README.md

metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: custom-cloud-model
    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: 0.9423868060112

custom-cloud-model

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.2205
• Accuracy: 0.9424

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9957	1.0	80	0.8805	0.7675
0.829	2.0	160	0.3883	0.8539
0.7625	3.0	240	0.3983	0.8868
0.6964	4.0	320	0.2094	0.9300
0.422	5.0	400	0.2364	0.9259
0.3852	6.0	480	0.1997	0.9321
0.3882	7.0	560	0.2917	0.9136
0.2866	8.0	640	0.2616	0.9383
0.2217	9.0	720	0.2164	0.9424
0.1768	10.0	800	0.2873	0.9321
0.1724	11.0	880	0.3396	0.9239
0.1415	12.0	960	0.2368	0.9486
0.1551	13.0	1040	0.2600	0.9342
0.0656	14.0	1120	0.2325	0.9362
0.0751	15.0	1200	0.1522	0.9527
0.0712	16.0	1280	0.1996	0.9424
0.0907	17.0	1360	0.2027	0.9444
0.0609	18.0	1440	0.1956	0.9465
0.0816	19.0	1520	0.2157	0.9486
0.0359	20.0	1600	0.2205	0.9424

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1