metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_beit_base_sgd_0001_fold1
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: 0.24444444444444444
hushem_5x_beit_base_sgd_0001_fold1
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: 1.5157
- Accuracy: 0.2444
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: 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 |
---|---|---|---|---|
1.4822 | 1.0 | 27 | 1.6002 | 0.2667 |
1.5214 | 2.0 | 54 | 1.5936 | 0.2667 |
1.5576 | 3.0 | 81 | 1.5870 | 0.2667 |
1.5472 | 4.0 | 108 | 1.5816 | 0.2667 |
1.4716 | 5.0 | 135 | 1.5767 | 0.2667 |
1.4758 | 6.0 | 162 | 1.5710 | 0.2667 |
1.4611 | 7.0 | 189 | 1.5663 | 0.2667 |
1.4821 | 8.0 | 216 | 1.5623 | 0.2667 |
1.4618 | 9.0 | 243 | 1.5580 | 0.2667 |
1.4567 | 10.0 | 270 | 1.5546 | 0.2667 |
1.4567 | 11.0 | 297 | 1.5511 | 0.2667 |
1.453 | 12.0 | 324 | 1.5484 | 0.2667 |
1.3888 | 13.0 | 351 | 1.5457 | 0.2667 |
1.4317 | 14.0 | 378 | 1.5428 | 0.2667 |
1.3877 | 15.0 | 405 | 1.5404 | 0.2667 |
1.4231 | 16.0 | 432 | 1.5382 | 0.2667 |
1.3948 | 17.0 | 459 | 1.5365 | 0.2667 |
1.4184 | 18.0 | 486 | 1.5346 | 0.2667 |
1.4164 | 19.0 | 513 | 1.5325 | 0.2667 |
1.4155 | 20.0 | 540 | 1.5309 | 0.2667 |
1.4058 | 21.0 | 567 | 1.5293 | 0.2667 |
1.3567 | 22.0 | 594 | 1.5276 | 0.2444 |
1.3445 | 23.0 | 621 | 1.5270 | 0.2444 |
1.3726 | 24.0 | 648 | 1.5258 | 0.2444 |
1.3733 | 25.0 | 675 | 1.5248 | 0.2444 |
1.386 | 26.0 | 702 | 1.5239 | 0.2444 |
1.392 | 27.0 | 729 | 1.5231 | 0.2444 |
1.3461 | 28.0 | 756 | 1.5218 | 0.2444 |
1.3599 | 29.0 | 783 | 1.5209 | 0.2444 |
1.4064 | 30.0 | 810 | 1.5203 | 0.2444 |
1.348 | 31.0 | 837 | 1.5201 | 0.2444 |
1.3411 | 32.0 | 864 | 1.5195 | 0.2444 |
1.4156 | 33.0 | 891 | 1.5189 | 0.2444 |
1.3382 | 34.0 | 918 | 1.5185 | 0.2444 |
1.3361 | 35.0 | 945 | 1.5180 | 0.2444 |
1.3197 | 36.0 | 972 | 1.5176 | 0.2444 |
1.3433 | 37.0 | 999 | 1.5173 | 0.2444 |
1.3575 | 38.0 | 1026 | 1.5170 | 0.2444 |
1.3276 | 39.0 | 1053 | 1.5168 | 0.2444 |
1.3024 | 40.0 | 1080 | 1.5166 | 0.2444 |
1.3207 | 41.0 | 1107 | 1.5163 | 0.2444 |
1.3095 | 42.0 | 1134 | 1.5162 | 0.2444 |
1.3386 | 43.0 | 1161 | 1.5160 | 0.2444 |
1.2808 | 44.0 | 1188 | 1.5159 | 0.2444 |
1.3213 | 45.0 | 1215 | 1.5158 | 0.2444 |
1.3279 | 46.0 | 1242 | 1.5157 | 0.2444 |
1.3133 | 47.0 | 1269 | 1.5157 | 0.2444 |
1.3138 | 48.0 | 1296 | 1.5157 | 0.2444 |
1.3263 | 49.0 | 1323 | 1.5157 | 0.2444 |
1.3148 | 50.0 | 1350 | 1.5157 | 0.2444 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0