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-DMAE-8e-6
    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: 0.10869565217391304

swinv2-tiny-patch4-window8-256-DMAE-8e-6

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: 7.9427
Accuracy: 0.1087

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: 8e-06
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	0.86	3	7.9427	0.1087
No log	2.0	7	7.9381	0.1087
7.9636	2.86	10	7.9301	0.1087
7.9636	4.0	14	7.9088	0.1087
7.9636	4.86	17	7.8857	0.1087
7.8732	6.0	21	7.8450	0.1087
7.8732	6.86	24	7.8049	0.1087
7.8732	8.0	28	7.7376	0.1087
7.6568	8.86	31	7.6783	0.1087
7.6568	10.0	35	7.5943	0.1087
7.6568	10.86	38	7.5288	0.1087
7.7458	12.0	42	7.4353	0.1087
7.7458	12.86	45	7.3610	0.1087
7.7458	14.0	49	7.2614	0.1087
7.3025	14.86	52	7.1894	0.1087
7.3025	16.0	56	7.0993	0.1087
7.3025	16.86	59	7.0348	0.1087
7.0862	18.0	63	6.9525	0.1087
7.0862	18.86	66	6.8945	0.1087
6.9553	20.0	70	6.8253	0.1087
6.9553	20.86	73	6.7795	0.1087
6.9553	22.0	77	6.7202	0.1087
6.8024	22.86	80	6.6757	0.1087
6.8024	24.0	84	6.6210	0.1087
6.8024	24.86	87	6.5785	0.1087
6.6652	26.0	91	6.5275	0.1087
6.6652	26.86	94	6.4949	0.1087
6.6652	28.0	98	6.4589	0.1087
6.467	28.86	101	6.4354	0.1087
6.467	30.0	105	6.4094	0.1087
6.467	30.86	108	6.3946	0.1087
6.4984	32.0	112	6.3796	0.1087
6.4984	32.86	115	6.3719	0.1087
6.4984	34.0	119	6.3668	0.1087
6.4603	34.29	120	6.3664	0.1087

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0