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_0001_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: 0.8216666666666667

smids_5x_deit_tiny_sgd_0001_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: 0.4623
Accuracy: 0.8217

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: 0.0001
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
1.1763	1.0	375	1.1547	0.3917
1.0966	2.0	750	1.0897	0.42
1.0223	3.0	1125	1.0444	0.46
0.9886	4.0	1500	1.0052	0.4917
0.9546	5.0	1875	0.9693	0.515
0.932	6.0	2250	0.9344	0.54
0.8619	7.0	2625	0.9000	0.57
0.857	8.0	3000	0.8647	0.5967
0.8079	9.0	3375	0.8304	0.62
0.7619	10.0	3750	0.7976	0.645
0.7316	11.0	4125	0.7657	0.665
0.6666	12.0	4500	0.7355	0.68
0.6961	13.0	4875	0.7078	0.69
0.6607	14.0	5250	0.6819	0.7083
0.6448	15.0	5625	0.6579	0.725
0.6031	16.0	6000	0.6371	0.7333
0.633	17.0	6375	0.6195	0.7433
0.6177	18.0	6750	0.6022	0.7533
0.5854	19.0	7125	0.5875	0.765
0.5213	20.0	7500	0.5748	0.77
0.5296	21.0	7875	0.5628	0.7833
0.5226	22.0	8250	0.5527	0.7917
0.5777	23.0	8625	0.5439	0.795
0.5616	24.0	9000	0.5354	0.8017
0.5254	25.0	9375	0.5279	0.8067
0.5443	26.0	9750	0.5213	0.8067
0.5349	27.0	10125	0.5152	0.8133
0.5476	28.0	10500	0.5090	0.8133
0.5198	29.0	10875	0.5041	0.815
0.4665	30.0	11250	0.4997	0.8167
0.5013	31.0	11625	0.4955	0.8167
0.5242	32.0	12000	0.4917	0.8167
0.5162	33.0	12375	0.4881	0.8167
0.5094	34.0	12750	0.4847	0.815
0.4537	35.0	13125	0.4817	0.8167
0.4056	36.0	13500	0.4788	0.8167
0.4566	37.0	13875	0.4763	0.8167
0.4864	38.0	14250	0.4740	0.8183
0.4572	39.0	14625	0.4721	0.82
0.5272	40.0	15000	0.4702	0.82
0.4662	41.0	15375	0.4685	0.82
0.4598	42.0	15750	0.4671	0.82
0.4764	43.0	16125	0.4660	0.82
0.4497	44.0	16500	0.4650	0.82
0.4734	45.0	16875	0.4641	0.82
0.4953	46.0	17250	0.4634	0.82
0.4817	47.0	17625	0.4629	0.8217
0.4691	48.0	18000	0.4625	0.8217
0.4502	49.0	18375	0.4623	0.8217
0.4257	50.0	18750	0.4623	0.8217

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2