metadata

license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swinv2-tiny-patch4-window8-256-RD-aptos19
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.616822429906542

swinv2-tiny-patch4-window8-256-RD-aptos19

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.6580
Accuracy: 0.6168

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: 0.00015
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	8	4.5659	0.4112
4.5175	2.0	16	3.6471	0.4112
3.927	3.0	24	1.6286	0.4112
1.6081	4.0	32	0.6781	0.5888
0.7702	5.0	40	0.8357	0.5888
0.7702	6.0	48	0.6766	0.5888
0.7502	7.0	56	0.7522	0.4112
0.7266	8.0	64	0.6792	0.5888
0.6954	9.0	72	0.6881	0.5888
0.6808	10.0	80	0.6780	0.5888
0.6808	11.0	88	0.7130	0.5888
0.7068	12.0	96	0.6771	0.5888
0.6792	13.0	104	0.6779	0.5888
0.6841	14.0	112	0.6766	0.5888
0.6777	15.0	120	0.6861	0.5888
0.6777	16.0	128	0.6773	0.5888
0.6818	17.0	136	0.6806	0.5888
0.6747	18.0	144	0.6929	0.5888
0.6814	19.0	152	0.6767	0.5888
0.6714	20.0	160	0.6745	0.5888
0.6714	21.0	168	0.6852	0.5888
0.6765	22.0	176	0.6816	0.5514
0.6822	23.0	184	0.6983	0.5888
0.6816	24.0	192	0.6706	0.5888
0.6868	25.0	200	0.6982	0.5701
0.6868	26.0	208	0.6878	0.5701
0.6724	27.0	216	0.6785	0.5888
0.6613	28.0	224	0.6843	0.5888
0.6501	29.0	232	0.7126	0.5888
0.6566	30.0	240	0.6917	0.5701
0.6566	31.0	248	0.7020	0.5607
0.6583	32.0	256	0.6782	0.5888
0.6501	33.0	264	0.6647	0.5888
0.654	34.0	272	0.6603	0.5981
0.6604	35.0	280	0.6873	0.5794
0.6604	36.0	288	0.6591	0.5794
0.6456	37.0	296	0.6580	0.6168
0.6483	38.0	304	0.6702	0.5981
0.6151	39.0	312	0.6785	0.5981
0.6291	40.0	320	0.6806	0.5981

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0