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_00001_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: 0.88

smids_1x_deit_tiny_adamax_00001_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: 0.6353
Accuracy: 0.88

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: 1e-05
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
0.7267	1.0	75	0.6452	0.735
0.4663	2.0	150	0.4479	0.8267
0.3889	3.0	225	0.3768	0.8467
0.4049	4.0	300	0.3517	0.8567
0.3455	5.0	375	0.3282	0.8733
0.2551	6.0	450	0.3120	0.8783
0.253	7.0	525	0.3013	0.8733
0.2149	8.0	600	0.3148	0.8733
0.1593	9.0	675	0.3191	0.8733
0.1223	10.0	750	0.3121	0.875
0.186	11.0	825	0.3224	0.875
0.0958	12.0	900	0.3269	0.875
0.1004	13.0	975	0.3361	0.8833
0.0897	14.0	1050	0.3443	0.8833
0.0668	15.0	1125	0.4038	0.8683
0.0352	16.0	1200	0.3877	0.865
0.026	17.0	1275	0.3941	0.88
0.0445	18.0	1350	0.4318	0.8767
0.0301	19.0	1425	0.4418	0.8783
0.0287	20.0	1500	0.4505	0.88
0.0241	21.0	1575	0.4895	0.8817
0.01	22.0	1650	0.4921	0.8833
0.0214	23.0	1725	0.5270	0.88
0.0229	24.0	1800	0.5245	0.8767
0.0113	25.0	1875	0.5406	0.8767
0.0032	26.0	1950	0.5510	0.8817
0.0224	27.0	2025	0.5698	0.8783
0.029	28.0	2100	0.5630	0.8733
0.0174	29.0	2175	0.5715	0.87
0.0132	30.0	2250	0.5787	0.8767
0.0005	31.0	2325	0.6094	0.8783
0.0004	32.0	2400	0.5908	0.875
0.0169	33.0	2475	0.6294	0.8767
0.0005	34.0	2550	0.6011	0.875
0.0188	35.0	2625	0.6103	0.88
0.0003	36.0	2700	0.6040	0.8783
0.0093	37.0	2775	0.6346	0.875
0.0003	38.0	2850	0.6319	0.875
0.0004	39.0	2925	0.6321	0.875
0.0005	40.0	3000	0.6332	0.875
0.0131	41.0	3075	0.6261	0.88
0.0004	42.0	3150	0.6258	0.8783
0.0183	43.0	3225	0.6307	0.8783
0.0032	44.0	3300	0.6338	0.8783
0.0145	45.0	3375	0.6347	0.8817
0.0002	46.0	3450	0.6408	0.88
0.0126	47.0	3525	0.6363	0.8817
0.0174	48.0	3600	0.6374	0.8833
0.0002	49.0	3675	0.6360	0.8817
0.0129	50.0	3750	0.6353	0.88

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0