metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: SCUTFVD-resnet50-fold01
results: []
SCUTFVD-resnet50-fold01
This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3516
- Accuracy: 1.0
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.3847 | 1.0 | 75 | 5.0682 | 0.1875 |
| 2.5630 | 2.0 | 150 | 4.0558 | 0.25 |
| 2.0217 | 3.0 | 225 | 4.9411 | 0.2188 |
| 1.7360 | 4.0 | 300 | 2.1920 | 0.8438 |
| 1.4617 | 5.0 | 375 | 2.9501 | 0.5 |
| 1.2141 | 6.0 | 450 | 2.4084 | 0.5625 |
| 0.9616 | 7.0 | 525 | 0.7715 | 1.0 |
| 0.8966 | 8.0 | 600 | 1.4465 | 1.0 |
| 0.7456 | 9.0 | 675 | 0.7191 | 1.0 |
| 0.7394 | 10.0 | 750 | 0.3516 | 1.0 |
Framework versions
- Transformers 5.1.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2