smids_5x_beit_base_adamax_0001_fold4
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5977
- Accuracy: 0.8717
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: 0.0001
- 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 |
|---|---|---|---|---|
| 0.3006 | 1.0 | 375 | 0.3431 | 0.865 |
| 0.2258 | 2.0 | 750 | 0.3974 | 0.8433 |
| 0.1308 | 3.0 | 1125 | 0.4504 | 0.8633 |
| 0.1539 | 4.0 | 1500 | 0.4844 | 0.865 |
| 0.0793 | 5.0 | 1875 | 0.5671 | 0.8683 |
| 0.0565 | 6.0 | 2250 | 0.6745 | 0.865 |
| 0.0735 | 7.0 | 2625 | 0.5104 | 0.8983 |
| 0.0686 | 8.0 | 3000 | 0.7410 | 0.8767 |
| 0.0395 | 9.0 | 3375 | 0.6717 | 0.88 |
| 0.057 | 10.0 | 3750 | 0.5892 | 0.885 |
| 0.0561 | 11.0 | 4125 | 0.7571 | 0.8733 |
| 0.0534 | 12.0 | 4500 | 0.9537 | 0.8583 |
| 0.0346 | 13.0 | 4875 | 0.8297 | 0.85 |
| 0.0136 | 14.0 | 5250 | 0.9195 | 0.8667 |
| 0.0218 | 15.0 | 5625 | 0.9025 | 0.87 |
| 0.0052 | 16.0 | 6000 | 1.0564 | 0.865 |
| 0.0551 | 17.0 | 6375 | 0.9490 | 0.8633 |
| 0.0659 | 18.0 | 6750 | 0.9404 | 0.8717 |
| 0.0263 | 19.0 | 7125 | 0.9533 | 0.875 |
| 0.0009 | 20.0 | 7500 | 0.9914 | 0.87 |
| 0.0008 | 21.0 | 7875 | 1.1404 | 0.855 |
| 0.0028 | 22.0 | 8250 | 1.0363 | 0.8733 |
| 0.0035 | 23.0 | 8625 | 1.0823 | 0.865 |
| 0.0007 | 24.0 | 9000 | 1.0248 | 0.8733 |
| 0.0408 | 25.0 | 9375 | 0.9782 | 0.8683 |
| 0.0262 | 26.0 | 9750 | 1.0392 | 0.8683 |
| 0.0167 | 27.0 | 10125 | 1.0282 | 0.8717 |
| 0.0115 | 28.0 | 10500 | 0.9251 | 0.885 |
| 0.0242 | 29.0 | 10875 | 1.0471 | 0.8767 |
| 0.0002 | 30.0 | 11250 | 1.0729 | 0.8817 |
| 0.0011 | 31.0 | 11625 | 1.1808 | 0.87 |
| 0.0 | 32.0 | 12000 | 1.2243 | 0.8617 |
| 0.0 | 33.0 | 12375 | 1.2017 | 0.8733 |
| 0.0002 | 34.0 | 12750 | 1.2888 | 0.865 |
| 0.0 | 35.0 | 13125 | 1.1910 | 0.8717 |
| 0.0002 | 36.0 | 13500 | 1.3235 | 0.8683 |
| 0.0 | 37.0 | 13875 | 1.2685 | 0.8617 |
| 0.0109 | 38.0 | 14250 | 1.3836 | 0.865 |
| 0.0001 | 39.0 | 14625 | 1.3162 | 0.8733 |
| 0.0002 | 40.0 | 15000 | 1.3327 | 0.86 |
| 0.0 | 41.0 | 15375 | 1.4460 | 0.8567 |
| 0.0 | 42.0 | 15750 | 1.5521 | 0.8583 |
| 0.0 | 43.0 | 16125 | 1.6052 | 0.86 |
| 0.0 | 44.0 | 16500 | 1.5790 | 0.865 |
| 0.0 | 45.0 | 16875 | 1.5481 | 0.8667 |
| 0.0 | 46.0 | 17250 | 1.5829 | 0.8667 |
| 0.0 | 47.0 | 17625 | 1.6010 | 0.8717 |
| 0.0008 | 48.0 | 18000 | 1.5864 | 0.87 |
| 0.0 | 49.0 | 18375 | 1.5922 | 0.8683 |
| 0.0001 | 50.0 | 18750 | 1.5977 | 0.8717 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2