finetuned-potato-food

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: 0.3937
• Accuracy: 0.9234

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
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7637	1.0	19	1.2292	0.7512
1.1281	2.0	38	0.8659	0.7512
0.8499	3.0	57	0.7229	0.7560
0.7548	4.0	76	0.6560	0.8373
0.7307	5.0	95	0.6091	0.8373
0.6577	6.0	114	0.5660	0.8565
0.5867	7.0	133	0.5283	0.8660
0.5593	8.0	152	0.5003	0.8756
0.5223	9.0	171	0.4790	0.8947
0.5012	10.0	190	0.4601	0.9091
0.513	11.0	209	0.4451	0.9091
0.4479	12.0	228	0.4331	0.9091
0.4355	13.0	247	0.4242	0.9091
0.4304	14.0	266	0.4142	0.9139
0.4188	15.0	285	0.4088	0.9234
0.3923	16.0	304	0.4057	0.9234
0.413	17.0	323	0.4002	0.9234
0.4014	18.0	342	0.3968	0.9234
0.3984	19.0	361	0.3940	0.9234
0.3867	20.0	380	0.3937	0.9234

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2