README.md

metadata

license: other
base_model: apple/mobilevit-small
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - f1
  - accuracy
model-index:
  - name: car_identified_model_11
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.7241379310344829
          - name: Accuracy
            type: accuracy
            value: 0.08333333333333333

car_identified_model_11

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

• Loss: 0.6686
• F1: 0.7241
• Roc Auc: 0.6667
• Accuracy: 0.0833

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2582	1.0	1	0.6938	0.5926	0.5417	0.0833
0.2582	2.0	2	0.6937	0.6415	0.6042	0.0833
0.2582	3.0	4	0.6918	0.6429	0.5833	0.0
0.2582	4.0	5	0.6893	0.6316	0.5625	0.0
0.2582	5.0	6	0.6871	0.6667	0.6042	0.0833
0.2582	6.0	8	0.6844	0.6786	0.625	0.0833
0.2582	7.0	9	0.6827	0.7018	0.6458	0.0833
0.2582	8.0	10	0.6817	0.6667	0.6042	0.0833
0.2582	9.0	11	0.6809	0.6897	0.625	0.0833
0.2582	10.0	12	0.6804	0.6897	0.625	0.0833
0.2582	11.0	14	0.6792	0.6897	0.625	0.0833
0.2582	12.0	15	0.6787	0.7119	0.6458	0.0833
0.2582	13.0	16	0.6780	0.7119	0.6458	0.0833
0.2582	14.0	18	0.6771	0.7241	0.6667	0.0833
0.2582	15.0	19	0.6765	0.7241	0.6667	0.0833
0.2582	16.0	20	0.6762	0.7458	0.6875	0.0833
0.2582	17.0	21	0.6758	0.7333	0.6667	0.0833
0.2582	18.0	22	0.6753	0.7458	0.6875	0.0833
0.2582	19.0	24	0.6744	0.7333	0.6667	0.0833
0.2582	20.0	25	0.6740	0.7241	0.6667	0.0833
0.2582	21.0	26	0.6737	0.7241	0.6667	0.0833
0.2582	22.0	28	0.6733	0.7458	0.6875	0.0833
0.2582	23.0	29	0.6725	0.7458	0.6875	0.0833
0.2582	24.0	30	0.6720	0.7368	0.6875	0.0833
0.2582	25.0	31	0.6719	0.7241	0.6667	0.0833
0.2582	26.0	32	0.6713	0.7241	0.6667	0.0833
0.2582	27.0	34	0.6711	0.7241	0.6667	0.0833
0.2582	28.0	35	0.6705	0.7241	0.6667	0.0833
0.2582	29.0	36	0.6700	0.7368	0.6875	0.0833
0.2582	30.0	38	0.6696	0.7241	0.6667	0.0833
0.2582	31.0	39	0.6695	0.7241	0.6667	0.0833
0.2582	32.0	40	0.6693	0.7368	0.6875	0.1667
0.2582	33.0	41	0.6692	0.7241	0.6667	0.0833
0.2582	34.0	42	0.6694	0.7241	0.6667	0.0833
0.2582	35.0	44	0.6692	0.7241	0.6667	0.0833
0.2582	36.0	45	0.6693	0.7241	0.6667	0.0833
0.2582	37.0	46	0.6693	0.7241	0.6667	0.0833
0.2582	38.0	48	0.6690	0.7241	0.6667	0.0833
0.2582	39.0	49	0.6689	0.7368	0.6875	0.0833
0.2582	40.0	50	0.6686	0.7241	0.6667	0.0833

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1