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_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: 0.855

smids_1x_deit_tiny_adamax_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: 1.0690
Accuracy: 0.855

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
0.7211	1.0	75	0.5344	0.7933
0.4907	2.0	150	0.4899	0.8217
0.4082	3.0	225	0.3985	0.8433
0.5374	4.0	300	0.4992	0.7867
0.3999	5.0	375	0.4245	0.8317
0.2788	6.0	450	0.4489	0.8333
0.2587	7.0	525	0.4635	0.8433
0.4094	8.0	600	0.4633	0.8517
0.2907	9.0	675	0.3956	0.855
0.1834	10.0	750	0.5651	0.8483
0.1936	11.0	825	0.5738	0.8317
0.0829	12.0	900	0.6121	0.8517
0.1614	13.0	975	0.7303	0.8317
0.1046	14.0	1050	0.6603	0.8333
0.0809	15.0	1125	0.6576	0.835
0.0884	16.0	1200	0.7089	0.8433
0.0489	17.0	1275	0.6901	0.855
0.1163	18.0	1350	0.9715	0.8083
0.0364	19.0	1425	0.8902	0.8417
0.0696	20.0	1500	0.9452	0.8317
0.0058	21.0	1575	1.0231	0.845
0.0448	22.0	1650	0.8657	0.855
0.0768	23.0	1725	1.0329	0.8367
0.0352	24.0	1800	0.8052	0.8467
0.0563	25.0	1875	0.7949	0.84
0.0082	26.0	1950	1.0964	0.8283
0.0281	27.0	2025	1.0752	0.8283
0.0273	28.0	2100	0.9073	0.8567
0.0259	29.0	2175	0.9898	0.8467
0.0073	30.0	2250	0.9057	0.855
0.0002	31.0	2325	1.1211	0.8333
0.0001	32.0	2400	0.9915	0.8533
0.0124	33.0	2475	1.0550	0.8517
0.0001	34.0	2550	1.0250	0.8533
0.0062	35.0	2625	1.0105	0.8533
0.0001	36.0	2700	1.0089	0.8533
0.0047	37.0	2775	1.0162	0.855
0.0	38.0	2850	1.0334	0.85
0.0	39.0	2925	1.0457	0.85
0.0	40.0	3000	1.0361	0.8567
0.0039	41.0	3075	1.0596	0.855
0.0	42.0	3150	1.0411	0.8567
0.0081	43.0	3225	1.0513	0.855
0.0001	44.0	3300	1.0505	0.855
0.0027	45.0	3375	1.0576	0.8583
0.0	46.0	3450	1.0612	0.8583
0.0065	47.0	3525	1.0629	0.8567
0.0058	48.0	3600	1.0684	0.8567
0.0	49.0	3675	1.0680	0.8567
0.0041	50.0	3750	1.0690	0.855

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0