metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: invitrace-vit-food
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7150311057595826
invitrace-vit-food
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3123
- Accuracy: 0.7150
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
5.0709 | 0.0803 | 200 | 5.0587 | 0.0460 |
4.953 | 0.1605 | 400 | 4.9295 | 0.1174 |
4.8249 | 0.2408 | 600 | 4.7934 | 0.2099 |
4.6523 | 0.3210 | 800 | 4.6597 | 0.2266 |
4.5648 | 0.4013 | 1000 | 4.5348 | 0.2814 |
4.5212 | 0.4815 | 1200 | 4.4125 | 0.2882 |
4.2975 | 0.5618 | 1400 | 4.2945 | 0.3345 |
4.2548 | 0.6421 | 1600 | 4.1838 | 0.3761 |
4.0395 | 0.7223 | 1800 | 4.0774 | 0.3873 |
3.9615 | 0.8026 | 2000 | 3.9822 | 0.4080 |
3.9325 | 0.8828 | 2200 | 3.8886 | 0.4124 |
3.8862 | 0.9631 | 2400 | 3.7977 | 0.4479 |
3.3958 | 1.0433 | 2600 | 3.6938 | 0.4618 |
3.4241 | 1.1236 | 2800 | 3.6019 | 0.4722 |
3.3326 | 1.2039 | 3000 | 3.5157 | 0.4951 |
3.2437 | 1.2841 | 3200 | 3.4209 | 0.5139 |
3.2519 | 1.3644 | 3400 | 3.3291 | 0.5198 |
3.2528 | 1.4446 | 3600 | 3.2425 | 0.5308 |
3.117 | 1.5249 | 3800 | 3.1715 | 0.5505 |
3.014 | 1.6051 | 4000 | 3.0965 | 0.5408 |
2.8688 | 1.6854 | 4200 | 3.0171 | 0.5577 |
2.9096 | 1.7657 | 4400 | 2.9386 | 0.5748 |
2.8936 | 1.8459 | 4600 | 2.8630 | 0.5788 |
2.7947 | 1.9262 | 4800 | 2.7981 | 0.5842 |
2.7247 | 2.0064 | 5000 | 2.7218 | 0.5910 |
2.3716 | 2.0867 | 5200 | 2.6467 | 0.6091 |
2.3813 | 2.1669 | 5400 | 2.5855 | 0.6037 |
2.1125 | 2.2472 | 5600 | 2.5160 | 0.6091 |
2.0332 | 2.3274 | 5800 | 2.4506 | 0.6207 |
2.0413 | 2.4077 | 6000 | 2.3949 | 0.6263 |
2.3041 | 2.4880 | 6200 | 2.3396 | 0.6183 |
1.7894 | 2.5682 | 6400 | 2.2855 | 0.6372 |
1.9194 | 2.6485 | 6600 | 2.2341 | 0.6386 |
2.0286 | 2.7287 | 6800 | 2.1997 | 0.6392 |
1.7409 | 2.8090 | 7000 | 2.1385 | 0.6478 |
1.794 | 2.8892 | 7200 | 2.0876 | 0.6528 |
1.6189 | 2.9695 | 7400 | 2.0540 | 0.6570 |
1.5587 | 3.0498 | 7600 | 2.0068 | 0.6629 |
1.2941 | 3.1300 | 7800 | 1.9610 | 0.6701 |
1.3048 | 3.2103 | 8000 | 1.9325 | 0.6639 |
1.1526 | 3.2905 | 8200 | 1.8883 | 0.6699 |
1.2333 | 3.3708 | 8400 | 1.8505 | 0.6693 |
1.1094 | 3.4510 | 8600 | 1.8273 | 0.6703 |
1.4851 | 3.5313 | 8800 | 1.7896 | 0.6829 |
1.1991 | 3.6116 | 9000 | 1.7648 | 0.6829 |
1.1898 | 3.6918 | 9200 | 1.7250 | 0.6903 |
0.973 | 3.7721 | 9400 | 1.7261 | 0.6769 |
