metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_tiny_adamax_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: 0.6190476190476191

hushem_1x_deit_tiny_adamax_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: 2.7093
Accuracy: 0.6190

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
No log	1.0	6	1.4186	0.2619
1.7828	2.0	12	1.5668	0.2381
1.7828	3.0	18	1.3464	0.2619
1.4289	4.0	24	1.2387	0.2857
1.3071	5.0	30	1.0086	0.5952
1.3071	6.0	36	1.1662	0.3333
1.1964	7.0	42	1.2853	0.4286
1.1964	8.0	48	1.2187	0.3333
1.0152	9.0	54	0.8730	0.6190
0.7906	10.0	60	0.9343	0.5714
0.7906	11.0	66	1.6411	0.5
0.5517	12.0	72	2.1397	0.3095
0.5517	13.0	78	1.0282	0.5476
0.856	14.0	84	1.1613	0.4762
0.4273	15.0	90	1.2606	0.5476
0.4273	16.0	96	1.4223	0.5952
0.2649	17.0	102	1.5904	0.6429
0.2649	18.0	108	2.3346	0.5714
0.1584	19.0	114	2.4890	0.5476
0.1352	20.0	120	2.2551	0.5476
0.1352	21.0	126	1.7877	0.5714
0.1303	22.0	132	2.3533	0.5714
0.1303	23.0	138	2.3850	0.5714
0.0457	24.0	144	2.3656	0.6667
0.0031	25.0	150	2.3202	0.6190
0.0031	26.0	156	2.4368	0.6667
0.0014	27.0	162	2.5601	0.6429
0.0014	28.0	168	2.6475	0.6667
0.0004	29.0	174	2.7011	0.6667
0.0002	30.0	180	2.7227	0.6429
0.0002	31.0	186	2.7312	0.6429
0.0002	32.0	192	2.7259	0.6429
0.0002	33.0	198	2.7193	0.6429
0.0001	34.0	204	2.7128	0.6429
0.0001	35.0	210	2.7095	0.6429
0.0001	36.0	216	2.7084	0.6429
0.0001	37.0	222	2.7078	0.6429
0.0001	38.0	228	2.7079	0.6429
0.0001	39.0	234	2.7085	0.6429
0.0001	40.0	240	2.7091	0.6190
0.0001	41.0	246	2.7093	0.6190
0.0001	42.0	252	2.7093	0.6190
0.0001	43.0	258	2.7093	0.6190
0.0001	44.0	264	2.7093	0.6190
0.0001	45.0	270	2.7093	0.6190
0.0001	46.0	276	2.7093	0.6190
0.0001	47.0	282	2.7093	0.6190
0.0001	48.0	288	2.7093	0.6190
0.0001	49.0	294	2.7093	0.6190
0.0001	50.0	300	2.7093	0.6190

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1