metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_1x_beit_base_rms_001_fold3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.3953488372093023
hushem_1x_beit_base_rms_001_fold3
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: 1.6210
- Accuracy: 0.3953
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 |
---|---|---|---|---|
No log | 1.0 | 6 | 4.8894 | 0.2326 |
4.4417 | 2.0 | 12 | 1.8176 | 0.2558 |
4.4417 | 3.0 | 18 | 1.7138 | 0.2558 |
1.6178 | 4.0 | 24 | 1.4939 | 0.2558 |
1.4727 | 5.0 | 30 | 1.4012 | 0.2326 |
1.4727 | 6.0 | 36 | 1.4010 | 0.2558 |
1.3417 | 7.0 | 42 | 1.4942 | 0.3023 |
1.3417 | 8.0 | 48 | 1.4300 | 0.2558 |
1.3201 | 9.0 | 54 | 1.3963 | 0.2326 |
1.3475 | 10.0 | 60 | 1.4128 | 0.3488 |
1.3475 | 11.0 | 66 | 1.4248 | 0.3023 |
1.286 | 12.0 | 72 | 1.4058 | 0.3488 |
1.286 | 13.0 | 78 | 1.3763 | 0.3023 |
1.2349 | 14.0 | 84 | 1.3835 | 0.2791 |
1.2129 | 15.0 | 90 | 1.3655 | 0.3488 |
1.2129 | 16.0 | 96 | 1.3765 | 0.2558 |
1.215 | 17.0 | 102 | 1.3898 | 0.3488 |
1.215 | 18.0 | 108 | 1.4215 | 0.3721 |
1.1858 | 19.0 | 114 | 1.4008 | 0.3023 |
1.1772 | 20.0 | 120 | 1.3543 | 0.2791 |
1.1772 | 21.0 | 126 | 1.5020 | 0.2791 |
1.1365 | 22.0 | 132 | 1.4006 | 0.3256 |
1.1365 | 23.0 | 138 | 1.4145 | 0.3256 |
1.1417 | 24.0 | 144 | 1.3987 | 0.2791 |
1.0966 | 25.0 | 150 | 1.4121 | 0.3023 |
1.0966 | 26.0 | 156 | 1.3953 | 0.2791 |
1.0941 | 27.0 | 162 | 1.5116 | 0.3256 |
1.0941 | 28.0 | 168 | 1.3871 | 0.3488 |
1.0777 | 29.0 | 174 | 1.3779 | 0.3488 |
1.0766 | 30.0 | 180 | 1.3806 | 0.3488 |
1.0766 | 31.0 | 186 | 1.4716 | 0.3256 |
1.0237 | 32.0 | 192 | 1.4549 | 0.3488 |
1.0237 | 33.0 | 198 | 1.5155 | 0.3721 |
1.0081 | 34.0 | 204 | 1.4254 | 0.3488 |
0.9905 | 35.0 | 210 | 1.4408 | 0.3953 |
0.9905 | 36.0 | 216 | 1.6753 | 0.3953 |
0.9364 | 37.0 | 222 | 1.7926 | 0.3488 |
0.9364 | 38.0 | 228 | 1.6780 | 0.4186 |
0.8986 | 39.0 | 234 | 1.6075 | 0.3953 |
0.8892 | 40.0 | 240 | 1.5788 | 0.4419 |
0.8892 | 41.0 | 246 | 1.6155 | 0.4186 |
0.8545 | 42.0 | 252 | 1.6210 | 0.3953 |
0.8545 | 43.0 | 258 | 1.6210 | 0.3953 |
0.8504 | 44.0 | 264 | 1.6210 | 0.3953 |
0.8795 | 45.0 | 270 | 1.6210 | 0.3953 |
0.8795 | 46.0 | 276 | 1.6210 | 0.3953 |
0.8368 | 47.0 | 282 | 1.6210 | 0.3953 |
0.8368 | 48.0 | 288 | 1.6210 | 0.3953 |
0.8886 | 49.0 | 294 | 1.6210 | 0.3953 |
0.8644 | 50.0 | 300 | 1.6210 | 0.3953 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0