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_rms_001_fold5
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: 0.34146341463414637
hushem_5x_beit_base_rms_001_fold5
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: 2.4962
- Accuracy: 0.3415
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 |
|---|---|---|---|---|
| 1.501 | 1.0 | 28 | 1.3919 | 0.2439 |
| 1.3993 | 2.0 | 56 | 1.4008 | 0.2683 |
| 1.4258 | 3.0 | 84 | 1.4098 | 0.2439 |
| 1.4011 | 4.0 | 112 | 1.3674 | 0.2683 |
| 1.4153 | 5.0 | 140 | 1.3306 | 0.2683 |
| 1.3649 | 6.0 | 168 | 1.4784 | 0.2195 |
| 1.3525 | 7.0 | 196 | 1.2906 | 0.4390 |
| 1.3374 | 8.0 | 224 | 1.1798 | 0.5122 |
| 1.2661 | 9.0 | 252 | 1.3479 | 0.5122 |
| 1.3011 | 10.0 | 280 | 1.3054 | 0.4878 |
| 1.2212 | 11.0 | 308 | 1.1612 | 0.5122 |
| 1.2579 | 12.0 | 336 | 1.2572 | 0.2683 |
| 1.2438 | 13.0 | 364 | 1.1160 | 0.4634 |
| 1.2218 | 14.0 | 392 | 1.1291 | 0.4878 |
| 1.2455 | 15.0 | 420 | 1.4587 | 0.4390 |
| 1.2528 | 16.0 | 448 | 1.3009 | 0.5122 |
| 1.2445 | 17.0 | 476 | 1.1915 | 0.5122 |
| 1.1729 | 18.0 | 504 | 1.3461 | 0.4390 |
| 1.2917 | 19.0 | 532 | 1.3956 | 0.3659 |
| 1.2335 | 20.0 | 560 | 1.1161 | 0.4146 |
| 1.1787 | 21.0 | 588 | 1.4220 | 0.4390 |
| 1.1076 | 22.0 | 616 | 1.2157 | 0.5122 |
| 1.1837 | 23.0 | 644 | 1.2878 | 0.4634 |
| 1.065 | 24.0 | 672 | 1.3373 | 0.3659 |
| 1.0753 | 25.0 | 700 | 1.2968 | 0.4634 |
| 1.0288 | 26.0 | 728 | 1.2996 | 0.4146 |
| 1.0679 | 27.0 | 756 | 1.2975 | 0.3902 |
| 1.0591 | 28.0 | 784 | 1.3051 | 0.4634 |
| 1.0148 | 29.0 | 812 | 1.2575 | 0.5854 |
| 1.0668 | 30.0 | 840 | 1.3174 | 0.3415 |
| 0.9767 | 31.0 | 868 | 1.3259 | 0.4390 |
| 0.9254 | 32.0 | 896 | 1.3236 | 0.4878 |
| 0.9064 | 33.0 | 924 | 1.5265 | 0.3902 |
| 0.9504 | 34.0 | 952 | 1.2456 | 0.4390 |
| 0.8534 | 35.0 | 980 | 1.2811 | 0.5122 |
| 0.8361 | 36.0 | 1008 | 1.2101 | 0.6098 |
| 0.7846 | 37.0 | 1036 | 1.3727 | 0.4390 |
| 0.7661 | 38.0 | 1064 | 1.4030 | 0.4878 |
| 0.8237 | 39.0 | 1092 | 1.3385 | 0.4634 |
| 0.7652 | 40.0 | 1120 | 1.6174 | 0.4146 |
| 0.6764 | 41.0 | 1148 | 1.6358 | 0.4390 |
| 0.5675 | 42.0 | 1176 | 1.7675 | 0.4390 |
| 0.5777 | 43.0 | 1204 | 1.8573 | 0.4390 |
| 0.5704 | 44.0 | 1232 | 2.0252 | 0.3902 |
| 0.5677 | 45.0 | 1260 | 2.0725 | 0.3902 |
| 0.4676 | 46.0 | 1288 | 2.4159 | 0.3171 |
| 0.4167 | 47.0 | 1316 | 2.4083 | 0.3415 |
| 0.416 | 48.0 | 1344 | 2.4826 | 0.3415 |
| 0.3715 | 49.0 | 1372 | 2.4962 | 0.3415 |
| 0.368 | 50.0 | 1400 | 2.4962 | 0.3415 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0