Edit model card

swin-tiny-patch4-window7-224-FINALConcreteClassifier-SWIN50epochsAUGMENTED

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

  • Loss: 0.0000
  • Accuracy: {'accuracy': 1.0}
  • F1: {'f1': 1.0}
  • Precision: {'precision': 1.0}
  • Recall: {'recall': 1.0}

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.3875 0.9994 407 0.2752 {'accuracy': 0.9272224781206817} {'f1': 0.9299076962468851} {'precision': 0.9308936484753314} {'recall': 0.9298532516284993}
0.2001 1.9988 814 0.0583 {'accuracy': 0.983110701673576} {'f1': 0.9837765293059086} {'precision': 0.9846788595224822} {'recall': 0.9836211079426627}
0.1626 2.9982 1221 0.0207 {'accuracy': 0.9938584369722094} {'f1': 0.9941597712458348} {'precision': 0.9943896461187967} {'recall': 0.9941051527238169}
0.088 4.0 1629 0.0088 {'accuracy': 0.9969292184861047} {'f1': 0.9970539871142889} {'precision': 0.9970656946831583} {'recall': 0.9970776666292009}
0.1079 4.9994 2036 0.0046 {'accuracy': 0.9987716873944419} {'f1': 0.9988142853329625} {'precision': 0.9988066339632395} {'recall': 0.99882263684388}
0.102 5.9988 2443 0.0034 {'accuracy': 0.9989252264701366} {'f1': 0.9989565946802677} {'precision': 0.998933981872335} {'recall': 0.9989857043158454}
0.0594 6.9982 2850 0.0118 {'accuracy': 0.9972362966374942} {'f1': 0.9973346644159505} {'precision': 0.9973144572332442} {'recall': 0.9974051297029489}
0.0335 8.0 3258 0.0030 {'accuracy': 0.9987716873944419} {'f1': 0.9988034164628696} {'precision': 0.9987863396601946} {'recall': 0.9988260749455921}
0.0368 8.9994 3665 0.0036 {'accuracy': 0.9990787655458314} {'f1': 0.999110823927686} {'precision': 0.99909200968523} {'recall': 0.9991359447004609}
0.0564 9.9988 4072 0.0040 {'accuracy': 0.9984646092430524} {'f1': 0.998509715288995} {'precision': 0.9984881711855396} {'recall': 0.9985402551521871}
0.052 10.9982 4479 0.0021 {'accuracy': 0.9989252264701366} {'f1': 0.998956584824745} {'precision': 0.9989419496612204} {'recall': 0.9989777168523596}
0.0429 12.0 4887 0.0033 {'accuracy': 0.9983110701673575} {'f1': 0.9983570515623278} {'precision': 0.9984174575960668} {'recall': 0.9983115930842853}
0.047 12.9994 5294 0.0008 {'accuracy': 0.9998464609243052} {'f1': 0.9998504202011455} {'precision': 0.9998534583821805} {'recall': 0.9998475609756098}
0.0391 13.9988 5701 0.0005 {'accuracy': 0.9998464609243052} {'f1': 0.999851770829272} {'precision': 0.9998561565017261} {'recall': 0.9998475609756098}
0.0499 14.9982 6108 0.0011 {'accuracy': 0.9995393827729157} {'f1': 0.9995512387635233} {'precision': 0.9995614035087719} {'recall': 0.9995426829268292}
0.0351 16.0 6516 0.0003 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.021 16.9994 6923 0.0054 {'accuracy': 0.9984646092430524} {'f1': 0.9985038406196534} {'precision': 0.9985498839907192} {'recall': 0.9984756097560976}
0.0384 17.9988 7330 0.0004 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0093 18.9982 7737 0.0007 {'accuracy': 0.9995393827729157} {'f1': 0.999555371210602} {'precision': 0.9995443499392467} {'recall': 0.9995679723502304}
0.0264 20.0 8145 0.0004 {'accuracy': 0.9998464609243052} {'f1': 0.9998528788154148} {'precision': 0.9998499399759904} {'recall': 0.9998559907834101}
0.0191 20.9994 8552 0.0002 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.05 21.9988 8959 0.0002 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0155 22.9982 9366 0.0003 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0164 24.0 9774 0.0038 {'accuracy': 0.9987716873944419} {'f1': 0.998813860406548} {'precision': 0.9988584474885844} {'recall': 0.998780487804878}
0.0202 24.9994 10181 0.0004 {'accuracy': 0.9998464609243052} {'f1': 0.9998504202011455} {'precision': 0.9998534583821805} {'recall': 0.9998475609756098}
0.0576 25.9988 10588 0.0001 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0098 26.9982 10995 0.0001 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0091 28.0 11403 0.0001 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0259 28.9994 11810 0.0004 {'accuracy': 0.9995393827729157} {'f1': 0.999555371210602} {'precision': 0.9995443499392467} {'recall': 0.9995679723502304}
0.0064 29.9988 12217 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0097 30.9982 12624 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0102 32.0 13032 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0082 32.9994 13439 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0094 33.9988 13846 0.0002 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0085 34.9982 14253 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0079 36.0 14661 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.006 36.9994 15068 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0039 37.9988 15475 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.023 38.9982 15882 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0026 40.0 16290 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0289 40.9994 16697 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0026 41.9988 17104 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0155 42.9982 17511 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0016 44.0 17919 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0005 44.9994 18326 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0058 45.9988 18733 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0012 46.9982 19140 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.001 48.0 19548 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0016 48.9994 19955 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}
0.0015 49.9693 20350 0.0000 {'accuracy': 1.0} {'f1': 1.0} {'precision': 1.0} {'recall': 1.0}

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.3.1
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
20
Safetensors
Model size
27.6M params
Tensor type
I64
·
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for mmomm25/swin-tiny-patch4-window7-224-FINALConcreteClassifier-SWIN50epochsAUGMENTED

Finetuned
(464)
this model

Evaluation results