resnet-50-finetuned-plantdie
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: 1.4394
- Accuracy: 0.4957
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7322 | 1.0 | 17 | 1.6975 | 0.3846 |
| 1.6739 | 2.0 | 34 | 1.6243 | 0.4444 |
| 1.5932 | 3.0 | 51 | 1.5576 | 0.4615 |
| 1.5707 | 4.0 | 68 | 1.5096 | 0.4530 |
| 1.5099 | 5.0 | 85 | 1.4788 | 0.4744 |
| 1.4802 | 6.0 | 102 | 1.4541 | 0.4744 |
| 1.4641 | 7.0 | 119 | 1.4394 | 0.4957 |
| 1.4636 | 8.0 | 136 | 1.4261 | 0.4957 |
| 1.4265 | 9.0 | 153 | 1.4176 | 0.4957 |
| 1.4383 | 10.0 | 170 | 1.4118 | 0.4957 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1