smids_5x_deit_base_adamax_00001_fold5
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6879
- Accuracy: 0.9
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2538 | 1.0 | 375 | 0.3339 | 0.8467 |
| 0.1892 | 2.0 | 750 | 0.2698 | 0.8917 |
| 0.1183 | 3.0 | 1125 | 0.2626 | 0.9 |
| 0.1141 | 4.0 | 1500 | 0.2917 | 0.8883 |
| 0.071 | 5.0 | 1875 | 0.3136 | 0.9 |
| 0.0217 | 6.0 | 2250 | 0.3618 | 0.8933 |
| 0.0346 | 7.0 | 2625 | 0.4213 | 0.89 |
| 0.0047 | 8.0 | 3000 | 0.4689 | 0.8983 |
| 0.022 | 9.0 | 3375 | 0.5039 | 0.8983 |
| 0.0024 | 10.0 | 3750 | 0.5358 | 0.8917 |
| 0.0059 | 11.0 | 4125 | 0.5640 | 0.895 |
| 0.0001 | 12.0 | 4500 | 0.5647 | 0.8967 |
| 0.0001 | 13.0 | 4875 | 0.6088 | 0.895 |
| 0.0002 | 14.0 | 5250 | 0.5907 | 0.9017 |
| 0.0001 | 15.0 | 5625 | 0.6332 | 0.8967 |
| 0.0001 | 16.0 | 6000 | 0.6424 | 0.8833 |
| 0.0001 | 17.0 | 6375 | 0.6207 | 0.8983 |
| 0.0068 | 18.0 | 6750 | 0.6552 | 0.895 |
| 0.0 | 19.0 | 7125 | 0.6642 | 0.9017 |
| 0.0 | 20.0 | 7500 | 0.6453 | 0.8883 |
| 0.0001 | 21.0 | 7875 | 0.6986 | 0.895 |
| 0.0265 | 22.0 | 8250 | 0.7065 | 0.8883 |
| 0.0 | 23.0 | 8625 | 0.6670 | 0.8967 |
| 0.0 | 24.0 | 9000 | 0.6793 | 0.8967 |
| 0.0 | 25.0 | 9375 | 0.6516 | 0.9017 |
| 0.0 | 26.0 | 9750 | 0.6626 | 0.89 |
| 0.0 | 27.0 | 10125 | 0.6877 | 0.895 |
| 0.0 | 28.0 | 10500 | 0.6598 | 0.8967 |
| 0.0 | 29.0 | 10875 | 0.6682 | 0.8933 |
| 0.0145 | 30.0 | 11250 | 0.6761 | 0.8983 |
| 0.0 | 31.0 | 11625 | 0.6763 | 0.8983 |
| 0.0 | 32.0 | 12000 | 0.6749 | 0.8967 |
| 0.0 | 33.0 | 12375 | 0.6798 | 0.8983 |
| 0.0 | 34.0 | 12750 | 0.6830 | 0.8967 |
| 0.0 | 35.0 | 13125 | 0.6787 | 0.9 |
| 0.0 | 36.0 | 13500 | 0.6883 | 0.895 |
| 0.0 | 37.0 | 13875 | 0.6805 | 0.8983 |
| 0.003 | 38.0 | 14250 | 0.6825 | 0.895 |
| 0.0 | 39.0 | 14625 | 0.6851 | 0.8967 |
| 0.0 | 40.0 | 15000 | 0.6877 | 0.8983 |
| 0.0 | 41.0 | 15375 | 0.6804 | 0.8983 |
| 0.0 | 42.0 | 15750 | 0.6888 | 0.8983 |
| 0.0 | 43.0 | 16125 | 0.6877 | 0.8983 |
| 0.0 | 44.0 | 16500 | 0.6899 | 0.8983 |
| 0.0 | 45.0 | 16875 | 0.6911 | 0.8967 |
| 0.0 | 46.0 | 17250 | 0.6870 | 0.8983 |
| 0.0023 | 47.0 | 17625 | 0.6868 | 0.8983 |
| 0.0 | 48.0 | 18000 | 0.6892 | 0.9 |
| 0.0 | 49.0 | 18375 | 0.6892 | 0.9 |
| 0.0021 | 50.0 | 18750 | 0.6879 | 0.9 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2