metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_base_rms_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: 0.885

smids_3x_deit_base_rms_00001_fold5

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.9726
Accuracy: 0.885

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
0.2653	1.0	225	0.2902	0.8817
0.1207	2.0	450	0.2612	0.9033
0.0968	3.0	675	0.3296	0.89
0.0298	4.0	900	0.4559	0.8883
0.0117	5.0	1125	0.4992	0.875
0.0194	6.0	1350	0.4918	0.8933
0.0374	7.0	1575	0.6989	0.8833
0.0219	8.0	1800	0.6248	0.8833
0.0334	9.0	2025	0.5552	0.89
0.0279	10.0	2250	0.6938	0.8767
0.0313	11.0	2475	0.7037	0.8933
0.0467	12.0	2700	0.7727	0.8817
0.0002	13.0	2925	0.7310	0.8883
0.0003	14.0	3150	0.7907	0.8883
0.0042	15.0	3375	0.6719	0.8917
0.0001	16.0	3600	0.7166	0.8883
0.0	17.0	3825	0.7878	0.8817
0.0001	18.0	4050	0.8205	0.885
0.0463	19.0	4275	0.7870	0.9017
0.0071	20.0	4500	0.8873	0.8867
0.0	21.0	4725	0.8762	0.89
0.0	22.0	4950	0.8528	0.89
0.0	23.0	5175	0.8386	0.8867
0.0046	24.0	5400	0.8618	0.8867
0.0	25.0	5625	0.8575	0.8883
0.0	26.0	5850	0.8716	0.8883
0.0	27.0	6075	0.9079	0.8833
0.0	28.0	6300	0.8533	0.895
0.0036	29.0	6525	0.9107	0.8883
0.0	30.0	6750	0.9085	0.8917
0.0	31.0	6975	0.9134	0.8883
0.0	32.0	7200	0.9080	0.8933
0.0034	33.0	7425	0.9660	0.8883
0.0	34.0	7650	0.9464	0.8883
0.0031	35.0	7875	0.9525	0.89
0.0	36.0	8100	0.9223	0.8917
0.0032	37.0	8325	0.9566	0.89
0.0	38.0	8550	0.9486	0.8933
0.0	39.0	8775	0.9542	0.8917
0.0	40.0	9000	0.9546	0.8883
0.0	41.0	9225	0.9671	0.8867
0.0	42.0	9450	0.9604	0.885
0.0026	43.0	9675	0.9661	0.8867
0.0	44.0	9900	0.9673	0.8883
0.0	45.0	10125	0.9685	0.8883
0.0	46.0	10350	0.9692	0.8867
0.0	47.0	10575	0.9716	0.8867
0.0	48.0	10800	0.9722	0.8867
0.0	49.0	11025	0.9726	0.8867
0.0	50.0	11250	0.9726	0.885

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2