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-da2-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: 0.7608695652173914

swinv2-tiny-patch4-window8-256-DMAE-da2-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: 0.9368
Accuracy: 0.7609

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
1.4149	0.9565	11	1.3905	0.2174
1.3431	1.9348	22	1.3828	0.3043
1.2396	2.9130	33	1.2675	0.4348
1.1377	3.9783	45	1.2067	0.3478
1.0144	4.9565	56	0.9060	0.6087
0.9016	5.9348	67	0.8025	0.6739
0.7941	6.9130	78	0.7812	0.6957
0.6986	7.9783	90	0.9441	0.5870
0.6245	8.9565	101	0.8641	0.6957
0.6044	9.9348	112	0.8648	0.6087
0.536	10.9130	123	0.8800	0.5870
0.4825	11.9783	135	0.8388	0.7391
0.4972	12.9565	146	0.8763	0.7174
0.4284	13.9348	157	0.8228	0.6957
0.3961	14.9130	168	0.8260	0.7174
0.3877	15.9783	180	0.9368	0.7609
0.3744	16.9565	191	1.1221	0.6304
0.3266	17.9348	202	1.0177	0.6739
0.3257	18.9130	213	1.0300	0.6957
0.3164	19.9783	225	1.1344	0.6957
0.2965	20.9565	236	0.9283	0.7391
0.293	21.9348	247	1.0128	0.6957
0.2929	22.9130	258	1.0450	0.7609
0.2878	23.9783	270	1.1482	0.7174
0.2447	24.9565	281	1.0716	0.7174
0.2601	25.9348	292	1.0770	0.6957
0.2299	26.9130	303	1.1769	0.7391
0.2401	27.9783	315	1.1407	0.7174
0.2347	28.9565	326	1.1929	0.6957
0.2584	29.9348	337	1.0957	0.6739
0.2204	30.9130	348	1.1721	0.6739
0.2031	31.9783	360	1.0843	0.6739
0.2241	32.9565	371	1.1350	0.6957
0.1798	33.9348	382	1.2419	0.6957
0.2435	34.9130	393	1.1522	0.6957
0.1857	35.9783	405	1.1207	0.6957
0.1889	36.9565	416	1.1711	0.6957
0.2043	37.9348	427	1.1978	0.6957
0.1951	38.9130	438	1.2107	0.7174
0.1901	39.1087	440	1.2108	0.7174

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3