--- library_name: transformers tags: - generated_from_trainer model-index: - name: unet-resnet18-malaria-trophozoites-wbc results: [] --- # unet-resnet18-malaria-trophozoites-wbc This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0317 ## 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: 30 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 211 | 0.1469 | | No log | 2.0 | 422 | 0.0453 | | 0.1321 | 3.0 | 633 | 0.0406 | | 0.1321 | 4.0 | 844 | 0.0401 | | 0.0395 | 5.0 | 1055 | 0.0415 | | 0.0395 | 6.0 | 1266 | 0.0386 | | 0.0395 | 7.0 | 1477 | 0.0389 | | 0.0367 | 8.0 | 1688 | 0.0367 | | 0.0367 | 9.0 | 1899 | 0.0359 | | 0.0356 | 10.0 | 2110 | 0.0383 | | 0.0356 | 11.0 | 2321 | 0.0379 | | 0.0342 | 12.0 | 2532 | 0.0383 | | 0.0342 | 13.0 | 2743 | 0.0360 | | 0.0342 | 14.0 | 2954 | 0.0355 | | 0.0339 | 15.0 | 3165 | 0.0340 | | 0.0339 | 16.0 | 3376 | 0.0346 | | 0.0328 | 17.0 | 3587 | 0.0343 | | 0.0328 | 18.0 | 3798 | 0.0346 | | 0.0319 | 19.0 | 4009 | 0.0338 | | 0.0319 | 20.0 | 4220 | 0.0348 | | 0.0319 | 21.0 | 4431 | 0.0333 | | 0.0313 | 22.0 | 4642 | 0.0342 | | 0.0313 | 23.0 | 4853 | 0.0334 | | 0.0314 | 24.0 | 5064 | 0.0327 | | 0.0314 | 25.0 | 5275 | 0.0328 | | 0.0314 | 26.0 | 5486 | 0.0327 | | 0.0304 | 27.0 | 5697 | 0.0324 | | 0.0304 | 28.0 | 5908 | 0.0321 | | 0.0303 | 29.0 | 6119 | 0.0320 | | 0.0303 | 30.0 | 6330 | 0.0317 | ### Framework versions - Transformers 4.48.3 - Pytorch 2.5.1+cu124 - Datasets 3.3.0 - Tokenizers 0.21.0