resnet-50-finetuned-ecg-classification-resnet
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: 0.3376
- Accuracy: 0.8716
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: 0.0005
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4623 | 1.0 | 23 | 0.4650 | 0.8257 |
0.4092 | 2.0 | 46 | 0.5639 | 0.8104 |
0.43 | 3.0 | 69 | 0.3935 | 0.8532 |
0.3558 | 4.0 | 92 | 0.4122 | 0.8349 |
0.331 | 5.0 | 115 | 0.3424 | 0.8716 |
0.324 | 6.0 | 138 | 0.3776 | 0.8716 |
0.2941 | 7.0 | 161 | 0.3448 | 0.8685 |
0.2961 | 8.0 | 184 | 0.3259 | 0.8777 |
0.326 | 9.0 | 207 | 0.3225 | 0.8838 |
0.3131 | 10.0 | 230 | 0.3376 | 0.8716 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 18