resnet-50-finetuned-nct-crc-he-45k
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0704
- Accuracy: 0.9789
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: 5e-05
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6319 | 1.0 | 246 | 1.5910 | 0.8181 |
| 0.335 | 2.0 | 492 | 0.2492 | 0.9397 |
| 0.2563 | 3.0 | 738 | 0.1462 | 0.9613 |
| 0.2055 | 4.0 | 985 | 0.1201 | 0.9679 |
| 0.1713 | 5.0 | 1231 | 0.1003 | 0.9719 |
| 0.1575 | 6.0 | 1477 | 0.1020 | 0.9722 |
| 0.1293 | 7.0 | 1723 | 0.0817 | 0.9747 |
| 0.1104 | 8.0 | 1970 | 0.0798 | 0.9779 |
| 0.1552 | 9.0 | 2216 | 0.0851 | 0.9763 |
| 0.1267 | 9.99 | 2460 | 0.0704 | 0.9789 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.10.0
- Tokenizers 0.13.2