metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_deit_small_sgd_00001_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: 0.5483333333333333

smids_10x_deit_small_sgd_00001_fold3

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

Loss: 0.9545
Accuracy: 0.5483

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
1.0617	1.0	750	1.0842	0.3733
1.0585	2.0	1500	1.0794	0.37
1.0424	3.0	2250	1.0744	0.3733
1.0456	4.0	3000	1.0693	0.3767
1.0291	5.0	3750	1.0643	0.3833
1.0038	6.0	4500	1.0594	0.3917
1.0218	7.0	5250	1.0545	0.4017
1.0056	8.0	6000	1.0497	0.4083
0.9993	9.0	6750	1.0451	0.4133
0.9987	10.0	7500	1.0406	0.4233
1.005	11.0	8250	1.0361	0.43
0.9768	12.0	9000	1.0318	0.4367
0.9767	13.0	9750	1.0276	0.4383
0.9832	14.0	10500	1.0235	0.4417
0.9795	15.0	11250	1.0196	0.4517
0.9438	16.0	12000	1.0158	0.47
0.9511	17.0	12750	1.0122	0.4733
0.9685	18.0	13500	1.0086	0.475
0.9616	19.0	14250	1.0051	0.4833
0.9593	20.0	15000	1.0018	0.485
0.9173	21.0	15750	0.9985	0.49
0.9516	22.0	16500	0.9954	0.5017
0.9352	23.0	17250	0.9923	0.5033
0.9563	24.0	18000	0.9894	0.5083
0.9134	25.0	18750	0.9866	0.5117
0.9284	26.0	19500	0.9839	0.515
0.8974	27.0	20250	0.9813	0.52
0.9371	28.0	21000	0.9789	0.52
0.8946	29.0	21750	0.9765	0.5283
0.9089	30.0	22500	0.9743	0.5317
0.9026	31.0	23250	0.9722	0.5333
0.9027	32.0	24000	0.9702	0.5317
0.9034	33.0	24750	0.9683	0.5333
0.9095	34.0	25500	0.9666	0.5333
0.8767	35.0	26250	0.9650	0.5367
0.8854	36.0	27000	0.9635	0.5367
0.8862	37.0	27750	0.9621	0.5367
0.9211	38.0	28500	0.9608	0.5367
0.8993	39.0	29250	0.9597	0.535
0.8897	40.0	30000	0.9587	0.5383
0.8933	41.0	30750	0.9578	0.5417
0.8954	42.0	31500	0.9571	0.5483
0.887	43.0	32250	0.9564	0.5483
0.902	44.0	33000	0.9558	0.5483
0.8561	45.0	33750	0.9554	0.5483
0.8814	46.0	34500	0.9551	0.5483
0.8975	47.0	35250	0.9548	0.5483
0.8624	48.0	36000	0.9546	0.5483
0.8832	49.0	36750	0.9546	0.5483
0.8754	50.0	37500	0.9545	0.5483

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2