metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_sgd_001_fold5
    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: 0.8966666666666666

smids_5x_deit_tiny_sgd_001_fold5

This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2922
Accuracy: 0.8967

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: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.732	1.0	375	0.7708	0.6633
0.5592	2.0	750	0.5202	0.805
0.438	3.0	1125	0.4358	0.8283
0.4192	4.0	1500	0.3942	0.8367
0.3481	5.0	1875	0.3697	0.855
0.3125	6.0	2250	0.3536	0.855
0.2839	7.0	2625	0.3373	0.8583
0.307	8.0	3000	0.3279	0.865
0.3167	9.0	3375	0.3230	0.8633
0.2868	10.0	3750	0.3137	0.8717
0.2359	11.0	4125	0.3108	0.8717
0.1975	12.0	4500	0.3038	0.8717
0.2176	13.0	4875	0.3032	0.8733
0.2542	14.0	5250	0.3007	0.875
0.2703	15.0	5625	0.2972	0.8683
0.1798	16.0	6000	0.2915	0.885
0.2588	17.0	6375	0.2956	0.89
0.2412	18.0	6750	0.2946	0.8917
0.2128	19.0	7125	0.2865	0.89
0.1689	20.0	7500	0.2885	0.8917
0.1828	21.0	7875	0.2918	0.885
0.1759	22.0	8250	0.2944	0.895
0.2982	23.0	8625	0.2937	0.895
0.1829	24.0	9000	0.2869	0.8917
0.2242	25.0	9375	0.2897	0.8967
0.1828	26.0	9750	0.2915	0.8967
0.2241	27.0	10125	0.2878	0.8933
0.1723	28.0	10500	0.2984	0.8967
0.1963	29.0	10875	0.2878	0.8867
0.1493	30.0	11250	0.2886	0.89
0.2083	31.0	11625	0.2897	0.8983
0.1814	32.0	12000	0.2856	0.8917
0.1849	33.0	12375	0.2930	0.895
0.2425	34.0	12750	0.2930	0.8967
0.156	35.0	13125	0.2856	0.89
0.1222	36.0	13500	0.2860	0.8933
0.1645	37.0	13875	0.2870	0.89
0.1564	38.0	14250	0.2951	0.8967
0.1413	39.0	14625	0.2881	0.8967
0.1794	40.0	15000	0.2908	0.8917
0.1449	41.0	15375	0.2944	0.8983
0.1425	42.0	15750	0.2915	0.8933
0.1565	43.0	16125	0.2889	0.895
0.1698	44.0	16500	0.2893	0.8933
0.1716	45.0	16875	0.2917	0.8983
0.1879	46.0	17250	0.2923	0.895
0.1864	47.0	17625	0.2918	0.8967
0.1231	48.0	18000	0.2914	0.8967
0.1631	49.0	18375	0.2921	0.8967
0.1701	50.0	18750	0.2922	0.8967

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2