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: 0.3417
Accuracy: 0.9242
F1: 0.9239

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: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.9936	78	1.2355	0.8278	0.8209
1.4688	2.0	157	0.7500	0.8979	0.8963
0.7373	2.9936	235	0.5169	0.9282	0.9277
0.342	4.0	314	0.3974	0.9290	0.9286
0.342	4.9936	392	0.3441	0.9282	0.9278
0.1623	6.0	471	0.3121	0.9290	0.9286
0.0783	6.9936	549	0.3035	0.9314	0.9311
0.0409	8.0	628	0.3237	0.9250	0.9247
0.0231	8.9936	706	0.3263	0.9258	0.9255
0.0231	10.0	785	0.3417	0.9242	0.9239

Framework versions

Transformers 4.44.2
Pytorch 2.6.0+cu124
Datasets 2.21.0
Tokenizers 0.19.1

Zodex/my-indian-food-model-v23-full

my-indian-food-model-v23-full

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Zodex/
my-indian-food-model-v23-full