1.2646 | 3.8523 | 9600 | 1.6804 | 0.6920 |
1.0756 | 3.9326 | 9800 | 1.6639 | 0.6934 |
1.0885 | 4.0128 | 10000 | 1.6324 | 0.6924 |
0.8466 | 4.0931 | 10200 | 1.6131 | 0.6994 |
0.8781 | 4.1734 | 10400 | 1.5981 | 0.6942 |
0.8557 | 4.2536 | 10600 | 1.5804 | 0.6988 |
0.852 | 4.3339 | 10800 | 1.5532 | 0.7014 |
0.7597 | 4.4141 | 11000 | 1.5395 | 0.7036 |
0.9044 | 4.4944 | 11200 | 1.5195 | 0.7034 |
0.7762 | 4.5746 | 11400 | 1.5106 | 0.7014 |
0.6486 | 4.6549 | 11600 | 1.4979 | 0.7034 |
0.7373 | 4.7352 | 11800 | 1.4804 | 0.7032 |
0.9194 | 4.8154 | 12000 | 1.4659 | 0.7038 |
0.6513 | 4.8957 | 12200 | 1.4487 | 0.7050 |
0.7235 | 4.9759 | 12400 | 1.4307 | 0.7082 |
0.4407 | 5.0562 | 12600 | 1.4304 | 0.7082 |
0.5979 | 5.1364 | 12800 | 1.4227 | 0.7112 |
0.6776 | 5.2167 | 13000 | 1.4237 | 0.7048 |
0.5239 | 5.2970 | 13200 | 1.4098 | 0.7066 |
0.5614 | 5.3772 | 13400 | 1.3947 | 0.7110 |
0.5483 | 5.4575 | 13600 | 1.3901 | 0.7114 |
0.4797 | 5.5377 | 13800 | 1.3844 | 0.7082 |
0.5795 | 5.6180 | 14000 | 1.3816 | 0.7120 |
0.5108 | 5.6982 | 14200 | 1.3748 | 0.7098 |
0.3919 | 5.7785 | 14400 | 1.3662 | 0.7138 |
0.5572 | 5.8587 | 14600 | 1.3542 | 0.7154 |
0.5333 | 5.9390 | 14800 | 1.3451 | 0.7152 |
0.2997 | 6.0193 | 15000 | 1.3406 | 0.7217 |
0.3923 | 6.0995 | 15200 | 1.3472 | 0.7162 |
0.4682 | 6.1798 | 15400 | 1.3437 | 0.7170 |
0.3758 | 6.2600 | 15600 | 1.3396 | 0.7162 |
0.3123 | 6.3403 | 15800 | 1.3393 | 0.7182 |
0.2974 | 6.4205 | 16000 | 1.3303 | 0.7150 |
0.3374 | 6.5008 | 16200 | 1.3275 | 0.7170 |
0.5128 | 6.5811 | 16400 | 1.3322 | 0.7126 |
0.4074 | 6.6613 | 16600 | 1.3254 | 0.7162 |
0.4761 | 6.7416 | 16800 | 1.3249 | 0.7144 |
0.2215 | 6.8218 | 17000 | 1.3247 | 0.7134 |
0.4581 | 6.9021 | 17200 | 1.3237 | 0.7120 |
0.2686 | 6.9823 | 17400 | 1.3138 | 0.7162 |
0.375 | 7.0626 | 17600 | 1.3197 | 0.7146 |
0.2512 | 7.1429 | 17800 | 1.3172 | 0.7146 |
0.3274 | 7.2231 | 18000 | 1.3222 | 0.7134 |
0.3209 | 7.3034 | 18200 | 1.3272 | 0.7126 |
0.2441 | 7.3836 | 18400 | 1.3216 | 0.7124 |
0.2725 | 7.4639 | 18600 | 1.3156 | 0.7132 |
0.2326 | 7.5441 | 18800 | 1.3155 | 0.7132 |
0.3594 | 7.6244 | 19000 | 1.3140 | 0.7162 |
0.2297 | 7.7047 | 19200 | 1.3133 | 0.7152 |
0.3722 | 7.7849 | 19400 | 1.3160 | 0.7130 |
0.202 | 7.8652 | 19600 | 1.3131 | 0.7142 |
0.2272 | 7.9454 | 19800 | 1.3123 | 0.7150 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1