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_00001_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: 0.26666666666666666
hushem_5x_beit_base_sgd_00001_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: 1.5922
- Accuracy: 0.2667
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 |
---|---|---|---|---|
1.4867 | 1.0 | 27 | 1.6071 | 0.2667 |
1.5392 | 2.0 | 54 | 1.6064 | 0.2667 |
1.5844 | 3.0 | 81 | 1.6056 | 0.2667 |
1.5797 | 4.0 | 108 | 1.6050 | 0.2667 |
1.5108 | 5.0 | 135 | 1.6044 | 0.2667 |
1.5236 | 6.0 | 162 | 1.6037 | 0.2667 |
1.5199 | 7.0 | 189 | 1.6031 | 0.2667 |
1.544 | 8.0 | 216 | 1.6026 | 0.2667 |
1.5317 | 9.0 | 243 | 1.6020 | 0.2667 |
1.537 | 10.0 | 270 | 1.6014 | 0.2667 |
1.5415 | 11.0 | 297 | 1.6010 | 0.2667 |
1.5478 | 12.0 | 324 | 1.6004 | 0.2667 |
1.4666 | 13.0 | 351 | 1.6000 | 0.2667 |
1.5352 | 14.0 | 378 | 1.5995 | 0.2667 |
1.478 | 15.0 | 405 | 1.5990 | 0.2667 |
1.5333 | 16.0 | 432 | 1.5986 | 0.2667 |
1.5245 | 17.0 | 459 | 1.5982 | 0.2667 |
1.5379 | 18.0 | 486 | 1.5978 | 0.2667 |
1.52 | 19.0 | 513 | 1.5975 | 0.2667 |
1.5508 | 20.0 | 540 | 1.5971 | 0.2667 |
1.5421 | 21.0 | 567 | 1.5967 | 0.2667 |
1.4919 | 22.0 | 594 | 1.5963 | 0.2667 |
1.483 | 23.0 | 621 | 1.5960 | 0.2667 |
1.5087 | 24.0 | 648 | 1.5957 | 0.2667 |
1.5236 | 25.0 | 675 | 1.5954 | 0.2667 |
1.5228 | 26.0 | 702 | 1.5951 | 0.2667 |
1.5439 | 27.0 | 729 | 1.5949 | 0.2667 |
1.5272 | 28.0 | 756 | 1.5946 | 0.2667 |
1.5029 | 29.0 | 783 | 1.5943 | 0.2667 |
1.5695 | 30.0 | 810 | 1.5941 | 0.2667 |
1.5057 | 31.0 | 837 | 1.5939 | 0.2667 |
1.5092 | 32.0 | 864 | 1.5937 | 0.2667 |
1.575 | 33.0 | 891 | 1.5935 | 0.2667 |
1.5175 | 34.0 | 918 | 1.5934 | 0.2667 |
1.4801 | 35.0 | 945 | 1.5932 | 0.2667 |
1.4771 | 36.0 | 972 | 1.5930 | 0.2667 |
1.5042 | 37.0 | 999 | 1.5929 | 0.2667 |
1.5372 | 38.0 | 1026 | 1.5928 | 0.2667 |
1.5158 | 39.0 | 1053 | 1.5927 | 0.2667 |
1.4902 | 40.0 | 1080 | 1.5926 | 0.2667 |
1.4904 | 41.0 | 1107 | 1.5925 | 0.2667 |
1.4817 | 42.0 | 1134 | 1.5924 | 0.2667 |
1.5064 | 43.0 | 1161 | 1.5923 | 0.2667 |
1.4625 | 44.0 | 1188 | 1.5923 | 0.2667 |
1.5064 | 45.0 | 1215 | 1.5923 | 0.2667 |
1.4956 | 46.0 | 1242 | 1.5922 | 0.2667 |
1.502 | 47.0 | 1269 | 1.5922 | 0.2667 |
1.495 | 48.0 | 1296 | 1.5922 | 0.2667 |
1.4896 | 49.0 | 1323 | 1.5922 | 0.2667 |
1.5118 | 50.0 | 1350 | 1.5922 | 0.2667 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0