metadata
library_name: transformers
license: apache-2.0
base_model: facebook/vit-msn-small
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-msn-small-wbc-blur-detector
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: 0.9456521739130435
vit-msn-small-wbc-blur-detector
This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3181
- Accuracy: 0.9457
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 3 | 0.6142 | 0.6304 |
| No log | 2.0 | 6 | 0.3853 | 0.8696 |
| No log | 3.0 | 9 | 0.4070 | 0.8261 |
| 0.494 | 4.0 | 12 | 0.1461 | 0.9348 |
| 0.494 | 5.0 | 15 | 0.1189 | 0.9565 |
| 0.494 | 6.0 | 18 | 0.1527 | 0.9457 |
| 0.2024 | 7.0 | 21 | 0.3323 | 0.9022 |
| 0.2024 | 8.0 | 24 | 0.1520 | 0.9457 |
| 0.2024 | 9.0 | 27 | 0.1572 | 0.9457 |
| 0.1419 | 10.0 | 30 | 0.1814 | 0.9348 |
| 0.1419 | 11.0 | 33 | 0.1778 | 0.9348 |
| 0.1419 | 12.0 | 36 | 0.1505 | 0.9348 |
| 0.1419 | 13.0 | 39 | 0.1891 | 0.9457 |
| 0.1053 | 14.0 | 42 | 0.7274 | 0.7935 |
| 0.1053 | 15.0 | 45 | 0.2669 | 0.9348 |
| 0.1053 | 16.0 | 48 | 0.2240 | 0.9348 |
| 0.3044 | 17.0 | 51 | 0.3497 | 0.8913 |
| 0.3044 | 18.0 | 54 | 0.2208 | 0.9348 |
| 0.3044 | 19.0 | 57 | 0.1733 | 0.9565 |
| 0.151 | 20.0 | 60 | 0.2038 | 0.9239 |
| 0.151 | 21.0 | 63 | 0.1282 | 0.9565 |
| 0.151 | 22.0 | 66 | 0.3231 | 0.9239 |
| 0.151 | 23.0 | 69 | 0.1565 | 0.9565 |
| 0.0875 | 24.0 | 72 | 0.1981 | 0.9457 |
| 0.0875 | 25.0 | 75 | 0.1974 | 0.9457 |
| 0.0875 | 26.0 | 78 | 0.2045 | 0.9457 |
| 0.0851 | 27.0 | 81 | 0.1841 | 0.9457 |
| 0.0851 | 28.0 | 84 | 0.2061 | 0.9565 |
| 0.0851 | 29.0 | 87 | 0.2077 | 0.9457 |
| 0.046 | 30.0 | 90 | 0.2199 | 0.9565 |
| 0.046 | 31.0 | 93 | 0.2038 | 0.9565 |
| 0.046 | 32.0 | 96 | 0.2077 | 0.9457 |
| 0.046 | 33.0 | 99 | 0.1877 | 0.9565 |
| 0.0533 | 34.0 | 102 | 0.2383 | 0.9348 |
| 0.0533 | 35.0 | 105 | 0.2571 | 0.9239 |
| 0.0533 | 36.0 | 108 | 0.2330 | 0.9565 |
| 0.0451 | 37.0 | 111 | 0.2420 | 0.9457 |
| 0.0451 | 38.0 | 114 | 0.2882 | 0.9239 |
| 0.0451 | 39.0 | 117 | 0.2386 | 0.9457 |
| 0.0401 | 40.0 | 120 | 0.2513 | 0.9348 |
| 0.0401 | 41.0 | 123 | 0.2672 | 0.9348 |
| 0.0401 | 42.0 | 126 | 0.2950 | 0.9457 |
| 0.0401 | 43.0 | 129 | 0.3232 | 0.9457 |
| 0.0329 | 44.0 | 132 | 0.3712 | 0.9239 |
| 0.0329 | 45.0 | 135 | 0.3529 | 0.9348 |
| 0.0329 | 46.0 | 138 | 0.2905 | 0.9457 |
| 0.0519 | 47.0 | 141 | 0.2670 | 0.9457 |
| 0.0519 | 48.0 | 144 | 0.2629 | 0.9457 |
| 0.0519 | 49.0 | 147 | 0.2761 | 0.9457 |
| 0.0281 | 50.0 | 150 | 0.3040 | 0.9457 |
| 0.0281 | 51.0 | 153 | 0.3191 | 0.9457 |
| 0.0281 | 52.0 | 156 | 0.3214 | 0.9457 |
| 0.0281 | 53.0 | 159 | 0.3132 | 0.9457 |
| 0.028 | 54.0 | 162 | 0.3115 | 0.9457 |
| 0.028 | 55.0 | 165 | 0.3116 | 0.9565 |
| 0.028 | 56.0 | 168 | 0.3225 | 0.9457 |
| 0.0361 | 57.0 | 171 | 0.3235 | 0.9457 |
| 0.0361 | 58.0 | 174 | 0.3200 | 0.9457 |
| 0.0361 | 59.0 | 177 | 0.3183 | 0.9457 |
| 0.0312 | 60.0 | 180 | 0.3181 | 0.9457 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1