metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_tiny_sgd_0001_fold3
    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: 0.7683333333333333

smids_3x_deit_tiny_sgd_0001_fold3

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: 0.6313
Accuracy: 0.7683

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: 0.0001
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
1.2114	1.0	225	1.2115	0.3783
1.0735	2.0	450	1.1384	0.3983
1.097	3.0	675	1.1002	0.4133
1.0469	4.0	900	1.0702	0.4533
1.0229	5.0	1125	1.0448	0.48
0.99	6.0	1350	1.0213	0.5
0.9781	7.0	1575	0.9993	0.5117
0.9907	8.0	1800	0.9784	0.54
0.927	9.0	2025	0.9582	0.545
0.8847	10.0	2250	0.9391	0.5583
0.9329	11.0	2475	0.9207	0.5733
0.8984	12.0	2700	0.9031	0.59
0.8494	13.0	2925	0.8859	0.605
0.8194	14.0	3150	0.8694	0.6183
0.7869	15.0	3375	0.8536	0.6283
0.8309	16.0	3600	0.8389	0.635
0.7966	17.0	3825	0.8246	0.64
0.8108	18.0	4050	0.8113	0.64
0.801	19.0	4275	0.7985	0.6533
0.771	20.0	4500	0.7864	0.66
0.7097	21.0	4725	0.7747	0.67
0.7109	22.0	4950	0.7636	0.6767
0.7079	23.0	5175	0.7529	0.6867
0.7294	24.0	5400	0.7431	0.69
0.7458	25.0	5625	0.7335	0.6883
0.6793	26.0	5850	0.7246	0.6917
0.6665	27.0	6075	0.7159	0.7017
0.6522	28.0	6300	0.7080	0.7083
0.7013	29.0	6525	0.7004	0.715
0.6636	30.0	6750	0.6932	0.7183
0.6224	31.0	6975	0.6867	0.72
0.6822	32.0	7200	0.6803	0.725
0.6885	33.0	7425	0.6745	0.7283
0.6623	34.0	7650	0.6692	0.7333
0.6059	35.0	7875	0.6642	0.735
0.6546	36.0	8100	0.6598	0.7417
0.6233	37.0	8325	0.6556	0.7433
0.6474	38.0	8550	0.6519	0.7467
0.606	39.0	8775	0.6483	0.75
0.6243	40.0	9000	0.6453	0.755
0.6167	41.0	9225	0.6425	0.7567
0.6518	42.0	9450	0.6401	0.7617
0.5844	43.0	9675	0.6380	0.7633
0.6425	44.0	9900	0.6361	0.7633
0.6354	45.0	10125	0.6346	0.7633
0.5465	46.0	10350	0.6333	0.765
0.6036	47.0	10575	0.6324	0.7667
0.5553	48.0	10800	0.6318	0.7683
0.6342	49.0	11025	0.6314	0.7683
0.5635	50.0	11250	0.6313	0.7683

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2