<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
large-algae-vit-rgb
This model is a fine-tuned version of samitizerxu/large-algae-vit-rgb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1659
- Accuracy: 0.5798
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2115 | 1.0 | 120 | 0.9078 | 0.6315 |
| 1.1249 | 2.0 | 240 | 0.9217 | 0.6320 |
| 1.1385 | 3.0 | 360 | 0.9518 | 0.6180 |
| 1.1347 | 4.0 | 480 | 1.0201 | 0.6068 |
| 1.1358 | 5.0 | 600 | 1.0801 | 0.5892 |
| 1.098 | 6.0 | 720 | 1.0932 | 0.5851 |
| 1.0882 | 7.0 | 840 | 1.0347 | 0.6033 |
| 1.0688 | 8.0 | 960 | 1.0403 | 0.6056 |
| 1.0863 | 9.0 | 1080 | 1.0466 | 0.6009 |
| 1.1253 | 10.0 | 1200 | 1.2308 | 0.5511 |
| 1.0393 | 11.0 | 1320 | 1.1434 | 0.5869 |
| 1.0749 | 12.0 | 1440 | 1.2155 | 0.5622 |
| 1.0433 | 13.0 | 1560 | 1.2466 | 0.5522 |
| 1.0141 | 14.0 | 1680 | 1.1880 | 0.5563 |
| 1.0516 | 15.0 | 1800 | 1.1006 | 0.5992 |
| 1.0696 | 16.0 | 1920 | 1.0971 | 0.5751 |
| 0.9867 | 17.0 | 2040 | 1.1689 | 0.5827 |
| 1.0234 | 18.0 | 2160 | 1.1846 | 0.5751 |
| 1.0364 | 19.0 | 2280 | 1.1480 | 0.5739 |
| 1.0314 | 20.0 | 2400 | 1.0977 | 0.5880 |
| 1.0179 | 21.0 | 2520 | 1.1258 | 0.5851 |
| 1.0584 | 22.0 | 2640 | 1.1569 | 0.5822 |
| 1.0222 | 23.0 | 2760 | 1.1672 | 0.5839 |
| 0.996 | 24.0 | 2880 | 1.1737 | 0.5798 |
| 1.0343 | 25.0 | 3000 | 1.1588 | 0.5792 |
| 0.9854 | 26.0 | 3120 | 1.1758 | 0.5763 |
| 0.9753 | 27.0 | 3240 | 1.1715 | 0.5763 |
| 0.9881 | 28.0 | 3360 | 1.1403 | 0.5839 |
| 1.0057 | 29.0 | 3480 | 1.1765 | 0.5781 |
| 0.9824 | 30.0 | 3600 | 1.1659 | 0.5798 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
