unet-resnet34-malaria-trophozoites-wbc

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1531

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: 0.003
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 242 0.2605
No log 2.0 484 0.2295
0.6582 3.0 726 0.1956
0.6582 4.0 968 0.2041
0.1668 5.0 1210 0.1908
0.1668 6.0 1452 0.1820
0.1603 7.0 1694 0.1835
0.1603 8.0 1936 0.1800
0.1545 9.0 2178 0.1878
0.1545 10.0 2420 0.1753
0.151 11.0 2662 0.1952
0.151 12.0 2904 0.1860
0.1454 13.0 3146 0.1827
0.1454 14.0 3388 0.1729
0.1441 15.0 3630 0.1673
0.1441 16.0 3872 0.1707
0.1425 17.0 4114 0.1654
0.1425 18.0 4356 0.1667
0.1405 19.0 4598 0.1673
0.1405 20.0 4840 0.1699
0.1381 21.0 5082 0.1641
0.1381 22.0 5324 0.1654
0.141 23.0 5566 0.1670
0.141 24.0 5808 0.1658
0.136 25.0 6050 0.1678
0.136 26.0 6292 0.1623
0.136 27.0 6534 0.1640
0.136 28.0 6776 0.1618
0.1326 29.0 7018 0.1594
0.1326 30.0 7260 0.1611
0.1337 31.0 7502 0.1623
0.1337 32.0 7744 0.1599
0.1337 33.0 7986 0.1588
0.1301 34.0 8228 0.1583
0.1301 35.0 8470 0.1585
0.1301 36.0 8712 0.1569
0.1301 37.0 8954 0.1573
0.1298 38.0 9196 0.1562
0.1298 39.0 9438 0.1581
0.1309 40.0 9680 0.1568
0.1309 41.0 9922 0.1558
0.1274 42.0 10164 0.1552
0.1274 43.0 10406 0.1553
0.127 44.0 10648 0.1567
0.127 45.0 10890 0.1542
0.1278 46.0 11132 0.1545
0.1278 47.0 11374 0.1549
0.1275 48.0 11616 0.1535
0.1275 49.0 11858 0.1541
0.126 50.0 12100 0.1531

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.1+cu124
  • Datasets 3.3.0
  • Tokenizers 0.21.0
Downloads last month
11
Safetensors
Model size
24.5M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support