	0.545
0.5636	2.0	400	1.1752	0.545
0.5356	3.0	600	1.2058	0.52
0.6525	4.0	800	1.0978	0.545
0.4262	5.0	1000	1.1396	0.55
0.5066	6.0	1200	1.1730	0.53
0.3765	7.0	1400	1.1041	0.585
0.3869	8.0	1600	1.2183	0.525
0.4331	9.0	1800	1.1815	0.535
0.4646	10.0	2000	1.1397	0.57
0.6802	11.0	2200	1.1624	0.525
0.679	12.0	2400	1.1541	0.52
0.6286	13.0	2600	1.1933	0.52
0.663	14.0	2800	1.2535	0.5
0.4078	15.0	3000	1.2326	0.495
0.6179	16.0	3200	1.1901	0.52
0.4192	17.0	3400	1.2329	0.525
0.3685	18.0	3600	1.2212	0.505
0.4928	19.0	3800	1.1887	0.555
0.5752	20.0	4000	1.1819	0.57

Framework versions

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