|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
model-index: |
|
- name: ryan03282024 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ryan03282024 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the properties dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2238 |
|
- Ordinal Mae: 0.4441 |
|
- Ordinal Accuracy: 0.6446 |
|
- Na Accuracy: 0.7992 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Ordinal Mae | Ordinal Accuracy | Na Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:----------------:|:-----------:| |
|
| 0.3421 | 0.04 | 100 | 0.3331 | 0.8749 | 0.3817 | 0.6911 | |
|
| 0.2813 | 0.09 | 200 | 0.3000 | 0.7492 | 0.5117 | 0.7954 | |
|
| 0.2619 | 0.13 | 300 | 0.3019 | 0.6841 | 0.5273 | 0.7046 | |
|
| 0.2863 | 0.17 | 400 | 0.2960 | 0.6538 | 0.5097 | 0.7336 | |
|
| 0.2159 | 0.22 | 500 | 0.2602 | 0.5404 | 0.5660 | 0.8243 | |
|
| 0.2235 | 0.26 | 600 | 0.2557 | 0.5015 | 0.5874 | 0.7780 | |
|
| 0.285 | 0.31 | 700 | 0.2564 | 0.5000 | 0.6180 | 0.6853 | |
|
| 0.2028 | 0.35 | 800 | 0.2862 | 0.6338 | 0.5068 | 0.7220 | |
|
| 0.2006 | 0.39 | 900 | 0.2495 | 0.4830 | 0.6299 | 0.7587 | |
|
| 0.2663 | 0.44 | 1000 | 0.2660 | 0.4893 | 0.6021 | 0.8610 | |
|
| 0.2062 | 0.48 | 1100 | 0.2481 | 0.4713 | 0.6267 | 0.8436 | |
|
| 0.1749 | 0.52 | 1200 | 0.2586 | 0.4959 | 0.6423 | 0.6737 | |
|
| 0.2197 | 0.57 | 1300 | 0.2349 | 0.4841 | 0.5981 | 0.8031 | |
|
| 0.2073 | 0.61 | 1400 | 0.2587 | 0.4878 | 0.6013 | 0.6950 | |
|
| 0.1915 | 0.66 | 1500 | 0.2393 | 0.4771 | 0.6322 | 0.7683 | |
|
| 0.2374 | 0.7 | 1600 | 0.2238 | 0.4441 | 0.6446 | 0.7992 | |
|
| 0.2278 | 0.74 | 1700 | 0.2453 | 0.4410 | 0.6539 | 0.7278 | |
|
| 0.2033 | 0.79 | 1800 | 0.2251 | 0.4584 | 0.6299 | 0.8185 | |
|
| 0.1843 | 0.83 | 1900 | 0.2280 | 0.4446 | 0.6513 | 0.8127 | |
|
| 0.1878 | 0.87 | 2000 | 0.2277 | 0.4454 | 0.6492 | 0.8127 | |
|
| 0.2608 | 0.92 | 2100 | 0.2309 | 0.4517 | 0.6192 | 0.8494 | |
|
| 0.201 | 0.96 | 2200 | 0.2459 | 0.4654 | 0.6406 | 0.7278 | |
|
| 0.1736 | 1.0 | 2300 | 0.2438 | 0.4474 | 0.6475 | 0.7201 | |
|
| 0.1374 | 1.05 | 2400 | 0.2368 | 0.4145 | 0.6622 | 0.7799 | |
|
| 0.1334 | 1.09 | 2500 | 0.2424 | 0.4105 | 0.6732 | 0.7510 | |
|
