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_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: 0.40476190476190477
hushem_5x_beit_base_sgd_0001_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: 1.3804
- Accuracy: 0.4048
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 |
|---|---|---|---|---|
| 1.4632 | 1.0 | 28 | 1.5173 | 0.2143 |
| 1.3741 | 2.0 | 56 | 1.5094 | 0.2381 |
| 1.4021 | 3.0 | 84 | 1.5010 | 0.2381 |
| 1.3681 | 4.0 | 112 | 1.4942 | 0.2381 |
| 1.4122 | 5.0 | 140 | 1.4872 | 0.2381 |
| 1.3657 | 6.0 | 168 | 1.4803 | 0.2619 |
| 1.3993 | 7.0 | 196 | 1.4742 | 0.2619 |
| 1.3652 | 8.0 | 224 | 1.4681 | 0.2619 |
| 1.3615 | 9.0 | 252 | 1.4624 | 0.2619 |
| 1.3492 | 10.0 | 280 | 1.4574 | 0.2619 |
| 1.3205 | 11.0 | 308 | 1.4526 | 0.2619 |
| 1.3552 | 12.0 | 336 | 1.4476 | 0.2619 |
| 1.3393 | 13.0 | 364 | 1.4435 | 0.2619 |
| 1.3397 | 14.0 | 392 | 1.4389 | 0.2619 |
| 1.3561 | 15.0 | 420 | 1.4347 | 0.2619 |
| 1.3361 | 16.0 | 448 | 1.4313 | 0.2619 |
| 1.3287 | 17.0 | 476 | 1.4281 | 0.2857 |
| 1.3138 | 18.0 | 504 | 1.4246 | 0.3095 |
| 1.3241 | 19.0 | 532 | 1.4213 | 0.3095 |
| 1.3033 | 20.0 | 560 | 1.4184 | 0.3095 |
| 1.3163 | 21.0 | 588 | 1.4155 | 0.3095 |
| 1.3116 | 22.0 | 616 | 1.4126 | 0.3095 |
| 1.3228 | 23.0 | 644 | 1.4101 | 0.3095 |
| 1.3214 | 24.0 | 672 | 1.4076 | 0.3333 |
| 1.2818 | 25.0 | 700 | 1.4051 | 0.3333 |
| 1.2948 | 26.0 | 728 | 1.4029 | 0.3333 |
| 1.3231 | 27.0 | 756 | 1.4008 | 0.3333 |
| 1.2969 | 28.0 | 784 | 1.3988 | 0.3333 |
| 1.2659 | 29.0 | 812 | 1.3969 | 0.3333 |
| 1.2426 | 30.0 | 840 | 1.3952 | 0.3571 |
| 1.2934 | 31.0 | 868 | 1.3935 | 0.3810 |
| 1.2777 | 32.0 | 896 | 1.3917 | 0.4048 |
| 1.2767 | 33.0 | 924 | 1.3904 | 0.4048 |
| 1.3162 | 34.0 | 952 | 1.3892 | 0.4048 |
| 1.2726 | 35.0 | 980 | 1.3880 | 0.4048 |
| 1.294 | 36.0 | 1008 | 1.3868 | 0.4048 |
| 1.2554 | 37.0 | 1036 | 1.3858 | 0.4048 |
| 1.2838 | 38.0 | 1064 | 1.3848 | 0.4048 |
| 1.2842 | 39.0 | 1092 | 1.3839 | 0.4048 |
| 1.2721 | 40.0 | 1120 | 1.3832 | 0.4048 |
| 1.2562 | 41.0 | 1148 | 1.3826 | 0.4048 |
| 1.2576 | 42.0 | 1176 | 1.3821 | 0.4048 |
| 1.3 | 43.0 | 1204 | 1.3815 | 0.4048 |
| 1.273 | 44.0 | 1232 | 1.3811 | 0.4048 |
| 1.2913 | 45.0 | 1260 | 1.3808 | 0.4048 |
| 1.2814 | 46.0 | 1288 | 1.3806 | 0.4048 |
| 1.2272 | 47.0 | 1316 | 1.3805 | 0.4048 |
| 1.2516 | 48.0 | 1344 | 1.3804 | 0.4048 |
| 1.2555 | 49.0 | 1372 | 1.3804 | 0.4048 |
| 1.3084 | 50.0 | 1400 | 1.3804 | 0.4048 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0