convnextv2-tiny-1k-224-finetuned-beans
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9837
- Accuracy: 0.6381
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: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7177 | 1.0 | 269 | 0.6939 | 0.5224 |
| 0.6132 | 2.0 | 538 | 0.6692 | 0.6101 |
| 0.642 | 3.0 | 807 | 0.6729 | 0.5951 |
| 0.6431 | 4.0 | 1076 | 0.6700 | 0.5690 |
| 0.5081 | 5.0 | 1345 | 0.7537 | 0.6213 |
| 0.4114 | 6.0 | 1614 | 0.9249 | 0.6175 |
| 0.3991 | 7.0 | 1883 | 0.9837 | 0.6381 |
| 0.2194 | 8.0 | 2152 | 1.4350 | 0.5802 |
| 0.0834 | 9.0 | 2421 | 1.3808 | 0.6138 |
| 0.15 | 10.0 | 2690 | 1.3277 | 0.6306 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0