| 0.1319 | 1.14 | 2600 | 0.2336 | 0.4155 | 0.6712 | 0.7741 | |
|
| 0.1549 | 1.18 | 2700 | 0.2525 | 0.4040 | 0.6625 | 0.7587 | |
|
| 0.116 | 1.22 | 2800 | 0.2501 | 0.4425 | 0.6371 | 0.7664 | |
|
| 0.1358 | 1.27 | 2900 | 0.2324 | 0.4136 | 0.6498 | 0.8185 | |
|
| 0.1614 | 1.31 | 3000 | 0.2637 | 0.4353 | 0.6316 | 0.7915 | |
|
| 0.1395 | 1.35 | 3100 | 0.2446 | 0.4020 | 0.6726 | 0.8012 | |
|
| 0.1208 | 1.4 | 3200 | 0.2465 | 0.3946 | 0.6764 | 0.8243 | |
|
| 0.1432 | 1.44 | 3300 | 0.2552 | 0.3919 | 0.6576 | 0.8900 | |
|
| 0.1358 | 1.48 | 3400 | 0.2561 | 0.3984 | 0.6796 | 0.7896 | |
|
| 0.0877 | 1.53 | 3500 | 0.2381 | 0.3901 | 0.6822 | 0.7876 | |
|
| 0.1212 | 1.57 | 3600 | 0.2600 | 0.4001 | 0.6949 | 0.7259 | |
|
| 0.1917 | 1.62 | 3700 | 0.2459 | 0.3889 | 0.6894 | 0.7819 | |
|
| 0.1175 | 1.66 | 3800 | 0.2444 | 0.3937 | 0.6819 | 0.7741 | |
|
| 0.1522 | 1.7 | 3900 | 0.2473 | 0.4010 | 0.6608 | 0.8050 | |
|
| 0.1027 | 1.75 | 4000 | 0.2354 | 0.4208 | 0.6478 | 0.7838 | |
|
| 0.1343 | 1.79 | 4100 | 0.2284 | 0.3977 | 0.6744 | 0.7992 | |
|
| 0.1552 | 1.83 | 4200 | 0.2607 | 0.4045 | 0.6715 | 0.7780 | |
|
| 0.1172 | 1.88 | 4300 | 0.2421 | 0.3971 | 0.6666 | 0.8282 | |
|
| 0.1381 | 1.92 | 4400 | 0.2253 | 0.3813 | 0.6793 | 0.7857 | |
|
| 0.1282 | 1.97 | 4500 | 0.2335 | 0.4146 | 0.6510 | 0.8436 | |
|
| 0.0734 | 2.01 | 4600 | 0.2382 | 0.3802 | 0.6897 | 0.7896 | |
|
| 0.1046 | 2.05 | 4700 | 0.2358 | 0.3695 | 0.6874 | 0.8012 | |
|
| 0.0529 | 2.1 | 4800 | 0.2463 | 0.3596 | 0.7096 | 0.7934 | |
|
| 0.0687 | 2.14 | 4900 | 0.2615 | 0.3921 | 0.6738 | 0.7857 | |
|
| 0.0613 | 2.18 | 5000 | 0.2543 | 0.3651 | 0.6877 | 0.8108 | |
|
| 0.0591 | 2.23 | 5100 | 0.2539 | 0.3693 | 0.6885 | 0.7915 | |
|
| 0.0474 | 2.27 | 5200 | 0.2650 | 0.3722 | 0.6836 | 0.7992 | |
|
| 0.0511 | 2.31 | 5300 | 0.2631 | 0.3681 | 0.6868 | 0.8127 | |
|
| 0.0683 | 2.36 | 5400 | 0.2714 | 0.3630 | 0.6955 | 0.7838 | |
|
| 0.0654 | 2.4 | 5500 | 0.2769 | 0.3673 | 0.6787 | 0.7992 | |
|
| 0.0581 | 2.45 | 5600 | 0.2777 | 0.3628 | 0.6952 | 0.7992 | |
|
| 0.072 | 2.49 | 5700 | 0.2919 | 0.3610 | 0.6888 | 0.7683 | |
|
| 0.0737 | 2.53 | 5800 | 0.2807 | 0.3612 | 0.6984 | 0.7838 | |
|
