metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_tiny_adamax_001_fold2
    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: 0.8901830282861897

smids_5x_deit_tiny_adamax_001_fold2

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: 1.1513
Accuracy: 0.8902

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
0.3758	1.0	375	0.3275	0.8619
0.3244	2.0	750	0.4328	0.8403
0.3305	3.0	1125	0.3559	0.8586
0.2057	4.0	1500	0.3484	0.8752
0.2037	5.0	1875	0.3334	0.8918
0.109	6.0	2250	0.3396	0.8869
0.1296	7.0	2625	0.4274	0.8719
0.1447	8.0	3000	0.4555	0.8569
0.0656	9.0	3375	0.4650	0.8869
0.0303	10.0	3750	0.5987	0.8602
0.0379	11.0	4125	0.5753	0.8835
0.0368	12.0	4500	0.6264	0.8669
0.0495	13.0	4875	0.6979	0.8569
0.0376	14.0	5250	0.7442	0.8636
0.0604	15.0	5625	0.8422	0.8636
0.0353	16.0	6000	0.7521	0.8852
0.0761	17.0	6375	0.7920	0.8752
0.004	18.0	6750	1.0354	0.8702
0.0148	19.0	7125	0.7279	0.8785
0.0237	20.0	7500	0.7424	0.8735
0.0011	21.0	7875	0.7919	0.8802
0.0017	22.0	8250	0.8106	0.8918
0.0086	23.0	8625	0.8451	0.8735
0.0037	24.0	9000	0.8674	0.8735
0.0002	25.0	9375	0.8393	0.8869
0.0036	26.0	9750	0.8897	0.8902
0.0019	27.0	10125	0.8685	0.8885
0.0	28.0	10500	0.8366	0.8902
0.0007	29.0	10875	0.9524	0.8985
0.0002	30.0	11250	0.9036	0.8918
0.0073	31.0	11625	0.9747	0.8935
0.0057	32.0	12000	0.9823	0.8885
0.0116	33.0	12375	0.9806	0.8935
0.0	34.0	12750	1.0179	0.8885
0.0	35.0	13125	1.0978	0.8785
0.0	36.0	13500	0.9957	0.8852
0.0	37.0	13875	1.0261	0.8902
0.0	38.0	14250	1.0512	0.8885
0.0	39.0	14625	1.0513	0.8902
0.0035	40.0	15000	1.0782	0.8902
0.0	41.0	15375	1.0839	0.8885
0.0032	42.0	15750	1.1078	0.8885
0.0027	43.0	16125	1.1099	0.8902
0.0028	44.0	16500	1.1218	0.8902
0.0032	45.0	16875	1.1207	0.8885
0.0	46.0	17250	1.1330	0.8885
0.0059	47.0	17625	1.1405	0.8885
0.0	48.0	18000	1.1472	0.8885
0.0026	49.0	18375	1.1507	0.8885
0.0022	50.0	18750	1.1513	0.8902

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2