Hugging Face's logo

Melo1512
/
vit-msn-small-wbc-classifier-0316-cleandataset-10

Image Classification
Transformers
TensorBoard
Safetensors
vit_msn
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vit-msn-small-wbc-classifier-0316-cleandataset-10 / README.md
Melo1512's picture
Melo1512
End of training
88f9005 verified
preview code
|
raw
history blame contribute delete
8.19 kB
metadata
library_name: transformers
license: apache-2.0
base_model: Melo1512/vit-msn-small-wbc-classifier-0316-cleandataset-10
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-msn-small-wbc-classifier-0316-cleandataset-10
    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: 0.8599162542824514

vit-msn-small-wbc-classifier-0316-cleandataset-10

This model is a fine-tuned version of Melo1512/vit-msn-small-wbc-classifier-0316-cleandataset-10 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3943
  • Accuracy: 0.8599

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: 1e-07
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3785 0.9730 18 0.3985 0.8569
0.3432 2.0 37 0.3996 0.8557
0.3454 2.9730 55 0.4011 0.8553
0.3639 4.0 74 0.4034 0.8538
0.3544 4.9730 92 0.4049 0.8546
0.3607 6.0 111 0.4057 0.8538
0.3652 6.9730 129 0.4046 0.8561
0.3639 8.0 148 0.4046 0.8553
0.3472 8.9730 166 0.4048 0.8561
0.3704 10.0 185 0.4033 0.8546
0.3954 10.9730 203 0.4009 0.8565
0.372 12.0 222 0.4022 0.8546
0.3599 12.9730 240 0.4005 0.8561
0.3689 14.0 259 0.4018 0.8550
0.3687 14.9730 277 0.4016 0.8553
0.3521 16.0 296 0.4000 0.8561
0.3817 16.9730 314 0.4001 0.8553
0.3768 18.0 333 0.3994 0.8550
0.3835 18.9730 351 0.4041 0.8546
0.3833 20.0 370 0.4042 0.8553
0.36 20.9730 388 0.4012 0.8561
0.3729 22.0 407 0.4023 0.8565
0.3647 22.9730 425 0.4029 0.8546
0.3811 24.0 444 0.4011 0.8561
0.38 24.9730 462 0.3999 0.8569
0.3588 26.0 481 0.3994 0.8557
0.3554 26.9730 499 0.3991 0.8561
0.354 28.0 518 0.3995 0.8561
0.3577 28.9730 536 0.3986 0.8557
0.3723 30.0 555 0.3998 0.8561
0.3763 30.9730 573 0.3994 0.8561
0.3701 32.0 592 0.3994 0.8569
0.3728 32.9730 610 0.3980 0.8553
0.3649 34.0 629 0.3964 0.8565
0.3551 34.9730 647 0.3982 0.8569
0.3832 36.0 666 0.3977 0.8576
0.3459 36.9730 684 0.3968 0.8561
0.3613 38.0 703 0.3966 0.8561
0.3588 38.9730 721 0.3968 0.8565
0.3483 40.0 740 0.3958 0.8573
0.3693 40.9730 758 0.3967 0.8576
0.3544 42.0 777 0.3988 0.8576
0.3701 42.9730 795 0.3976 0.8573
0.3649 44.0 814 0.3984 0.8565
0.3621 44.9730 832 0.3966 0.8573
0.3494 46.0 851 0.3989 0.8573
0.373 46.9730 869 0.3993 0.8573
0.3911 48.0 888 0.3978 0.8576
0.3716 48.9730 906 0.3967 0.8576
0.3685 50.0 925 0.3968 0.8576
0.3879 50.9730 943 0.3950 0.8573
0.3774 52.0 962 0.3951 0.8580
0.3588 52.9730 980 0.3950 0.8584
0.3746 54.0 999 0.3959 0.8584
0.3677 54.9730 1017 0.3960 0.8584
0.3608 56.0 1036 0.3965 0.8588
0.3518 56.9730 1054 0.3963 0.8580
0.3554 58.0 1073 0.3957 0.8588
0.3584 58.9730 1091 0.3957 0.8584
0.3776 60.0 1110 0.3948 0.8592
0.364 60.9730 1128 0.3942 0.8588
0.3647 62.0 1147 0.3942 0.8584
0.3613 62.9730 1165 0.3949 0.8588
0.3509 64.0 1184 0.3961 0.8584
0.3816 64.9730 1202 0.3967 0.8584
0.3552 66.0 1221 0.3957 0.8588
0.3461 66.9730 1239 0.3946 0.8588
0.364 68.0 1258 0.3940 0.8588
0.372 68.9730 1276 0.3943 0.8599
0.347 70.0 1295 0.3939 0.8592
0.3537 70.9730 1313 0.3943 0.8599
0.3537 72.0 1332 0.3950 0.8595
0.3823 72.9730 1350 0.3951 0.8592
0.3454 74.0 1369 0.3947 0.8592
0.3667 74.9730 1387 0.3949 0.8592
0.3585 76.0 1406 0.3945 0.8592
0.356 76.9730 1424 0.3947 0.8592
0.337 78.0 1443 0.3949 0.8592
0.3588 78.9730 1461 0.3944 0.8592
0.3591 80.0 1480 0.3941 0.8592
0.3638 80.9730 1498 0.3943 0.8592
0.367 82.0 1517 0.3941 0.8592
0.3694 82.9730 1535 0.3943 0.8592
0.3779 84.0 1554 0.3941 0.8592
0.344 84.9730 1572 0.3939 0.8595
0.3619 86.0 1591 0.3935 0.8592
0.342 86.9730 1609 0.3934 0.8595
0.3686 88.0 1628 0.3931 0.8595
0.3407 88.9730 1646 0.3931 0.8595
0.3553 90.0 1665 0.3933 0.8599
0.367 90.9730 1683 0.3934 0.8595
0.3665 92.0 1702 0.3932 0.8599
0.3684 92.9730 1720 0.3932 0.8599
0.3685 94.0 1739 0.3934 0.8595
0.375 94.9730 1757 0.3934 0.8592
0.3564 96.0 1776 0.3934 0.8592
0.362 96.9730 1794 0.3934 0.8592
0.3688 97.2973 1800 0.3934 0.8592

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.19.1