metadata

library_name: transformers
license: apache-2.0
base_model: facebook/vit-msn-small
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-msn-small-corect_cleaned_dataset_lateral_flow_ivalidation
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9230769230769231

vit-msn-small-corect_cleaned_dataset_lateral_flow_ivalidation

This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2318
Accuracy: 0.9231

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9231	3	0.6468	0.5604
No log	1.8462	6	0.4227	0.8462
No log	2.7692	9	0.3390	0.8608
0.5336	4.0	13	0.3115	0.8864
0.5336	4.9231	16	0.2986	0.8938
0.5336	5.8462	19	0.2318	0.9231
0.3565	6.7692	22	0.2767	0.9121
0.3565	8.0	26	0.2490	0.9084
0.3565	8.9231	29	0.3151	0.8938
0.3166	9.8462	32	0.2404	0.9231
0.3166	10.7692	35	0.2520	0.9158
0.3166	12.0	39	0.2515	0.9048
0.2657	12.9231	42	0.2344	0.9121
0.2657	13.8462	45	0.2187	0.9194
0.2657	14.7692	48	0.2289	0.9194
0.259	16.0	52	0.2251	0.9194
0.259	16.9231	55	0.2238	0.9231
0.259	17.8462	58	0.2312	0.9121
0.2514	18.4615	60	0.2305	0.9084

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1