metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_small_sgd_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_small_sgd_001_fold5

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: 0.3554
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
0.9725	1.0	75	0.9578	0.58
0.8549	2.0	150	0.8545	0.6367
0.7685	3.0	225	0.7653	0.6967
0.7189	4.0	300	0.6967	0.7383
0.6469	5.0	375	0.6428	0.7567
0.5993	6.0	450	0.5995	0.7667
0.5809	7.0	525	0.5645	0.7717
0.5382	8.0	600	0.5378	0.7817
0.5132	9.0	675	0.5146	0.7933
0.5002	10.0	750	0.4976	0.7817
0.5258	11.0	825	0.4771	0.8033
0.4262	12.0	900	0.4625	0.8183
0.4371	13.0	975	0.4503	0.8217
0.4112	14.0	1050	0.4406	0.8217
0.3773	15.0	1125	0.4328	0.8183
0.3566	16.0	1200	0.4255	0.82
0.3898	17.0	1275	0.4160	0.83
0.3699	18.0	1350	0.4107	0.8233
0.3811	19.0	1425	0.4043	0.84
0.3869	20.0	1500	0.4001	0.8317
0.363	21.0	1575	0.3965	0.8383
0.3336	22.0	1650	0.3912	0.8433
0.334	23.0	1725	0.3876	0.8433
0.3158	24.0	1800	0.3862	0.845
0.309	25.0	1875	0.3831	0.8433
0.3223	26.0	1950	0.3821	0.84
0.3225	27.0	2025	0.3783	0.8417
0.3412	28.0	2100	0.3753	0.845
0.3183	29.0	2175	0.3735	0.8433
0.3062	30.0	2250	0.3707	0.8417
0.2914	31.0	2325	0.3702	0.8417
0.2994	32.0	2400	0.3684	0.84
0.3197	33.0	2475	0.3663	0.8467
0.2992	34.0	2550	0.3643	0.85
0.3245	35.0	2625	0.3629	0.8517
0.2966	36.0	2700	0.3625	0.8483
0.2581	37.0	2775	0.3619	0.8467
0.3008	38.0	2850	0.3609	0.8483
0.2884	39.0	2925	0.3604	0.85
0.3019	40.0	3000	0.3593	0.85
0.3288	41.0	3075	0.3590	0.8517
0.3129	42.0	3150	0.3580	0.855
0.2899	43.0	3225	0.3573	0.855
0.2709	44.0	3300	0.3568	0.855
0.2859	45.0	3375	0.3565	0.8533
0.3026	46.0	3450	0.3561	0.8533
0.2643	47.0	3525	0.3557	0.855
0.2626	48.0	3600	0.3556	0.855
0.2672	49.0	3675	0.3555	0.855
0.2682	50.0	3750	0.3554	0.855

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0