metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_small_rms_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: 0.7720465890183028

smids_3x_deit_small_rms_001_fold2

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

Loss: 0.6000
Accuracy: 0.7720

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
1.1321	1.0	225	1.1948	0.4293
0.871	2.0	450	0.8948	0.5175
0.8008	3.0	675	0.7992	0.5408
0.8238	4.0	900	0.8283	0.5574
0.8152	5.0	1125	0.7604	0.6023
0.7386	6.0	1350	0.8796	0.5491
0.8772	7.0	1575	0.8860	0.5874
0.8376	8.0	1800	0.7510	0.6356
0.7551	9.0	2025	0.8017	0.6223
0.7343	10.0	2250	0.7106	0.6506
0.7921	11.0	2475	0.7927	0.6223
0.7457	12.0	2700	0.6623	0.6972
0.7029	13.0	2925	0.7255	0.6855
0.6991	14.0	3150	0.6397	0.7471
0.6797	15.0	3375	0.6573	0.6988
0.7545	16.0	3600	0.6382	0.7038
0.68	17.0	3825	0.6756	0.6805
0.624	18.0	4050	0.6219	0.7488
0.6708	19.0	4275	0.6554	0.7088
0.6335	20.0	4500	0.6777	0.6905
0.6626	21.0	4725	0.6194	0.7438
0.7083	22.0	4950	0.6072	0.7488
0.7252	23.0	5175	0.5921	0.7471
0.6519	24.0	5400	0.5775	0.7454
0.6375	25.0	5625	0.6257	0.7188
0.6035	26.0	5850	0.5599	0.7554
0.6072	27.0	6075	0.6182	0.7338
0.5614	28.0	6300	0.5694	0.7654
0.5851	29.0	6525	0.5778	0.7488
0.5267	30.0	6750	0.5678	0.7521
0.6187	31.0	6975	0.5810	0.7571
0.5995	32.0	7200	0.5883	0.7587
0.5524	33.0	7425	0.5665	0.7671
0.5635	34.0	7650	0.5545	0.7671
0.5514	35.0	7875	0.5682	0.7654
0.5935	36.0	8100	0.5461	0.7687
0.533	37.0	8325	0.5437	0.7820
0.4461	38.0	8550	0.5819	0.7571
0.4417	39.0	8775	0.5848	0.7554
0.4385	40.0	9000	0.5831	0.7754
0.4422	41.0	9225	0.6218	0.7504
0.5095	42.0	9450	0.5522	0.7787
0.4571	43.0	9675	0.5702	0.7854
0.4352	44.0	9900	0.5650	0.7920
0.4947	45.0	10125	0.6244	0.7504
0.4183	46.0	10350	0.5769	0.7754
0.4309	47.0	10575	0.5669	0.7820
0.441	48.0	10800	0.5895	0.7737
0.475	49.0	11025	0.5930	0.7704
0.4102	50.0	11250	0.6000	0.7720

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2