metadata
library_name: transformers
license: apache-2.0
base_model: timm/resnet18.a1_in1k
tags:
- image-classification
- vision
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-beans
results: []
vit-base-beans
This model is a fine-tuned version of timm/resnet18.a1_in1k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.8550
- Accuracy: 0.7895
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15.0
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 1.0881 | 1.0 | 130 | 0.4135 | 1.0902 |
| 1.0716 | 2.0 | 260 | 0.5038 | 1.0685 |
| 1.061 | 3.0 | 390 | 0.6241 | 1.0459 |
| 1.0514 | 4.0 | 520 | 0.6015 | 1.0407 |
| 1.05 | 5.0 | 650 | 0.6767 | 1.0332 |
| 1.0357 | 6.0 | 780 | 1.0109 | 0.6541 |
| 1.0012 | 7.0 | 910 | 0.9815 | 0.7368 |
| 0.9932 | 8.0 | 1040 | 0.9550 | 0.7669 |
| 0.9748 | 9.0 | 1170 | 0.9409 | 0.7669 |
| 0.9113 | 10.0 | 1300 | 0.9149 | 0.7820 |
| 0.9255 | 11.0 | 1430 | 0.8906 | 0.7895 |
| 0.8877 | 12.0 | 1560 | 0.8749 | 0.7895 |
| 0.9032 | 13.0 | 1690 | 0.8699 | 0.7970 |
| 0.9001 | 14.0 | 1820 | 0.8674 | 0.7820 |
| 0.8842 | 15.0 | 1950 | 0.8550 | 0.7895 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu118
- Datasets 2.21.0
- Tokenizers 0.20.0