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_fold4
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: 0.30952380952380953
hushem_5x_beit_base_sgd_00001_fold4
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: 1.4856
- Accuracy: 0.3095
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 |
---|---|---|---|---|
1.5648 | 1.0 | 28 | 1.5024 | 0.3095 |
1.5958 | 2.0 | 56 | 1.5016 | 0.3095 |
1.5478 | 3.0 | 84 | 1.5008 | 0.3095 |
1.6175 | 4.0 | 112 | 1.5001 | 0.3095 |
1.5019 | 5.0 | 140 | 1.4994 | 0.3095 |
1.5612 | 6.0 | 168 | 1.4987 | 0.3095 |
1.5556 | 7.0 | 196 | 1.4981 | 0.3095 |
1.5275 | 8.0 | 224 | 1.4974 | 0.3095 |
1.529 | 9.0 | 252 | 1.4968 | 0.3095 |
1.5306 | 10.0 | 280 | 1.4962 | 0.3095 |
1.5486 | 11.0 | 308 | 1.4956 | 0.3095 |
1.5567 | 12.0 | 336 | 1.4950 | 0.3095 |
1.5578 | 13.0 | 364 | 1.4945 | 0.3095 |
1.5601 | 14.0 | 392 | 1.4939 | 0.3095 |
1.5869 | 15.0 | 420 | 1.4934 | 0.3095 |
1.5292 | 16.0 | 448 | 1.4929 | 0.3095 |
1.584 | 17.0 | 476 | 1.4924 | 0.3095 |
1.5709 | 18.0 | 504 | 1.4919 | 0.3095 |
1.5246 | 19.0 | 532 | 1.4915 | 0.3095 |
1.508 | 20.0 | 560 | 1.4911 | 0.3095 |
1.5627 | 21.0 | 588 | 1.4907 | 0.3095 |
1.543 | 22.0 | 616 | 1.4904 | 0.3095 |
1.5306 | 23.0 | 644 | 1.4900 | 0.3095 |
1.5347 | 24.0 | 672 | 1.4896 | 0.3095 |
1.5296 | 25.0 | 700 | 1.4893 | 0.3095 |
1.5722 | 26.0 | 728 | 1.4889 | 0.3095 |
1.6103 | 27.0 | 756 | 1.4886 | 0.3095 |
1.5352 | 28.0 | 784 | 1.4883 | 0.3095 |
1.5133 | 29.0 | 812 | 1.4880 | 0.3095 |
1.4677 | 30.0 | 840 | 1.4878 | 0.3095 |
1.5424 | 31.0 | 868 | 1.4876 | 0.3095 |
1.5132 | 32.0 | 896 | 1.4873 | 0.3095 |
1.5611 | 33.0 | 924 | 1.4871 | 0.3095 |
1.5494 | 34.0 | 952 | 1.4869 | 0.3095 |
1.5087 | 35.0 | 980 | 1.4867 | 0.3095 |
1.5719 | 36.0 | 1008 | 1.4865 | 0.3095 |
1.5037 | 37.0 | 1036 | 1.4864 | 0.3095 |
1.5457 | 38.0 | 1064 | 1.4863 | 0.3095 |
1.5227 | 39.0 | 1092 | 1.4861 | 0.3095 |
1.5024 | 40.0 | 1120 | 1.4860 | 0.3095 |
1.5112 | 41.0 | 1148 | 1.4859 | 0.3095 |
1.4872 | 42.0 | 1176 | 1.4858 | 0.3095 |
1.5623 | 43.0 | 1204 | 1.4858 | 0.3095 |
1.5147 | 44.0 | 1232 | 1.4857 | 0.3095 |
1.5196 | 45.0 | 1260 | 1.4857 | 0.3095 |
1.5574 | 46.0 | 1288 | 1.4856 | 0.3095 |
1.5277 | 47.0 | 1316 | 1.4856 | 0.3095 |
1.602 | 48.0 | 1344 | 1.4856 | 0.3095 |
1.5259 | 49.0 | 1372 | 1.4856 | 0.3095 |
1.5075 | 50.0 | 1400 | 1.4856 | 0.3095 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0