metadata

license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: SWv2-DMAE-H-5-ps-clean-fix-U-40-Cross-2
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9047619047619048

SWv2-DMAE-H-5-ps-clean-fix-U-40-Cross-2

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: 0.3493
Accuracy: 0.9048

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: 4e-05
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
1.6089	0.98	12	1.6061	0.2024
1.6027	1.96	24	1.5770	0.2024
1.563	2.94	36	1.5561	0.2024
1.5141	4.0	49	1.4404	0.2024
1.3727	4.98	61	1.2293	0.6310
1.2375	5.96	73	0.9512	0.7738
1.0523	6.94	85	0.7222	0.75
0.9473	8.0	98	0.5629	0.8571
0.7895	8.98	110	0.4626	0.8571
0.7525	9.96	122	0.4545	0.8095
0.669	10.94	134	0.4193	0.8452
0.6892	12.0	147	0.4371	0.8333
0.6742	12.98	159	0.4079	0.8452
0.5667	13.96	171	0.3863	0.8690
0.56	14.94	183	0.4160	0.8571
0.5683	16.0	196	0.4555	0.7976
0.5347	16.98	208	0.3839	0.8571
0.4723	17.96	220	0.3763	0.8810
0.4566	18.94	232	0.3525	0.8690
0.4328	20.0	245	0.3548	0.8690
0.4691	20.98	257	0.3934	0.8571
0.3675	21.96	269	0.3728	0.8810
0.3744	22.94	281	0.3810	0.8690
0.3883	24.0	294	0.3982	0.8571
0.3633	24.98	306	0.4277	0.8690
0.3439	25.96	318	0.3579	0.8810
0.3924	26.94	330	0.3929	0.8571
0.3139	28.0	343	0.3637	0.8929
0.2987	28.98	355	0.3493	0.9048
0.3285	29.96	367	0.3524	0.9048
0.4061	30.94	379	0.3607	0.9048
0.3307	32.0	392	0.3616	0.8810
0.2882	32.98	404	0.3529	0.8810
0.3074	33.96	416	0.3429	0.8929
0.3141	34.94	428	0.3420	0.8929
0.3206	36.0	441	0.3537	0.8929
0.2772	36.98	453	0.3475	0.8929
0.2707	37.96	465	0.3461	0.8690
0.2857	38.94	477	0.3453	0.8929
0.277	39.18	480	0.3454	0.8929

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0