img_class_beans
This model is a fine-tuned version of juniorjukeko/img_class_beans on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.1220
- Accuracy: 0.9730
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: 16
- eval_batch_size: 16
- seed: 143
- 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 |
---|---|---|---|---|
0.1122 | 0.98 | 12 | 0.1660 | 0.9575 |
0.1356 | 1.96 | 24 | 0.1977 | 0.9421 |
0.0889 | 2.94 | 36 | 0.1504 | 0.9421 |
0.0793 | 4.0 | 49 | 0.1477 | 0.9575 |
0.0578 | 4.98 | 61 | 0.1320 | 0.9653 |
0.0514 | 5.96 | 73 | 0.1163 | 0.9730 |
0.0592 | 6.94 | 85 | 0.1363 | 0.9653 |
0.0532 | 8.0 | 98 | 0.1837 | 0.9382 |
0.0555 | 8.98 | 110 | 0.1400 | 0.9614 |
0.0723 | 9.8 | 120 | 0.1220 | 0.9730 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.