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_sgd_001_fold4
    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: 0.88

smids_5x_deit_tiny_sgd_001_fold4

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: 0.3364
Accuracy: 0.88

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
0.7169	1.0	375	0.7100	0.7433
0.5434	2.0	750	0.5311	0.79
0.3914	3.0	1125	0.4593	0.8267
0.3964	4.0	1500	0.4238	0.8467
0.3421	5.0	1875	0.4004	0.84
0.3188	6.0	2250	0.3866	0.845
0.3163	7.0	2625	0.3739	0.855
0.2969	8.0	3000	0.3662	0.8533
0.2771	9.0	3375	0.3587	0.8567
0.2869	10.0	3750	0.3526	0.8533
0.2532	11.0	4125	0.3512	0.855
0.2402	12.0	4500	0.3469	0.8617
0.2625	13.0	4875	0.3448	0.855
0.2773	14.0	5250	0.3426	0.8583
0.1973	15.0	5625	0.3405	0.86
0.1939	16.0	6000	0.3381	0.8633
0.2343	17.0	6375	0.3367	0.8633
0.2253	18.0	6750	0.3355	0.8667
0.2395	19.0	7125	0.3367	0.8633
0.1792	20.0	7500	0.3346	0.8667
0.2141	21.0	7875	0.3352	0.865
0.206	22.0	8250	0.3351	0.8683
0.1902	23.0	8625	0.3337	0.87
0.1953	24.0	9000	0.3324	0.8717
0.2357	25.0	9375	0.3339	0.8683
0.1602	26.0	9750	0.3324	0.8717
0.2058	27.0	10125	0.3335	0.8667
0.1817	28.0	10500	0.3349	0.87
0.1565	29.0	10875	0.3343	0.8667
0.2147	30.0	11250	0.3327	0.8717
0.1942	31.0	11625	0.3340	0.87
0.1633	32.0	12000	0.3333	0.8717
0.1571	33.0	12375	0.3335	0.8733
0.218	34.0	12750	0.3350	0.8733
0.1424	35.0	13125	0.3354	0.8783
0.1796	36.0	13500	0.3353	0.8717
0.1702	37.0	13875	0.3349	0.8767
0.161	38.0	14250	0.3343	0.875
0.1961	39.0	14625	0.3352	0.8767
0.1721	40.0	15000	0.3365	0.88
0.1561	41.0	15375	0.3358	0.8783
0.1604	42.0	15750	0.3354	0.8783
0.1786	43.0	16125	0.3364	0.8817
0.1636	44.0	16500	0.3360	0.88
0.2307	45.0	16875	0.3365	0.8783
0.1578	46.0	17250	0.3360	0.8783
0.232	47.0	17625	0.3366	0.8817
0.1744	48.0	18000	0.3365	0.88
0.1493	49.0	18375	0.3364	0.88
0.1447	50.0	18750	0.3364	0.88

Framework versions

Transformers 4.32.1
Pytorch 2.1.1+cu121
Datasets 2.12.0
Tokenizers 0.13.2