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-wbc-classifier-0316-cropped-cleaned-dataset-10
    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: 0.8854679802955665

vit-msn-small-wbc-classifier-0316-cropped-cleaned-dataset-10

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: 0.3986
Accuracy: 0.8855

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3709	1.0	17	0.6977	0.8050
0.5673	2.0	34	0.5949	0.8099
0.5227	3.0	51	0.6152	0.7931
0.4958	4.0	68	0.4351	0.8436
0.4402	5.0	85	0.3777	0.8580
0.3878	6.0	102	0.3970	0.8699
0.3646	7.0	119	0.3793	0.8641
0.3452	8.0	136	0.3550	0.8805
0.344	9.0	153	0.4003	0.8736
0.3365	10.0	170	0.3654	0.8830
0.3223	11.0	187	0.3571	0.8764
0.2819	12.0	204	0.3665	0.8789
0.2998	13.0	221	0.3609	0.8838
0.2959	14.0	238	0.4335	0.8719
0.2662	15.0	255	0.4245	0.8785
0.2668	16.0	272	0.3760	0.8846
0.2576	17.0	289	0.3728	0.8830
0.2398	18.0	306	0.4192	0.8814
0.2278	19.0	323	0.4156	0.8805
0.2033	20.0	340	0.4159	0.8851
0.2037	21.0	357	0.3986	0.8855
0.1934	22.0	374	0.4220	0.8822
0.1983	23.0	391	0.4159	0.8855
0.1746	24.0	408	0.4179	0.8855
0.1776	25.0	425	0.4247	0.8834

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1