Edit model card

convnext-tiny-224_flyswot

This model was trained from scratch on the image_folder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5319
  • F1: 0.9756

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 666
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss F1
No log 1.0 52 0.5478 0.9720
No log 2.0 104 0.5432 0.9709
No log 3.0 156 0.5437 0.9731
No log 4.0 208 0.5433 0.9712
No log 5.0 260 0.5373 0.9745
No log 6.0 312 0.5371 0.9756
No log 7.0 364 0.5381 0.9737
No log 8.0 416 0.5376 0.9744
No log 9.0 468 0.5431 0.9694
0.4761 10.0 520 0.5468 0.9725
0.4761 11.0 572 0.5404 0.9755
0.4761 12.0 624 0.5481 0.9669
0.4761 13.0 676 0.5432 0.9687
0.4761 14.0 728 0.5409 0.9731
0.4761 15.0 780 0.5403 0.9737
0.4761 16.0 832 0.5393 0.9737
0.4761 17.0 884 0.5412 0.9719
0.4761 18.0 936 0.5433 0.9674
0.4761 19.0 988 0.5367 0.9755
0.4705 20.0 1040 0.5389 0.9737
0.4705 21.0 1092 0.5396 0.9737
0.4705 22.0 1144 0.5514 0.9683
0.4705 23.0 1196 0.5550 0.9617
0.4705 24.0 1248 0.5428 0.9719
0.4705 25.0 1300 0.5371 0.9719
0.4705 26.0 1352 0.5455 0.9719
0.4705 27.0 1404 0.5409 0.9680
0.4705 28.0 1456 0.5345 0.9756
0.4696 29.0 1508 0.5381 0.9756
0.4696 30.0 1560 0.5387 0.9705
0.4696 31.0 1612 0.5540 0.9605
0.4696 32.0 1664 0.5467 0.9706
0.4696 33.0 1716 0.5322 0.9756
0.4696 34.0 1768 0.5325 0.9756
0.4696 35.0 1820 0.5305 0.9737
0.4696 36.0 1872 0.5305 0.9769
0.4696 37.0 1924 0.5345 0.9756
0.4696 38.0 1976 0.5315 0.9737
0.4699 39.0 2028 0.5333 0.9756
0.4699 40.0 2080 0.5316 0.9756
0.4699 41.0 2132 0.5284 0.9756
0.4699 42.0 2184 0.5325 0.9756
0.4699 43.0 2236 0.5321 0.9756
0.4699 44.0 2288 0.5322 0.9756
0.4699 45.0 2340 0.5323 0.9756
0.4699 46.0 2392 0.5318 0.9756
0.4699 47.0 2444 0.5329 0.9756
0.4699 48.0 2496 0.5317 0.9756
0.4701 49.0 2548 0.5317 0.9756
0.4701 50.0 2600 0.5319 0.9756

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.0.0
  • Tokenizers 0.11.6
Downloads last month
993
Hosted inference API
Drag image file here or click to browse from your device
This model can be loaded on the Inference API on-demand.

Space using flyswot/convnext-tiny-224_flyswot

Evaluation results