resnet-101-finetuned_resnet101-sgd-optimizer-autotags
This model is a fine-tuned version of microsoft/resnet-101 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0245
- Accuracy: 0.6781
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 2.7106 | 0.99 | 65 | 2.7615 | 0.1371 |
| 2.5331 | 1.99 | 130 | 2.6702 | 0.1495 |
| 2.2557 | 2.99 | 195 | 2.2049 | 0.2924 |
| 2.0473 | 3.99 | 260 | 2.0434 | 0.3619 |
| 1.6644 | 4.99 | 325 | 1.6585 | 0.4438 |
| 1.5685 | 5.99 | 390 | 1.4183 | 0.5419 |
| 1.377 | 6.99 | 455 | 1.2873 | 0.5981 |
| 1.2441 | 7.99 | 520 | 1.1502 | 0.6362 |
| 1.1983 | 8.99 | 585 | 1.0553 | 0.6657 |
| 1.0988 | 9.99 | 650 | 1.0245 | 0.6781 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2