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-OT
    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: 0.8225806451612904

swinv2-tiny-patch4-window8-256-OT

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: 0.6192
Accuracy: 0.8226

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	0.91	5	8.8439	0.0806
8.7922	2.0	11	8.0016	0.0806
8.7922	2.91	16	6.0009	0.0806
6.5264	4.0	22	2.7431	0.0806
6.5264	4.91	27	1.3018	0.4516
2.16	6.0	33	1.2696	0.4516
2.16	6.91	38	1.2057	0.4516
1.2876	8.0	44	1.2157	0.4516
1.2876	8.91	49	1.2459	0.4516
1.2456	10.0	55	1.2110	0.4516
1.1901	10.91	60	1.1861	0.4516
1.1901	12.0	66	1.0847	0.4677
1.0665	12.91	71	1.0944	0.4677
1.0665	14.0	77	1.1854	0.4677
1.033	14.91	82	1.0252	0.5
1.033	16.0	88	1.2164	0.5161
1.0323	16.91	93	1.0643	0.5
1.0323	18.0	99	0.9802	0.6613
0.9329	18.91	104	0.9475	0.5968
0.8619	20.0	110	0.9115	0.6452
0.8619	20.91	115	0.8894	0.6452
0.8019	22.0	121	0.8276	0.6935
0.8019	22.91	126	0.8156	0.6774
0.7675	24.0	132	0.7928	0.6290
0.7675	24.91	137	0.7163	0.7419
0.6762	26.0	143	0.7388	0.6774
0.6762	26.91	148	0.6519	0.7581
0.6771	28.0	154	0.6710	0.7419
0.6771	28.91	159	0.6074	0.7581
0.6424	30.0	165	0.6729	0.7258
0.6139	30.91	170	0.5744	0.7903
0.6139	32.0	176	0.6192	0.8226
0.5713	32.91	181	0.6453	0.7903
0.5713	34.0	187	0.6392	0.7903
0.5462	34.91	192	0.5956	0.8226
0.5462	36.0	198	0.5893	0.8226
0.5393	36.36	200	0.5898	0.8226

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0