smids_10x_deit_tiny_sgd_001_fold3
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2982
- Accuracy: 0.895
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: 0.001
- 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 |
---|---|---|---|---|
0.5867 | 1.0 | 750 | 0.5827 | 0.7783 |
0.3913 | 2.0 | 1500 | 0.4291 | 0.83 |
0.3437 | 3.0 | 2250 | 0.3734 | 0.86 |
0.3224 | 4.0 | 3000 | 0.3340 | 0.8633 |
0.3802 | 5.0 | 3750 | 0.3192 | 0.875 |
0.3066 | 6.0 | 4500 | 0.3104 | 0.88 |
0.2589 | 7.0 | 5250 | 0.2967 | 0.8867 |
0.2794 | 8.0 | 6000 | 0.2987 | 0.8867 |
0.1833 | 9.0 | 6750 | 0.2867 | 0.8933 |
0.2023 | 10.0 | 7500 | 0.2817 | 0.9 |
0.2616 | 11.0 | 8250 | 0.2809 | 0.8883 |
0.2286 | 12.0 | 9000 | 0.2812 | 0.8983 |
0.191 | 13.0 | 9750 | 0.2821 | 0.895 |
0.2573 | 14.0 | 10500 | 0.2824 | 0.895 |
0.233 | 15.0 | 11250 | 0.2788 | 0.9033 |
0.227 | 16.0 | 12000 | 0.2755 | 0.9133 |
0.2065 | 17.0 | 12750 | 0.2819 | 0.8933 |
0.1957 | 18.0 | 13500 | 0.2734 | 0.9033 |
0.1915 | 19.0 | 14250 | 0.2738 | 0.9017 |
0.1774 | 20.0 | 15000 | 0.2840 | 0.8967 |
0.1639 | 21.0 | 15750 | 0.2800 | 0.9 |
0.18 | 22.0 | 16500 | 0.2722 | 0.9033 |
0.1754 | 23.0 | 17250 | 0.2797 | 0.8983 |
0.1721 | 24.0 | 18000 | 0.2818 | 0.8967 |
0.2322 | 25.0 | 18750 | 0.2867 | 0.8933 |
0.1833 | 26.0 | 19500 | 0.2854 | 0.8933 |
0.0838 | 27.0 | 20250 | 0.2833 | 0.9083 |
0.1291 | 28.0 | 21000 | 0.2872 | 0.8883 |
0.1475 | 29.0 | 21750 | 0.2853 | 0.8933 |
0.1339 | 30.0 | 22500 | 0.2879 | 0.8917 |
0.0869 | 31.0 | 23250 | 0.2884 | 0.895 |
0.1341 | 32.0 | 24000 | 0.2859 | 0.89 |
0.1322 | 33.0 | 24750 | 0.2895 | 0.8933 |
0.1482 | 34.0 | 25500 | 0.2910 | 0.8933 |
0.1123 | 35.0 | 26250 | 0.2921 | 0.8933 |
0.1145 | 36.0 | 27000 | 0.2928 | 0.8933 |
0.1372 | 37.0 | 27750 | 0.2965 | 0.8917 |
0.1907 | 38.0 | 28500 | 0.2941 | 0.8917 |
0.1101 | 39.0 | 29250 | 0.2932 | 0.89 |
0.1502 | 40.0 | 30000 | 0.2921 | 0.895 |
0.1006 | 41.0 | 30750 | 0.2941 | 0.8983 |
0.1237 | 42.0 | 31500 | 0.2961 | 0.8967 |
0.0943 | 43.0 | 32250 | 0.2963 | 0.895 |
0.1038 | 44.0 | 33000 | 0.2980 | 0.8983 |
0.1286 | 45.0 | 33750 | 0.2956 | 0.8917 |
0.0851 | 46.0 | 34500 | 0.2954 | 0.8917 |
0.1551 | 47.0 | 35250 | 0.2984 | 0.8917 |
0.0707 | 48.0 | 36000 | 0.2985 | 0.8967 |
0.143 | 49.0 | 36750 | 0.2982 | 0.8967 |
0.1125 | 50.0 | 37500 | 0.2982 | 0.895 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hkivancoral/smids_10x_deit_tiny_sgd_001_fold3
Base model
facebook/deit-tiny-patch16-224