resnet-50-finetuned-drugsclass
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: 1.3435
- Accuracy: 0.4935
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: 20
- eval_batch_size: 20
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3882 | 0.99 | 17 | 1.3435 | 0.4935 |
| 1.3408 | 1.97 | 34 | 1.3189 | 0.4870 |
| 1.318 | 2.96 | 51 | 1.3059 | 0.4675 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3