resnet-50-pac_aug
This model is a fine-tuned version of kiranshivaraju/resnet-50-pac_aug on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6055
- Recall: 0.0
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 | Recall |
|---|---|---|---|---|
| 0.6335 | 1.0 | 15 | 0.6352 | 0.0 |
| 0.643 | 2.0 | 30 | 0.6276 | 0.0 |
| 0.6434 | 3.0 | 45 | 0.6228 | 0.0 |
| 0.6305 | 4.0 | 60 | 0.6156 | 0.0 |
| 0.6339 | 5.0 | 75 | 0.6167 | 0.0 |
| 0.6346 | 6.0 | 90 | 0.6112 | 0.0 |
| 0.6235 | 7.0 | 105 | 0.6095 | 0.0 |
| 0.6279 | 8.0 | 120 | 0.6082 | 0.0 |
| 0.6241 | 9.0 | 135 | 0.6073 | 0.0 |
| 0.6233 | 10.0 | 150 | 0.6055 | 0.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1