metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: resnet_aug
results: []
resnet_aug
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2587
- Accuracy: 0.4686
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 | Accuracy |
|---|---|---|---|---|
| 1.6578 | 1.0 | 240 | 1.6593 | 0.2533 |
| 1.5544 | 2.0 | 480 | 1.5545 | 0.2803 |
| 1.4653 | 3.0 | 720 | 1.4689 | 0.3404 |
| 1.3595 | 4.0 | 960 | 1.3931 | 0.3914 |
| 1.2991 | 5.0 | 1200 | 1.3410 | 0.4208 |
| 1.2512 | 6.0 | 1440 | 1.3049 | 0.4421 |
| 1.1948 | 7.0 | 1680 | 1.2843 | 0.4552 |
| 1.1679 | 8.0 | 1920 | 1.2667 | 0.4613 |
| 1.1842 | 9.0 | 2160 | 1.2635 | 0.4668 |
| 1.1268 | 10.0 | 2400 | 1.2587 | 0.4686 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1