Augusto777's picture
Model save
33be873 verified
|
raw
history blame
7.66 kB
metadata
base_model: MBZUAI/swiftformer-xs
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swiftformer-xs-ve-U13-b-80
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6956521739130435

swiftformer-xs-ve-U13-b-80

This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0596
  • Accuracy: 0.6957

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: 0.0003
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • 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
No log 0.92 6 1.3858 0.2391
1.3856 2.0 13 1.3828 0.2826
1.3856 2.92 19 1.3769 0.1957
1.3734 4.0 26 1.3624 0.1304
1.2978 4.92 32 1.3553 0.1522
1.2978 6.0 39 1.4121 0.0870
1.1702 6.92 45 1.3720 0.2391
1.0743 8.0 52 1.3162 0.3478
1.0743 8.92 58 1.2252 0.3696
0.9504 10.0 65 1.1689 0.4348
0.8305 10.92 71 1.0516 0.5870
0.8305 12.0 78 0.9548 0.6739
0.7374 12.92 84 0.9138 0.7174
0.6207 14.0 91 0.9353 0.6522
0.6207 14.92 97 0.8640 0.6739
0.5184 16.0 104 0.8122 0.7826
0.4606 16.92 110 0.7136 0.8043
0.4606 18.0 117 0.7955 0.7609
0.4332 18.92 123 0.7790 0.6957
0.3315 20.0 130 0.8117 0.7391
0.3315 20.92 136 0.8068 0.7609
0.3229 22.0 143 0.8786 0.7826
0.3229 22.92 149 0.9030 0.7174
0.3065 24.0 156 0.8253 0.6522
0.2315 24.92 162 0.7398 0.8043
0.2315 26.0 169 0.7939 0.7609
0.222 26.92 175 0.6640 0.8478
0.1756 28.0 182 0.8510 0.7391
0.1756 28.92 188 0.9861 0.7174
0.1702 30.0 195 1.1060 0.7609
0.202 30.92 201 1.0929 0.7391
0.202 32.0 208 0.8670 0.7826
0.1665 32.92 214 0.8033 0.7609
0.1695 34.0 221 0.7235 0.7826
0.1695 34.92 227 0.8917 0.7609
0.1807 36.0 234 0.9215 0.7391
0.1289 36.92 240 0.8231 0.8043
0.1289 38.0 247 0.9256 0.7826
0.145 38.92 253 0.8866 0.7826
0.1422 40.0 260 0.8511 0.8261
0.1422 40.92 266 0.9956 0.7391
0.1313 42.0 273 1.3005 0.7391
0.1313 42.92 279 1.1532 0.6739
0.1128 44.0 286 1.0891 0.7391
0.1213 44.92 292 1.0765 0.7391
0.1213 46.0 299 0.9142 0.7391
0.1161 46.92 305 0.9100 0.7174
0.1123 48.0 312 0.8907 0.7826
0.1123 48.92 318 0.9462 0.7609
0.1107 50.0 325 0.8592 0.7391
0.0915 50.92 331 0.9894 0.7609
0.0915 52.0 338 1.1094 0.7609
0.0981 52.92 344 1.1956 0.7609
0.0762 54.0 351 1.0079 0.7826
0.0762 54.92 357 0.9899 0.7609
0.1083 56.0 364 0.9164 0.7826
0.1087 56.92 370 0.9263 0.7826
0.1087 58.0 377 0.9160 0.7391
0.0871 58.92 383 1.0179 0.7174
0.0852 60.0 390 0.9246 0.7391
0.0852 60.92 396 0.8929 0.8043
0.0613 62.0 403 0.9989 0.7174
0.0613 62.92 409 1.0367 0.7174
0.0899 64.0 416 1.1213 0.6957
0.0669 64.92 422 1.0093 0.7609
0.0669 66.0 429 1.0129 0.7391
0.0791 66.92 435 0.9979 0.7174
0.0848 68.0 442 1.0137 0.7391
0.0848 68.92 448 1.0761 0.6957
0.0799 70.0 455 1.0152 0.6957
0.0727 70.92 461 1.1302 0.6957
0.0727 72.0 468 1.0468 0.7174
0.0763 72.92 474 1.0759 0.6739
0.06 74.0 481 1.0803 0.7174
0.06 74.92 487 1.0484 0.6957
0.0746 76.0 494 0.9999 0.7174
0.0687 76.92 500 0.9937 0.7174
0.0687 78.0 507 1.1189 0.6957
0.0761 78.92 513 1.1013 0.6957
0.0729 80.0 520 1.0294 0.6957
0.0729 80.92 526 1.0860 0.7174
0.0472 82.0 533 1.0327 0.7174
0.0472 82.92 539 1.0225 0.7174
0.0519 84.0 546 1.1345 0.6957
0.0688 84.92 552 1.0923 0.6957
0.0688 86.0 559 1.0876 0.7174
0.0462 86.92 565 1.0740 0.6957
0.0457 88.0 572 1.1074 0.6957
0.0457 88.92 578 1.0777 0.6957
0.0482 90.0 585 1.0495 0.7391
0.0464 90.92 591 1.0395 0.7174
0.0464 92.0 598 1.1446 0.7174
0.0578 92.31 600 1.0596 0.6957

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0