update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: raildefectfft2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
config: Dhika--defectfft
|
| 19 |
+
split: validation
|
| 20 |
+
args: Dhika--defectfft
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.7485714285714286
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# raildefectfft2
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 1.2327
|
| 35 |
+
- Accuracy: 0.7486
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 0.0002
|
| 55 |
+
- train_batch_size: 30
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 30
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 66 |
+
| 1.3922 | 0.67 | 10 | 1.1690 | 0.6114 |
|
| 67 |
+
| 0.8518 | 1.33 | 20 | 0.8874 | 0.6829 |
|
| 68 |
+
| 0.5386 | 2.0 | 30 | 0.7207 | 0.7543 |
|
| 69 |
+
| 0.3125 | 2.67 | 40 | 0.8383 | 0.7286 |
|
| 70 |
+
| 0.2264 | 3.33 | 50 | 0.8440 | 0.7429 |
|
| 71 |
+
| 0.1613 | 4.0 | 60 | 0.8516 | 0.7457 |
|
| 72 |
+
| 0.119 | 4.67 | 70 | 1.3625 | 0.6 |
|
| 73 |
+
| 0.0972 | 5.33 | 80 | 0.9110 | 0.7429 |
|
| 74 |
+
| 0.0844 | 6.0 | 90 | 0.8272 | 0.78 |
|
| 75 |
+
| 0.0725 | 6.67 | 100 | 0.8958 | 0.74 |
|
| 76 |
+
| 0.0708 | 7.33 | 110 | 1.0972 | 0.7371 |
|
| 77 |
+
| 0.041 | 8.0 | 120 | 1.0089 | 0.7629 |
|
| 78 |
+
| 0.0312 | 8.67 | 130 | 1.0348 | 0.7629 |
|
| 79 |
+
| 0.0401 | 9.33 | 140 | 1.2427 | 0.7257 |
|
| 80 |
+
| 0.0271 | 10.0 | 150 | 1.0154 | 0.7543 |
|
| 81 |
+
| 0.0328 | 10.67 | 160 | 1.0373 | 0.7714 |
|
| 82 |
+
| 0.023 | 11.33 | 170 | 1.0051 | 0.7686 |
|
| 83 |
+
| 0.0199 | 12.0 | 180 | 0.9775 | 0.7657 |
|
| 84 |
+
| 0.0189 | 12.67 | 190 | 1.0088 | 0.7657 |
|
| 85 |
+
| 0.0188 | 13.33 | 200 | 1.1904 | 0.7343 |
|
| 86 |
+
| 0.0167 | 14.0 | 210 | 1.2999 | 0.7286 |
|
| 87 |
+
| 0.0159 | 14.67 | 220 | 1.1326 | 0.7514 |
|
| 88 |
+
| 0.0145 | 15.33 | 230 | 1.1386 | 0.7543 |
|
| 89 |
+
| 0.015 | 16.0 | 240 | 1.1441 | 0.7543 |
|
| 90 |
+
| 0.0133 | 16.67 | 250 | 1.1544 | 0.7514 |
|
| 91 |
+
| 0.0132 | 17.33 | 260 | 1.1629 | 0.7514 |
|
| 92 |
+
| 0.0121 | 18.0 | 270 | 1.1708 | 0.7514 |
|
| 93 |
+
| 0.0121 | 18.67 | 280 | 1.1773 | 0.7514 |
|
| 94 |
+
| 0.0114 | 19.33 | 290 | 1.1831 | 0.7514 |
|
| 95 |
+
| 0.0111 | 20.0 | 300 | 1.1883 | 0.7514 |
|
| 96 |
+
| 0.011 | 20.67 | 310 | 1.1937 | 0.7514 |
|
| 97 |
+
| 0.0103 | 21.33 | 320 | 1.1993 | 0.7514 |
|
| 98 |
+
| 0.0103 | 22.0 | 330 | 1.2046 | 0.7514 |
|
| 99 |
+
| 0.0103 | 22.67 | 340 | 1.2089 | 0.7514 |
|
| 100 |
+
| 0.0096 | 23.33 | 350 | 1.2133 | 0.7514 |
|
| 101 |
+
| 0.0095 | 24.0 | 360 | 1.2171 | 0.7514 |
|
| 102 |
+
| 0.0096 | 24.67 | 370 | 1.2204 | 0.7514 |
|
| 103 |
+
| 0.0093 | 25.33 | 380 | 1.2235 | 0.7486 |
|
| 104 |
+
| 0.0091 | 26.0 | 390 | 1.2262 | 0.7486 |
|
| 105 |
+
| 0.0092 | 26.67 | 400 | 1.2280 | 0.7514 |
|
| 106 |
+
| 0.0089 | 27.33 | 410 | 1.2296 | 0.7514 |
|
| 107 |
+
| 0.0092 | 28.0 | 420 | 1.2310 | 0.7514 |
|
| 108 |
+
| 0.0089 | 28.67 | 430 | 1.2319 | 0.7486 |
|
| 109 |
+
| 0.0089 | 29.33 | 440 | 1.2325 | 0.7486 |
|
| 110 |
+
| 0.0088 | 30.0 | 450 | 1.2327 | 0.7486 |
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
### Framework versions
|
| 114 |
+
|
| 115 |
+
- Transformers 4.30.2
|
| 116 |
+
- Pytorch 2.0.1+cu118
|
| 117 |
+
- Datasets 2.12.0
|
| 118 |
+
- Tokenizers 0.13.3
|