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_001_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: 0.8935108153078203

smids_1x_deit_tiny_adamax_001_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: 0.8198
Accuracy: 0.8935

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
0.6145	1.0	75	0.5428	0.7970
0.3766	2.0	150	0.5726	0.7720
0.4048	3.0	225	0.6119	0.7920
0.3699	4.0	300	0.3532	0.8619
0.3283	5.0	375	0.4734	0.8270
0.2617	6.0	450	0.5747	0.8053
0.2131	7.0	525	0.4492	0.8486
0.1731	8.0	600	0.4339	0.8686
0.1832	9.0	675	0.5654	0.8336
0.1286	10.0	750	1.0166	0.7704
0.0921	11.0	825	0.5592	0.8519
0.0818	12.0	900	0.6074	0.8486
0.1315	13.0	975	0.7091	0.8369
0.0851	14.0	1050	0.6304	0.8436
0.0354	15.0	1125	0.8000	0.8469
0.0659	16.0	1200	0.7712	0.8586
0.0297	17.0	1275	0.8136	0.8686
0.058	18.0	1350	0.7968	0.8536
0.0096	19.0	1425	0.7312	0.8719
0.0206	20.0	1500	0.7618	0.8453
0.0111	21.0	1575	1.0098	0.8336
0.0053	22.0	1650	0.8487	0.8502
0.0105	23.0	1725	0.7386	0.8702
0.0094	24.0	1800	0.8515	0.8419
0.0004	25.0	1875	0.8080	0.8636
0.0177	26.0	1950	0.6472	0.8819
0.0321	27.0	2025	0.6905	0.8785
0.0096	28.0	2100	0.6932	0.8852
0.0091	29.0	2175	0.7066	0.8869
0.0059	30.0	2250	0.7159	0.8819
0.0056	31.0	2325	0.7490	0.8869
0.0	32.0	2400	0.7569	0.8885
0.0	33.0	2475	0.7589	0.8869
0.0003	34.0	2550	0.7519	0.8935
0.01	35.0	2625	0.7808	0.8902
0.0	36.0	2700	0.7653	0.8918
0.0001	37.0	2775	0.7709	0.8902
0.0	38.0	2850	0.7835	0.8885
0.0016	39.0	2925	0.7996	0.8935
0.0	40.0	3000	0.7825	0.8918
0.0036	41.0	3075	0.7879	0.8918
0.0	42.0	3150	0.7990	0.8935
0.003	43.0	3225	0.8020	0.8935
0.0034	44.0	3300	0.8080	0.8935
0.0	45.0	3375	0.8073	0.8935
0.0	46.0	3450	0.8161	0.8935
0.0029	47.0	3525	0.8235	0.8918
0.0	48.0	3600	0.8195	0.8935
0.0023	49.0	3675	0.8192	0.8935
0.0022	50.0	3750	0.8198	0.8935

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0