metadata

library_name: transformers
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-DMAE-da-colab
    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: 0.7391304347826086

swinv2-tiny-patch4-window8-256-DMAE-da-colab

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: 0.9394
Accuracy: 0.7391

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3823	0.9565	11	1.4058	0.1957
1.3366	2.0	23	1.4482	0.1957
1.2352	2.9565	34	1.2309	0.4565
1.1374	4.0	46	1.1031	0.6087
1.0344	4.9565	57	1.0230	0.5870
0.8772	6.0	69	0.9115	0.6522
0.7321	6.9565	80	0.8858	0.6522
0.6319	8.0	92	0.8665	0.6522
0.6438	8.9565	103	0.7738	0.7174
0.4714	10.0	115	0.8492	0.6304
0.433	10.9565	126	0.8386	0.6957
0.4793	12.0	138	0.9394	0.7391
0.4769	12.9565	149	0.9471	0.6522
0.3872	14.0	161	1.1526	0.6087
0.3906	14.9565	172	1.0575	0.6522
0.3798	16.0	184	1.0593	0.6957
0.3377	16.9565	195	1.0783	0.6087
0.3919	18.0	207	1.1067	0.6522
0.3631	18.9565	218	1.1018	0.6739
0.2762	20.0	230	1.1479	0.6522
0.2935	20.9565	241	1.1055	0.6957
0.3029	22.0	253	1.1203	0.6739
0.2857	22.9565	264	1.2820	0.6304
0.2603	24.0	276	1.2550	0.6304
0.2162	24.9565	287	1.1655	0.6739
0.2465	26.0	299	1.2511	0.6739
0.2238	26.9565	310	1.3461	0.6304
0.2271	28.0	322	1.3472	0.6304
0.2694	28.9565	333	1.4501	0.6304
0.1903	30.0	345	1.4629	0.6304
0.2054	30.9565	356	1.4672	0.6304
0.199	32.0	368	1.4725	0.6304
0.2034	32.9565	379	1.4507	0.6522
0.2048	34.0	391	1.4330	0.6304
0.1767	34.9565	402	1.4638	0.6304
0.1799	36.0	414	1.4232	0.6304
0.1903	36.9565	425	1.4508	0.6304
0.1864	38.0	437	1.4460	0.6304
0.1818	38.2609	440	1.4456	0.6304

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3