|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: invitrace-ilivewell-freeze-layer11 |
|
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: 0.7194461167971101 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# invitrace-ilivewell-freeze-layer11 |
|
|
|
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 imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3049 |
|
- Accuracy: 0.7194 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:| |
|
| 5.0728 | 0.0803 | 200 | 5.0558 | 0.0417 | |
|
| 4.9729 | 0.1605 | 400 | 4.9402 | 0.0865 | |
|
| 4.8315 | 0.2408 | 600 | 4.8201 | 0.1738 | |
|
| 4.6814 | 0.3210 | 800 | 4.6929 | 0.1999 | |
|
| 4.5936 | 0.4013 | 1000 | 4.5779 | 0.2296 | |
|
| 4.5513 | 0.4815 | 1200 | 4.4604 | 0.2645 | |
|
| 4.3161 | 0.5618 | 1400 | 4.3466 | 0.2976 | |
|
| 4.2724 | 0.6421 | 1600 | 4.2445 | 0.3472 | |
|
| 4.1105 | 0.7223 | 1800 | 4.1402 | 0.3530 | |
|
| 4.076 | 0.8026 | 2000 | 4.0522 | 0.3703 | |
|
| 3.9963 | 0.8828 | 2200 | 3.9616 | 0.3803 | |
|
| 3.9235 | 0.9631 | 2400 | 3.8737 | 0.4122 | |
|
| 3.5191 | 1.0433 | 2600 | 3.7816 | 0.4142 | |
|
| 3.6156 | 1.1236 | 2800 | 3.6908 | 0.4345 | |
|
| 3.4338 | 1.2039 | 3000 | 3.6081 | 0.4487 | |
|
| 3.4952 | 1.2841 | 3200 | 3.5293 | 0.4792 | |
|
| 3.369 | 1.3644 | 3400 | 3.4345 | 0.4836 | |
|
| 3.3625 | 1.4446 | 3600 | 3.3572 | 0.5065 | |
|
| 3.3323 | 1.5249 | 3800 | 3.2832 | 0.5160 | |
|
| 3.2143 | 1.6051 | 4000 | 3.2152 | 0.5035 | |
|
| 3.0538 | 1.6854 | 4200 | 3.1389 | 0.5212 | |
|
| 3.0841 | 1.7657 | 4400 | 3.0654 | 0.5418 | |
|
| 2.9804 | 1.8459 | 4600 | 2.9880 | 0.5493 | |
|
| 3.0014 | 1.9262 | 4800 | 2.9356 | 0.5449 | |
|
| 3.0302 | 2.0064 | 5000 | 2.8573 | 0.5585 | |
|
| 2.714 | 2.0867 | 5200 | 2.7933 | 0.5667 | |
|
| 2.6886 | 2.1669 | 5400 | 2.7398 | 0.5649 | |
|
| 2.4439 | 2.2472 | 5600 | 2.6725 | 0.5802 | |
|
| 2.3172 | 2.3274 | 5800 | 2.6106 | 0.5836 | |
|
| 2.3907 | 2.4077 | 6000 | 2.5523 | 0.5896 | |
|
| 2.617 | 2.4880 | 6200 | 2.4995 | 0.5942 | |
|
| 2.1277 | 2.5682 | 6400 | 2.4401 | 0.6041 | |
|
| 2.2384 | 2.6485 | 6600 | 2.3903 | 0.6113 | |
|
| 2.2872 | 2.7287 | 6800 | 2.3348 | 0.6163 | |
|
| 2.1654 | 2.8090 | 7000 | 2.3031 | 0.6083 | |
|
| 2.1407 | 2.8892 | 7200 | 2.2365 | 0.6239 | |
|
| 2.0487 | 2.9695 | 7400 | 2.2016 | 0.6179 | |
|
| 1.9755 | 3.0498 | 7600 | 2.1587 | 0.6281 | |
|
| 1.7432 | 3.1300 | 7800 | 2.1125 | 0.6382 | |
|
| 1.7321 | 3.2103 | 8000 | 2.0822 | 0.6438 | |
|
| 1.4812 | 3.2905 | 8200 | 2.0482 | 0.6390 | |
|
| 1.637 | 3.3708 | 8400 | 1.9964 | 0.6556 | |
|
| 1.538 | 3.4510 | 8600 | 1.9785 | 0.6472 | |
|
| 1.9383 | 3.5313 | 8800 | 1.9220 | 0.6602 | |
|
| 1.5674 | 3.6116 | 9000 | 1.9167 | 0.6558 | |
|
| 1.6303 | 3.6918 | 9200 | 1.8803 | 0.6629 | |
