metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_tiny_adamax_00001_fold2
    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: 0.8535773710482529

smids_1x_deit_tiny_adamax_00001_fold2

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: 0.9040
Accuracy: 0.8536

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: 1e-05
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
0.7328	1.0	75	0.6585	0.7321
0.4509	2.0	150	0.4910	0.7903
0.3653	3.0	225	0.4211	0.8253
0.2986	4.0	300	0.4104	0.8353
0.2809	5.0	375	0.3830	0.8336
0.2519	6.0	450	0.3604	0.8502
0.2227	7.0	525	0.3681	0.8552
0.2223	8.0	600	0.3795	0.8419
0.1548	9.0	675	0.3730	0.8552
0.1857	10.0	750	0.3841	0.8602
0.1291	11.0	825	0.3934	0.8602
0.08	12.0	900	0.4226	0.8552
0.0831	13.0	975	0.4456	0.8486
0.0574	14.0	1050	0.5173	0.8436
0.0548	15.0	1125	0.4816	0.8602
0.051	16.0	1200	0.5112	0.8569
0.0349	17.0	1275	0.5235	0.8536
0.0192	18.0	1350	0.5709	0.8502
0.027	19.0	1425	0.6300	0.8453
0.0409	20.0	1500	0.6458	0.8502
0.009	21.0	1575	0.6679	0.8552
0.0172	22.0	1650	0.6845	0.8519
0.0015	23.0	1725	0.7310	0.8552
0.0059	24.0	1800	0.7388	0.8552
0.0018	25.0	1875	0.7514	0.8569
0.0008	26.0	1950	0.7646	0.8552
0.0024	27.0	2025	0.7898	0.8569
0.0185	28.0	2100	0.7969	0.8519
0.0012	29.0	2175	0.8175	0.8619
0.003	30.0	2250	0.8189	0.8536
0.0009	31.0	2325	0.8193	0.8569
0.0003	32.0	2400	0.8343	0.8602
0.0006	33.0	2475	0.8317	0.8586
0.0003	34.0	2550	0.8413	0.8536
0.026	35.0	2625	0.8594	0.8519
0.0003	36.0	2700	0.8747	0.8519
0.0002	37.0	2775	0.8582	0.8536
0.0003	38.0	2850	0.8927	0.8536
0.0067	39.0	2925	0.8896	0.8519
0.0002	40.0	3000	0.8915	0.8536
0.003	41.0	3075	0.8737	0.8586
0.0003	42.0	3150	0.9065	0.8519
0.0159	43.0	3225	0.8958	0.8552
0.0007	44.0	3300	0.8969	0.8519
0.0002	45.0	3375	0.9007	0.8519
0.0002	46.0	3450	0.9037	0.8536
0.007	47.0	3525	0.9095	0.8536
0.0002	48.0	3600	0.9035	0.8536
0.0057	49.0	3675	0.9034	0.8536
0.0097	50.0	3750	0.9040	0.8536

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0