metadata

tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: msi-vit-small
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.599979032708974
          - name: F1
            type: f1
            value: 0.2863021385373153
          - name: Precision
            type: precision
            value: 0.6335540838852097
          - name: Recall
            type: recall
            value: 0.18493757551349174

msi-vit-small

This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.5796
Accuracy: 0.6000
F1: 0.2863
Precision: 0.6336
Recall: 0.1849

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-06
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.3142	1.0	1008	0.8965	0.6329	0.5060	0.6079	0.4333
0.2063	2.0	2016	1.5189	0.6062	0.3005	0.6550	0.1950
0.19	3.0	3024	1.4818	0.6270	0.3399	0.7318	0.2213
0.1718	4.0	4032	1.2353	0.6046	0.4096	0.5816	0.3161
0.161	5.0	5040	1.5953	0.6342	0.3508	0.7623	0.2278
0.1805	6.0	6048	1.0789	0.6552	0.4647	0.7119	0.3449
0.1619	7.0	7056	1.2646	0.5479	0.2591	0.4484	0.1822
0.1655	8.0	8064	1.7155	0.5910	0.2654	0.6011	0.1703
0.17	9.0	9072	2.1142	0.5797	0.1729	0.5913	0.1012
0.1703	10.0	10080	1.5796	0.6000	0.2863	0.6336	0.1849

Framework versions

Transformers 4.36.0
Pytorch 2.0.1+cu117
Datasets 2.15.0
Tokenizers 0.15.0