Hugging Face's logo

corranm
/
square_run_min_loss

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
square_run_min_loss / README.md
corranm's picture
corranm
End of training
c257af9 verified
preview code
|
raw
history blame contribute delete
9.08 kB
metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: square_run_min_loss
    results: []

square_run_min_loss

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5286
  • F1 Macro: 0.4619
  • F1 Micro: 0.5455
  • F1 Weighted: 0.5156
  • Precision Macro: 0.4696
  • Precision Micro: 0.5455
  • Precision Weighted: 0.5176
  • Recall Macro: 0.4841
  • Recall Micro: 0.5455
  • Recall Weighted: 0.5455
  • Accuracy: 0.5455

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 35

Training results

Training Loss Epoch Step Validation Loss F1 Macro F1 Micro F1 Weighted Precision Macro Precision Micro Precision Weighted Recall Macro Recall Micro Recall Weighted Accuracy
1.934 1.0 58 1.8780 0.0664 0.2045 0.0901 0.1708 0.2045 0.2415 0.1534 0.2045 0.2045 0.2045
1.8145 2.0 116 1.8828 0.0691 0.1742 0.0755 0.0608 0.1742 0.0658 0.1575 0.1742 0.1742 0.1742
1.8527 3.0 174 1.7131 0.2503 0.3788 0.3053 0.2573 0.3788 0.3062 0.3094 0.3788 0.3788 0.3788
1.6734 4.0 232 1.7940 0.1621 0.2803 0.2087 0.2145 0.2803 0.2624 0.2076 0.2803 0.2803 0.2803
1.6408 5.0 290 1.6808 0.1570 0.3333 0.1965 0.1432 0.3333 0.1858 0.2702 0.3333 0.3333 0.3333
1.5696 6.0 348 1.5061 0.3172 0.4470 0.3802 0.3895 0.4470 0.4186 0.3618 0.4470 0.4470 0.4470
1.4543 7.0 406 1.3674 0.4113 0.5152 0.4708 0.4077 0.5152 0.4630 0.4479 0.5152 0.5152 0.5152
1.2349 8.0 464 1.3137 0.4024 0.5 0.4550 0.4050 0.5 0.4606 0.4479 0.5 0.5 0.5
1.2544 9.0 522 1.3322 0.4209 0.5076 0.4748 0.4224 0.5076 0.4737 0.4480 0.5076 0.5076 0.5076
1.206 10.0 580 1.3818 0.3555 0.4621 0.4009 0.3931 0.4621 0.4372 0.4129 0.4621 0.4621 0.4621
1.0416 11.0 638 1.3142 0.4610 0.5606 0.5249 0.5218 0.5606 0.5872 0.4951 0.5606 0.5606 0.5606
1.1494 12.0 696 1.3793 0.4106 0.4773 0.4652 0.4619 0.4773 0.5256 0.4227 0.4773 0.4773 0.4773
0.7366 13.0 754 1.1936 0.5656 0.6515 0.6383 0.5708 0.6515 0.6446 0.5790 0.6515 0.6515 0.6515
1.3729 14.0 812 1.2285 0.5151 0.6061 0.5861 0.5714 0.6061 0.6314 0.5225 0.6061 0.6061 0.6061
1.3638 15.0 870 1.1742 0.5389 0.6212 0.6055 0.5617 0.6212 0.6334 0.5513 0.6212 0.6212 0.6212
0.9063 16.0 928 1.2325 0.5079 0.5985 0.5770 0.5077 0.5985 0.5715 0.5215 0.5985 0.5985 0.5985
0.4584 17.0 986 1.1497 0.5515 0.6364 0.6210 0.5676 0.6364 0.6286 0.5575 0.6364 0.6364 0.6364
0.86 18.0 1044 1.2673 0.4925 0.5909 0.5719 0.4968 0.5909 0.5681 0.5031 0.5909 0.5909 0.5909
0.2113 19.0 1102 1.2132 0.5180 0.6212 0.5986 0.5386 0.6212 0.6049 0.5257 0.6212 0.6212 0.6212
0.1168 20.0 1160 1.2442 0.5543 0.6136 0.6070 0.5742 0.6136 0.6164 0.5517 0.6136 0.6136 0.6136
0.3149 21.0 1218 1.2900 0.5446 0.6288 0.6146 0.5463 0.6288 0.6120 0.5534 0.6288 0.6288 0.6288
0.0793 22.0 1276 1.3290 0.5692 0.6288 0.6210 0.5960 0.6288 0.6359 0.5651 0.6288 0.6288 0.6288
0.1761 23.0 1334 1.4284 0.5572 0.6212 0.6032 0.6454 0.6212 0.6563 0.5516 0.6212 0.6212 0.6212
0.1714 24.0 1392 1.2994 0.5782 0.6288 0.6344 0.5899 0.6288 0.6461 0.5728 0.6288 0.6288 0.6288
0.465 25.0 1450 1.4011 0.5581 0.6136 0.6134 0.5662 0.6136 0.6188 0.5556 0.6136 0.6136 0.6136
0.2203 26.0 1508 1.4701 0.5741 0.6288 0.6266 0.6167 0.6288 0.6553 0.5676 0.6288 0.6288 0.6288
0.0574 27.0 1566 1.4511 0.5800 0.6364 0.6352 0.6073 0.6364 0.6546 0.5738 0.6364 0.6364 0.6364
0.0399 28.0 1624 1.4921 0.5674 0.6061 0.6133 0.5933 0.6061 0.6390 0.5645 0.6061 0.6061 0.6061
0.0269 29.0 1682 1.4752 0.5563 0.6288 0.6283 0.5686 0.6288 0.6350 0.5515 0.6288 0.6288 0.6288
0.0267 30.0 1740 1.5353 0.5621 0.6136 0.6142 0.5859 0.6136 0.6324 0.5565 0.6136 0.6136 0.6136
0.1094 31.0 1798 1.5126 0.5912 0.6515 0.6529 0.6028 0.6515 0.6604 0.5867 0.6515 0.6515 0.6515
0.0243 32.0 1856 1.4900 0.5985 0.6591 0.6563 0.6103 0.6591 0.6604 0.5935 0.6591 0.6591 0.6591
0.0366 33.0 1914 1.4680 0.6275 0.6894 0.6851 0.6369 0.6894 0.6855 0.6241 0.6894 0.6894 0.6894
0.0235 34.0 1972 1.4772 0.6216 0.6818 0.6795 0.6324 0.6818 0.6836 0.6173 0.6818 0.6818 0.6818
0.0345 35.0 2030 1.4754 0.6556 0.6970 0.6961 0.6722 0.6970 0.7038 0.6479 0.6970 0.6970 0.6970

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.6.0+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0