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

Loss: 0.6866
Accuracy: 0.8286

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.9933	0.1946	100	3.0302	0.4679
2.4249	0.3891	200	2.2643	0.5594
2.1319	0.5837	300	2.0092	0.5691
1.7793	0.7782	400	1.7550	0.6086
1.8401	0.9728	500	1.6372	0.6407
1.3499	1.1673	600	1.3922	0.6908
1.2906	1.3619	700	1.2705	0.7118
0.9804	1.5564	800	1.1602	0.7322
1.0783	1.7510	900	1.1229	0.7308
0.968	1.9455	1000	1.0598	0.7468
0.6267	2.1401	1100	0.9519	0.7663
0.7739	2.3346	1200	0.9060	0.7785
0.8705	2.5292	1300	0.8600	0.7945
0.7832	2.7237	1400	0.8134	0.8023
0.7061	2.9183	1500	0.8009	0.7984
0.4784	3.1128	1600	0.7495	0.8087
0.514	3.3074	1700	0.7359	0.8101
0.4407	3.5019	1800	0.7049	0.8184
0.4831	3.6965	1900	0.6899	0.8208
0.4283	3.8911	2000	0.6866	0.8286

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

blaze-05/finetuned-indian-food

finetuned-indian-food

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

blaze-05/
finetuned-indian-food