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_00001_fold5
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: 0.8292682926829268
hushem_1x_beit_base_rms_00001_fold5
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: 0.7273
- Accuracy: 0.8293
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: 1e-05
- 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 | 1.3481 | 0.2927 |
1.3909 | 2.0 | 12 | 0.6605 | 0.7317 |
1.3909 | 3.0 | 18 | 0.4292 | 0.8780 |
0.5403 | 4.0 | 24 | 0.4452 | 0.7805 |
0.1465 | 5.0 | 30 | 0.3293 | 0.8537 |
0.1465 | 6.0 | 36 | 0.3638 | 0.8537 |
0.0351 | 7.0 | 42 | 0.4318 | 0.8537 |
0.0351 | 8.0 | 48 | 0.5448 | 0.8537 |
0.0141 | 9.0 | 54 | 0.6437 | 0.8049 |
0.0043 | 10.0 | 60 | 0.5878 | 0.8293 |
0.0043 | 11.0 | 66 | 0.6177 | 0.8537 |
0.0037 | 12.0 | 72 | 0.5464 | 0.8537 |
0.0037 | 13.0 | 78 | 0.5884 | 0.8537 |
0.0055 | 14.0 | 84 | 0.5978 | 0.8537 |
0.0023 | 15.0 | 90 | 0.6603 | 0.8293 |
0.0023 | 16.0 | 96 | 0.8364 | 0.7805 |
0.0022 | 17.0 | 102 | 0.7710 | 0.8049 |
0.0022 | 18.0 | 108 | 0.8111 | 0.7805 |
0.0021 | 19.0 | 114 | 0.8487 | 0.7805 |
0.0014 | 20.0 | 120 | 0.7148 | 0.8049 |
0.0014 | 21.0 | 126 | 0.7288 | 0.8049 |
0.0018 | 22.0 | 132 | 0.6188 | 0.8537 |
0.0018 | 23.0 | 138 | 0.6580 | 0.8537 |
0.0007 | 24.0 | 144 | 0.6927 | 0.8537 |
0.0009 | 25.0 | 150 | 0.6863 | 0.8537 |
0.0009 | 26.0 | 156 | 0.6891 | 0.8537 |
0.0005 | 27.0 | 162 | 0.7029 | 0.8537 |
0.0005 | 28.0 | 168 | 0.6879 | 0.8537 |
0.0008 | 29.0 | 174 | 0.7177 | 0.8537 |
0.0005 | 30.0 | 180 | 0.7192 | 0.8537 |
0.0005 | 31.0 | 186 | 0.6892 | 0.8537 |
0.0009 | 32.0 | 192 | 0.7016 | 0.8537 |
0.0009 | 33.0 | 198 | 0.6329 | 0.8537 |
0.0013 | 34.0 | 204 | 0.6550 | 0.8537 |
0.0012 | 35.0 | 210 | 0.7178 | 0.8293 |
0.0012 | 36.0 | 216 | 0.7226 | 0.8293 |
0.0005 | 37.0 | 222 | 0.7238 | 0.8293 |
0.0005 | 38.0 | 228 | 0.7249 | 0.8293 |
0.0004 | 39.0 | 234 | 0.7268 | 0.8293 |
0.0005 | 40.0 | 240 | 0.7276 | 0.8293 |
0.0005 | 41.0 | 246 | 0.7269 | 0.8293 |
0.0008 | 42.0 | 252 | 0.7273 | 0.8293 |
0.0008 | 43.0 | 258 | 0.7273 | 0.8293 |
0.0005 | 44.0 | 264 | 0.7273 | 0.8293 |
0.0004 | 45.0 | 270 | 0.7273 | 0.8293 |
0.0004 | 46.0 | 276 | 0.7273 | 0.8293 |
0.0071 | 47.0 | 282 | 0.7273 | 0.8293 |
0.0071 | 48.0 | 288 | 0.7273 | 0.8293 |
0.0008 | 49.0 | 294 | 0.7273 | 0.8293 |
0.0003 | 50.0 | 300 | 0.7273 | 0.8293 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0