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: 0.6701570749282837

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: 1.6095
• Accuracy: 0.6702

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0582	1.0	34	1.8348	0.3351
1.2969	2.0	68	1.2586	0.5288
0.9759	3.0	102	1.0590	0.6047
0.8705	4.0	136	0.9122	0.6466
0.6166	5.0	170	0.9506	0.6597
0.5408	6.0	204	0.9137	0.6623
0.3518	7.0	238	1.1081	0.6440
0.3488	8.0	272	1.0060	0.6545
0.3068	9.0	306	1.0221	0.6780
0.2824	10.0	340	1.1638	0.6283
0.2048	11.0	374	1.2044	0.6518
0.1972	12.0	408	1.2988	0.6440
0.1818	13.0	442	1.1882	0.6728
0.1316	14.0	476	1.2993	0.6518
0.12	15.0	510	1.2681	0.6754
0.0997	16.0	544	1.3582	0.6780
0.1069	17.0	578	1.3963	0.6571
0.078	18.0	612	1.4492	0.6675
0.0783	19.0	646	1.4504	0.6545
0.0765	20.0	680	1.5165	0.6675
0.068	21.0	714	1.4972	0.6649
0.0768	22.0	748	1.4949	0.6492
0.0631	23.0	782	1.5874	0.6754
0.0425	24.0	816	1.5859	0.6675
0.0503	25.0	850	1.5003	0.6702
0.0486	26.0	884	1.5484	0.6675
0.0383	27.0	918	1.5526	0.6780
0.036	28.0	952	1.6089	0.6623
0.0212	29.0	986	1.5983	0.6754
0.0269	30.0	1020	1.6095	0.6702

Framework versions

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