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_adamax_001_fold2
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: 0.5777777777777777
hushem_5x_beit_base_adamax_001_fold2
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: 6.3078
- Accuracy: 0.5778
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 |
---|---|---|---|---|
1.4226 | 1.0 | 27 | 1.4140 | 0.2667 |
1.2045 | 2.0 | 54 | 1.6573 | 0.2889 |
1.2481 | 3.0 | 81 | 1.5730 | 0.2889 |
1.322 | 4.0 | 108 | 1.5814 | 0.2889 |
0.9418 | 5.0 | 135 | 1.4941 | 0.4889 |
0.9982 | 6.0 | 162 | 1.2480 | 0.4222 |
0.9049 | 7.0 | 189 | 1.2328 | 0.4667 |
0.7944 | 8.0 | 216 | 1.2343 | 0.4889 |
0.9595 | 9.0 | 243 | 1.3356 | 0.4667 |
0.7289 | 10.0 | 270 | 1.3692 | 0.4889 |
0.696 | 11.0 | 297 | 1.4324 | 0.4444 |
0.7466 | 12.0 | 324 | 1.4783 | 0.4667 |
0.7646 | 13.0 | 351 | 1.3725 | 0.4889 |
0.6451 | 14.0 | 378 | 2.0057 | 0.5333 |
0.5784 | 15.0 | 405 | 2.4024 | 0.4444 |
0.5544 | 16.0 | 432 | 2.4151 | 0.5111 |
0.563 | 17.0 | 459 | 1.9054 | 0.5556 |
0.5213 | 18.0 | 486 | 3.0169 | 0.5333 |
0.551 | 19.0 | 513 | 2.4504 | 0.5333 |
0.613 | 20.0 | 540 | 2.7289 | 0.5333 |
0.4577 | 21.0 | 567 | 2.8661 | 0.5111 |
0.3823 | 22.0 | 594 | 2.7689 | 0.4444 |
0.3921 | 23.0 | 621 | 3.3303 | 0.5556 |
0.3974 | 24.0 | 648 | 3.5099 | 0.4444 |
0.3186 | 25.0 | 675 | 2.8023 | 0.5556 |
0.2983 | 26.0 | 702 | 3.0145 | 0.4889 |
0.2885 | 27.0 | 729 | 3.6675 | 0.4667 |
0.1902 | 28.0 | 756 | 3.2605 | 0.5556 |
0.2253 | 29.0 | 783 | 4.9420 | 0.5111 |
0.1963 | 30.0 | 810 | 4.0120 | 0.4889 |
0.1797 | 31.0 | 837 | 4.7762 | 0.5778 |
0.1892 | 32.0 | 864 | 4.0878 | 0.5333 |
0.1404 | 33.0 | 891 | 4.6569 | 0.5111 |
0.0882 | 34.0 | 918 | 4.6823 | 0.5556 |
0.1578 | 35.0 | 945 | 5.1512 | 0.5111 |
0.0782 | 36.0 | 972 | 5.2444 | 0.5778 |
0.0461 | 37.0 | 999 | 5.0650 | 0.5556 |
0.0253 | 38.0 | 1026 | 5.4464 | 0.5556 |
0.0617 | 39.0 | 1053 | 5.7436 | 0.5778 |
0.0131 | 40.0 | 1080 | 6.2467 | 0.5556 |
0.0373 | 41.0 | 1107 | 6.5043 | 0.5778 |
0.0018 | 42.0 | 1134 | 6.2715 | 0.5778 |
0.0403 | 43.0 | 1161 | 6.0713 | 0.5556 |
0.0098 | 44.0 | 1188 | 6.6508 | 0.5556 |
0.0159 | 45.0 | 1215 | 6.4236 | 0.5778 |
0.0031 | 46.0 | 1242 | 6.3525 | 0.5778 |
0.007 | 47.0 | 1269 | 6.2593 | 0.5778 |
0.0011 | 48.0 | 1296 | 6.3063 | 0.5778 |
0.0085 | 49.0 | 1323 | 6.3078 | 0.5778 |
0.0126 | 50.0 | 1350 | 6.3078 | 0.5778 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0