my-indian-food-model

This model is a fine-tuned version of Mullerjo/food-101-finetuned-model on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 3.3405

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-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
4.3392	1.0	200	4.3079
4.2752	2.0	400	4.1525
4.0883	3.0	600	4.0151
3.8867	4.0	800	3.8951
3.7826	5.0	1000	3.7895
3.8011	6.0	1200	3.6985
3.6833	7.0	1400	3.6184
3.5309	8.0	1600	3.5509
3.5389	9.0	1800	3.4930
3.4727	10.0	2000	3.4455
3.4881	11.0	2200	3.4073
3.4434	12.0	2400	3.3777
3.366	13.0	2600	3.3570
3.3948	14.0	2800	3.3447
3.3238	15.0	3000	3.3405

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.1