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_fold1
    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: 0.8330550918196995

smids_1x_deit_tiny_sgd_001_fold1

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: 0.4210
Accuracy: 0.8331

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
1.0811	1.0	76	1.0552	0.4808
0.945	2.0	152	0.9389	0.5793
0.8473	3.0	228	0.8609	0.6361
0.7999	4.0	304	0.8002	0.6561
0.6841	5.0	380	0.7558	0.6745
0.6329	6.0	456	0.7159	0.6895
0.6112	7.0	532	0.6747	0.7112
0.5645	8.0	608	0.6404	0.7195
0.5735	9.0	684	0.6198	0.7162
0.4448	10.0	760	0.5963	0.7362
0.4826	11.0	836	0.5775	0.7446
0.4884	12.0	912	0.5596	0.7546
0.419	13.0	988	0.5449	0.7629
0.4668	14.0	1064	0.5322	0.7713
0.3648	15.0	1140	0.5206	0.7780
0.435	16.0	1216	0.5120	0.7796
0.3985	17.0	1292	0.5037	0.7846
0.3605	18.0	1368	0.4957	0.7913
0.4239	19.0	1444	0.4882	0.7980
0.3983	20.0	1520	0.4823	0.7980
0.3854	21.0	1596	0.4759	0.8047
0.3728	22.0	1672	0.4711	0.8114
0.3399	23.0	1748	0.4667	0.8047
0.3623	24.0	1824	0.4632	0.8114
0.3017	25.0	1900	0.4575	0.8164
0.388	26.0	1976	0.4531	0.8147
0.2998	27.0	2052	0.4507	0.8147
0.3486	28.0	2128	0.4459	0.8180
0.2911	29.0	2204	0.4440	0.8214
0.2957	30.0	2280	0.4418	0.8230
0.3626	31.0	2356	0.4385	0.8264
0.2887	32.0	2432	0.4361	0.8214
0.3011	33.0	2508	0.4347	0.8247
0.3216	34.0	2584	0.4321	0.8230
0.4399	35.0	2660	0.4322	0.8314
0.3353	36.0	2736	0.4294	0.8297
0.3238	37.0	2812	0.4281	0.8280
0.3158	38.0	2888	0.4267	0.8297
0.316	39.0	2964	0.4263	0.8331
0.3078	40.0	3040	0.4248	0.8297
0.2618	41.0	3116	0.4247	0.8331
0.2721	42.0	3192	0.4237	0.8314
0.2921	43.0	3268	0.4227	0.8347
0.3099	44.0	3344	0.4222	0.8347
0.3081	45.0	3420	0.4219	0.8347
0.2984	46.0	3496	0.4214	0.8347
0.2929	47.0	3572	0.4213	0.8331
0.3041	48.0	3648	0.4210	0.8331
0.2743	49.0	3724	0.4210	0.8331
0.3962	50.0	3800	0.4210	0.8331

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0