|
| 1.3882 | 3.7721 | 9400 | 1.8531 | 0.6619 | |
|
| 1.5955 | 3.8523 | 9600 | 1.8092 | 0.6739 | |
|
| 1.5168 | 3.9326 | 9800 | 1.7814 | 0.6763 | |
|
| 1.5228 | 4.0128 | 10000 | 1.7617 | 0.6697 | |
|
| 1.3918 | 4.0931 | 10200 | 1.7434 | 0.6771 | |
|
| 1.3898 | 4.1734 | 10400 | 1.6937 | 0.6769 | |
|
| 1.3597 | 4.2536 | 10600 | 1.6928 | 0.6801 | |
|
| 1.3249 | 4.3339 | 10800 | 1.6636 | 0.6807 | |
|
| 1.361 | 4.4141 | 11000 | 1.6585 | 0.6829 | |
|
| 1.2845 | 4.4944 | 11200 | 1.6296 | 0.6887 | |
|
| 1.2342 | 4.5746 | 11400 | 1.6049 | 0.6928 | |
|
| 1.1281 | 4.6549 | 11600 | 1.5856 | 0.6948 | |
|
| 1.2667 | 4.7352 | 11800 | 1.5775 | 0.6905 | |
|
| 1.3742 | 4.8154 | 12000 | 1.5698 | 0.6911 | |
|
| 1.076 | 4.8957 | 12200 | 1.5423 | 0.6942 | |
|
| 1.2422 | 4.9759 | 12400 | 1.5282 | 0.6970 | |
|
| 0.9078 | 5.0562 | 12600 | 1.5109 | 0.6992 | |
|
| 1.0157 | 5.1364 | 12800 | 1.4908 | 0.7010 | |
|
| 1.1909 | 5.2167 | 13000 | 1.4917 | 0.7006 | |
|
| 1.0085 | 5.2970 | 13200 | 1.4804 | 0.6996 | |
|
| 1.0942 | 5.3772 | 13400 | 1.4662 | 0.7024 | |
|
| 0.9015 | 5.4575 | 13600 | 1.4785 | 0.6952 | |
|
| 0.899 | 5.5377 | 13800 | 1.4409 | 0.7076 | |
|
| 1.1695 | 5.6180 | 14000 | 1.4347 | 0.7074 | |
|
| 0.9743 | 5.6982 | 14200 | 1.4381 | 0.7084 | |
|
| 0.9005 | 5.7785 | 14400 | 1.4145 | 0.7086 | |
|
| 1.0092 | 5.8587 | 14600 | 1.4067 | 0.7128 | |
|
| 0.9859 | 5.9390 | 14800 | 1.3790 | 0.7186 | |
|
| 0.8728 | 6.0193 | 15000 | 1.3951 | 0.7138 | |
|
| 0.8551 | 6.0995 | 15200 | 1.3765 | 0.7211 | |
|
| 0.8369 | 6.1798 | 15400 | 1.3751 | 0.7154 | |
|
| 0.8989 | 6.2600 | 15600 | 1.3641 | 0.7168 | |
|
| 0.7289 | 6.3403 | 15800 | 1.3701 | 0.7162 | |
|
| 0.7181 | 6.4205 | 16000 | 1.3661 | 0.7088 | |
|
| 0.7517 | 6.5008 | 16200 | 1.3528 | 0.7136 | |
|
| 1.0271 | 6.5811 | 16400 | 1.3405 | 0.7200 | |
|
| 0.8599 | 6.6613 | 16600 | 1.3296 | 0.7215 | |
|
| 1.0141 | 6.7416 | 16800 | 1.3379 | 0.7190 | |
|
| 0.6966 | 6.8218 | 17000 | 1.3294 | 0.7194 | |
|
| 0.9327 | 6.9021 | 17200 | 1.3241 | 0.7198 | |
|
| 0.8072 | 6.9823 | 17400 | 1.3226 | 0.7196 | |
|
| 0.9195 | 7.0626 | 17600 | 1.3234 | 0.7170 | |
|
| 0.6585 | 7.1429 | 17800 | 1.3171 | 0.7207 | |
|
| 0.9513 | 7.2231 | 18000 | 1.3064 | 0.7190 | |
|
| 0.7139 | 7.3034 | 18200 | 1.3156 | 0.7215 | |
|
| 0.7199 | 7.3836 | 18400 | 1.3098 | 0.7249 | |
|
| 0.7799 | 7.4639 | 18600 | 1.3210 | 0.7166 | |
|
| 0.7034 | 7.5441 | 18800 | 1.3015 | 0.7245 | |
|
| 0.8172 | 7.6244 | 19000 | 1.2978 | 0.7289 | |
|
| 0.6842 | 7.7047 | 19200 | 1.3084 | 0.7184 | |
|
| 0.8592 | 7.7849 | 19400 | 1.2991 | 0.7231 | |
|
| 0.7255 | 7.8652 | 19600 | 1.2929 | 0.7257 | |
|
| 0.8207 | 7.9454 | 19800 | 1.3049 | 0.7194 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