| 0.0667 | 2.58 | 5900 | 0.2926 | 0.3607 | 0.7001 | 0.7510 | |
|
| 0.0669 | 2.62 | 6000 | 0.2875 | 0.3616 | 0.6891 | 0.7992 | |
|
| 0.0535 | 2.66 | 6100 | 0.2854 | 0.3565 | 0.6960 | 0.7683 | |
|
| 0.06 | 2.71 | 6200 | 0.2847 | 0.3501 | 0.7015 | 0.7741 | |
|
| 0.0534 | 2.75 | 6300 | 0.2821 | 0.3495 | 0.7007 | 0.7625 | |
|
| 0.0526 | 2.79 | 6400 | 0.2834 | 0.3853 | 0.6700 | 0.7625 | |
|
| 0.0841 | 2.84 | 6500 | 0.2839 | 0.3504 | 0.7044 | 0.7490 | |
|
| 0.0529 | 2.88 | 6600 | 0.2858 | 0.3595 | 0.6897 | 0.7819 | |
|
| 0.0811 | 2.93 | 6700 | 0.2843 | 0.3480 | 0.7047 | 0.7799 | |
|
| 0.0502 | 2.97 | 6800 | 0.2892 | 0.3483 | 0.7010 | 0.7819 | |
|
| 0.0273 | 3.01 | 6900 | 0.2801 | 0.3454 | 0.6958 | 0.8108 | |
|
| 0.0306 | 3.06 | 7000 | 0.2782 | 0.3444 | 0.7024 | 0.8031 | |
|
| 0.0257 | 3.1 | 7100 | 0.2797 | 0.3352 | 0.7085 | 0.7934 | |
|
| 0.0241 | 3.14 | 7200 | 0.2828 | 0.3343 | 0.7059 | 0.7954 | |
|
| 0.0255 | 3.19 | 7300 | 0.2890 | 0.3364 | 0.6981 | 0.8050 | |
|
| 0.0245 | 3.23 | 7400 | 0.2906 | 0.3392 | 0.7044 | 0.7992 | |
|
| 0.0232 | 3.28 | 7500 | 0.2891 | 0.3338 | 0.7036 | 0.7857 | |
|
| 0.0352 | 3.32 | 7600 | 0.2908 | 0.3443 | 0.6926 | 0.7896 | |
|
| 0.0376 | 3.36 | 7700 | 0.2877 | 0.3315 | 0.7050 | 0.7915 | |
|
| 0.025 | 3.41 | 7800 | 0.2889 | 0.3316 | 0.7076 | 0.7896 | |
|
| 0.0225 | 3.45 | 7900 | 0.2902 | 0.3286 | 0.7070 | 0.7819 | |
|
| 0.024 | 3.49 | 8000 | 0.2902 | 0.3270 | 0.7102 | 0.7954 | |
|
| 0.0404 | 3.54 | 8100 | 0.2950 | 0.3294 | 0.7053 | 0.7896 | |
|
| 0.0221 | 3.58 | 8200 | 0.2924 | 0.3271 | 0.7093 | 0.7934 | |
|
| 0.0182 | 3.62 | 8300 | 0.2921 | 0.3237 | 0.7105 | 0.7934 | |
|
| 0.0304 | 3.67 | 8400 | 0.2911 | 0.3231 | 0.7134 | 0.7857 | |
|
| 0.0193 | 3.71 | 8500 | 0.2915 | 0.3221 | 0.7166 | 0.7838 | |
|
| 0.0223 | 3.76 | 8600 | 0.2931 | 0.3235 | 0.7122 | 0.7896 | |
|
| 0.0254 | 3.8 | 8700 | 0.2947 | 0.3214 | 0.7174 | 0.7876 | |
|
| 0.0215 | 3.84 | 8800 | 0.2936 | 0.3202 | 0.7128 | 0.7857 | |
|
| 0.0312 | 3.89 | 8900 | 0.2956 | 0.3210 | 0.7134 | 0.7857 | |
|
| 0.0189 | 3.93 | 9000 | 0.2946 | 0.3210 | 0.7125 | 0.7876 | |
|
| 0.021 | 3.97 | 9100 | 0.2949 | 0.3194 | 0.7145 | 0.7876 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
