metadata

library_name: transformers
license: other
base_model: apple/mobilevit-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: my_food_model
    results: []

my_food_model

This model is a fine-tuned version of apple/mobilevit-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0492
Accuracy: 0.7236

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.4987	1.0	592	4.4835	0.1002
3.6382	2.0	1184	3.4318	0.2707
2.9497	3.0	1776	2.5897	0.3945
2.586	4.0	2368	2.1261	0.4824
2.2806	5.0	2960	1.8201	0.5501
2.0928	6.0	3552	1.6291	0.5896
1.9839	7.0	4144	1.4954	0.6145
1.8465	8.0	4736	1.4209	0.6333
1.6939	9.0	5328	1.3486	0.6493
1.6212	10.0	5920	1.2959	0.6616
1.6672	11.0	6512	1.2299	0.6744
1.5973	12.0	7104	1.2018	0.6871
1.5419	13.0	7696	1.1750	0.6928
1.5003	14.0	8288	1.1297	0.7017
1.4908	15.0	8880	1.1184	0.7030
1.4033	16.0	9472	1.0983	0.7125
1.4015	17.0	10064	1.0832	0.7159
1.3651	18.0	10656	1.0728	0.7134
1.3698	19.0	11248	1.0678	0.7166
1.4136	20.0	11840	1.0541	0.7217
1.4679	21.0	12432	1.0542	0.7208
1.3328	22.0	13024	1.0466	0.7253
1.2773	23.0	13616	1.0655	0.7188
1.342	24.0	14208	1.0471	0.7236
1.3437	25.0	14800	1.0492	0.7236

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0