metadata

license: apache-2.0
base_model: facebook/deit-small-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: 0.8968386023294509

smids_5x_deit_tiny_adamax_001_fold2

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: 0.8883
Accuracy: 0.8968

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
0.3644	1.0	375	0.3398	0.8702
0.2716	2.0	750	0.3172	0.8735
0.3497	3.0	1125	0.3400	0.8586
0.1669	4.0	1500	0.3794	0.8669
0.2114	5.0	1875	0.2911	0.8902
0.1067	6.0	2250	0.4133	0.8752
0.1489	7.0	2625	0.5329	0.8419
0.1233	8.0	3000	0.4750	0.8769
0.121	9.0	3375	0.4209	0.8852
0.0613	10.0	3750	0.3960	0.8918
0.0185	11.0	4125	0.5647	0.8769
0.07	12.0	4500	0.5185	0.8586
0.0467	13.0	4875	0.5032	0.8985
0.0041	14.0	5250	0.5742	0.8918
0.0599	15.0	5625	0.7221	0.8652
0.0363	16.0	6000	0.6853	0.8852
0.0212	17.0	6375	0.5687	0.8985
0.0007	18.0	6750	0.6790	0.8702
0.0025	19.0	7125	0.5146	0.8935
0.0511	20.0	7500	0.4949	0.9052
0.0231	21.0	7875	0.5535	0.8952
0.0	22.0	8250	0.7099	0.9002
0.011	23.0	8625	0.7090	0.8902
0.0118	24.0	9000	0.7009	0.9068
0.0	25.0	9375	0.6598	0.8985
0.0089	26.0	9750	0.7133	0.8902
0.0142	27.0	10125	0.5886	0.9052
0.0	28.0	10500	0.6881	0.9018
0.0001	29.0	10875	0.7679	0.8985
0.0001	30.0	11250	0.7339	0.8968
0.0038	31.0	11625	0.8413	0.8918
0.0044	32.0	12000	0.7669	0.9035
0.0049	33.0	12375	0.7980	0.9052
0.0	34.0	12750	0.7835	0.9035
0.0	35.0	13125	0.8137	0.8968
0.0	36.0	13500	0.8434	0.8968
0.0	37.0	13875	0.8282	0.8952
0.0	38.0	14250	0.8297	0.8968
0.0	39.0	14625	0.8386	0.8935
0.0034	40.0	15000	0.8364	0.8952
0.0	41.0	15375	0.8624	0.8985
0.0031	42.0	15750	0.8414	0.8968
0.0026	43.0	16125	0.9010	0.8902
0.0026	44.0	16500	0.8826	0.8952
0.0029	45.0	16875	0.8702	0.8968
0.0	46.0	17250	0.8727	0.8968
0.0055	47.0	17625	0.8804	0.8968
0.0	48.0	18000	0.8849	0.8968
0.0025	49.0	18375	0.8877	0.8968
0.0023	50.0	18750	0.8883	0.8968

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2