Sabrina Bottazzi
commited on
Commit
·
83749b0
1
Parent(s):
234f153
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: 8-classifier-finetuned-padchest
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
config: default
|
| 19 |
+
split: train
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: F1
|
| 23 |
+
type: f1
|
| 24 |
+
value: 0.9325359911406422
|
| 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 |
+
# 8-classifier-finetuned-padchest
|
| 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: 0.2276
|
| 35 |
+
- F1: 0.9325
|
| 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: 5e-05
|
| 55 |
+
- train_batch_size: 32
|
| 56 |
+
- eval_batch_size: 32
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 128
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
+
- num_epochs: 50
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 69 |
+
| 0.6321 | 1.0 | 18 | 0.5224 | 0.7896 |
|
| 70 |
+
| 0.4633 | 2.0 | 36 | 0.3809 | 0.7896 |
|
| 71 |
+
| 0.3552 | 3.0 | 54 | 0.3305 | 0.7896 |
|
| 72 |
+
| 0.2718 | 4.0 | 72 | 0.2696 | 0.8197 |
|
| 73 |
+
| 0.2345 | 5.0 | 90 | 0.2178 | 0.9149 |
|
| 74 |
+
| 0.211 | 6.0 | 108 | 0.2405 | 0.8861 |
|
| 75 |
+
| 0.2208 | 7.0 | 126 | 0.2713 | 0.8605 |
|
| 76 |
+
| 0.1698 | 8.0 | 144 | 0.1747 | 0.9422 |
|
| 77 |
+
| 0.1547 | 9.0 | 162 | 0.1783 | 0.9322 |
|
| 78 |
+
| 0.1697 | 10.0 | 180 | 0.1629 | 0.9350 |
|
| 79 |
+
| 0.1684 | 11.0 | 198 | 0.1740 | 0.9319 |
|
| 80 |
+
| 0.1722 | 12.0 | 216 | 0.1885 | 0.9173 |
|
| 81 |
+
| 0.158 | 13.0 | 234 | 0.1637 | 0.9331 |
|
| 82 |
+
| 0.1469 | 14.0 | 252 | 0.1716 | 0.9325 |
|
| 83 |
+
| 0.1271 | 15.0 | 270 | 0.1700 | 0.9384 |
|
| 84 |
+
| 0.131 | 16.0 | 288 | 0.1785 | 0.9409 |
|
| 85 |
+
| 0.1245 | 17.0 | 306 | 0.2124 | 0.9206 |
|
| 86 |
+
| 0.1182 | 18.0 | 324 | 0.1715 | 0.9322 |
|
| 87 |
+
| 0.1082 | 19.0 | 342 | 0.1946 | 0.9322 |
|
| 88 |
+
| 0.1274 | 20.0 | 360 | 0.1757 | 0.9379 |
|
| 89 |
+
| 0.1115 | 21.0 | 378 | 0.1908 | 0.9307 |
|
| 90 |
+
| 0.0995 | 22.0 | 396 | 0.2001 | 0.9289 |
|
| 91 |
+
| 0.0996 | 23.0 | 414 | 0.1820 | 0.9293 |
|
| 92 |
+
| 0.0993 | 24.0 | 432 | 0.2095 | 0.9355 |
|
| 93 |
+
| 0.1006 | 25.0 | 450 | 0.1973 | 0.9314 |
|
| 94 |
+
| 0.0703 | 26.0 | 468 | 0.1934 | 0.9389 |
|
| 95 |
+
| 0.0901 | 27.0 | 486 | 0.2276 | 0.9238 |
|
| 96 |
+
| 0.0827 | 28.0 | 504 | 0.1949 | 0.936 |
|
| 97 |
+
| 0.0701 | 29.0 | 522 | 0.2076 | 0.9317 |
|
| 98 |
+
| 0.0813 | 30.0 | 540 | 0.2001 | 0.9374 |
|
| 99 |
+
| 0.0776 | 31.0 | 558 | 0.2440 | 0.9357 |
|
| 100 |
+
| 0.0842 | 32.0 | 576 | 0.2163 | 0.9271 |
|
| 101 |
+
| 0.0872 | 33.0 | 594 | 0.2248 | 0.9332 |
|
| 102 |
+
| 0.0743 | 34.0 | 612 | 0.2007 | 0.9344 |
|
| 103 |
+
| 0.0692 | 35.0 | 630 | 0.1971 | 0.9283 |
|
| 104 |
+
| 0.0763 | 36.0 | 648 | 0.2094 | 0.9393 |
|
| 105 |
+
| 0.0714 | 37.0 | 666 | 0.2139 | 0.9271 |
|
| 106 |
+
| 0.0683 | 38.0 | 684 | 0.2065 | 0.9331 |
|
| 107 |
+
| 0.0698 | 39.0 | 702 | 0.2177 | 0.9295 |
|
| 108 |
+
| 0.0507 | 40.0 | 720 | 0.2171 | 0.9344 |
|
| 109 |
+
| 0.0523 | 41.0 | 738 | 0.2240 | 0.9344 |
|
| 110 |
+
| 0.0546 | 42.0 | 756 | 0.2083 | 0.9394 |
|
| 111 |
+
| 0.0695 | 43.0 | 774 | 0.2171 | 0.936 |
|
| 112 |
+
| 0.0634 | 44.0 | 792 | 0.2193 | 0.9301 |
|
| 113 |
+
| 0.0462 | 45.0 | 810 | 0.2017 | 0.9409 |
|
| 114 |
+
| 0.0581 | 46.0 | 828 | 0.2209 | 0.9350 |
|
| 115 |
+
| 0.0468 | 47.0 | 846 | 0.2335 | 0.9301 |
|
| 116 |
+
| 0.0424 | 48.0 | 864 | 0.2294 | 0.9301 |
|
| 117 |
+
| 0.0472 | 49.0 | 882 | 0.2310 | 0.9350 |
|
| 118 |
+
| 0.044 | 50.0 | 900 | 0.2276 | 0.9325 |
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
### Framework versions
|
| 122 |
+
|
| 123 |
+
- Transformers 4.28.0.dev0
|
| 124 |
+
- Pytorch 2.0.0+cu117
|
| 125 |
+
- Datasets 2.18.0
|
| 126 |
+
- Tokenizers 0.13.3
|