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_sgd_001_fold4
    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: 0.835

smids_1x_deit_tiny_sgd_001_fold4

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: 0.4122
Accuracy: 0.835

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
1.0732	1.0	75	1.0625	0.4117
0.95	2.0	150	0.9470	0.52
0.8388	3.0	225	0.8541	0.6133
0.8107	4.0	300	0.7814	0.66
0.7296	5.0	375	0.7116	0.6933
0.6565	6.0	450	0.6560	0.7233
0.6075	7.0	525	0.6119	0.7367
0.5566	8.0	600	0.5801	0.76
0.5592	9.0	675	0.5568	0.7717
0.4945	10.0	750	0.5396	0.785
0.484	11.0	825	0.5228	0.79
0.4564	12.0	900	0.5098	0.7917
0.4689	13.0	975	0.5015	0.7917
0.4232	14.0	1050	0.4882	0.7967
0.4151	15.0	1125	0.4851	0.795
0.3646	16.0	1200	0.4743	0.8017
0.3676	17.0	1275	0.4658	0.8083
0.3612	18.0	1350	0.4603	0.8017
0.4051	19.0	1425	0.4555	0.81
0.3477	20.0	1500	0.4507	0.81
0.375	21.0	1575	0.4488	0.8017
0.3102	22.0	1650	0.4425	0.8083
0.3203	23.0	1725	0.4393	0.8117
0.3847	24.0	1800	0.4374	0.8133
0.3175	25.0	1875	0.4337	0.8133
0.3275	26.0	1950	0.4305	0.8183
0.2952	27.0	2025	0.4280	0.8167
0.3226	28.0	2100	0.4272	0.82
0.2919	29.0	2175	0.4254	0.82
0.3056	30.0	2250	0.4233	0.8233
0.2391	31.0	2325	0.4233	0.8233
0.3148	32.0	2400	0.4205	0.8267
0.2897	33.0	2475	0.4204	0.8267
0.2561	34.0	2550	0.4195	0.8267
0.2841	35.0	2625	0.4186	0.8283
0.2572	36.0	2700	0.4171	0.8267
0.2531	37.0	2775	0.4160	0.8267
0.2737	38.0	2850	0.4152	0.8333
0.276	39.0	2925	0.4146	0.8317
0.3158	40.0	3000	0.4142	0.8317
0.2611	41.0	3075	0.4144	0.8367
0.2512	42.0	3150	0.4134	0.835
0.2782	43.0	3225	0.4133	0.835
0.2613	44.0	3300	0.4133	0.8367
0.2656	45.0	3375	0.4131	0.835
0.2575	46.0	3450	0.4126	0.835
0.2475	47.0	3525	0.4125	0.8367
0.2893	48.0	3600	0.4124	0.835
0.2785	49.0	3675	0.4123	0.835
0.2483	50.0	3750	0.4122	0.835

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0