This model is a fine-tuned version of Zodex/my-indian-food-model-v25-full on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1462
Accuracy: 0.9796
F1: 0.9794

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
0.3137	0.2067	100	0.2117	0.9718	0.9713
0.2922	0.4134	200	0.1912	0.9767	0.9764
0.2657	0.6202	300	0.1740	0.9783	0.9780
0.2504	0.8269	400	0.1509	0.9798	0.9798
0.1864	1.0336	500	0.1485	0.9786	0.9786
0.1412	1.2403	600	0.1319	0.9814	0.9813
0.122	1.4470	700	0.1506	0.9804	0.9803
0.1236	1.6537	800	0.1581	0.9798	0.9797
0.1482	1.8605	900	0.1228	0.9824	0.9824
0.0882	2.0672	1000	0.1375	0.9822	0.9820
0.0564	2.2739	1100	0.1308	0.9793	0.9792
0.0467	2.4806	1200	0.1280	0.9827	0.9826
0.0483	2.6873	1300	0.1242	0.9832	0.9831
0.0526	2.8941	1400	0.1331	0.9824	0.9823
0.0441	3.1008	1500	0.1398	0.9814	0.9813
0.0165	3.3075	1600	0.1462	0.9796	0.9794

Framework versions

Transformers 4.44.2
Pytorch 2.3.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Zodex/my-final-food-model-v29-full

my-final-food-model-v29-full

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Zodex/
my-final-food-model-v29-full