Model save
Browse files
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: vit-base-patch16-224-finetuned-context-classifier
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: test
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8187702265372169
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# vit-base-patch16-224-finetuned-context-classifier
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.7157
|
36 |
+
- Accuracy: 0.8188
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 128
|
57 |
+
- eval_batch_size: 128
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 512
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 100
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.3586 | 2.0 | 10 | 1.2322 | 0.3916 |
|
71 |
+
| 1.0841 | 4.0 | 20 | 0.8444 | 0.6958 |
|
72 |
+
| 0.7282 | 6.0 | 30 | 0.5498 | 0.7767 |
|
73 |
+
| 0.4768 | 8.0 | 40 | 0.4273 | 0.8155 |
|
74 |
+
| 0.3332 | 10.0 | 50 | 0.4059 | 0.8220 |
|
75 |
+
| 0.242 | 12.0 | 60 | 0.4272 | 0.8252 |
|
76 |
+
| 0.1737 | 14.0 | 70 | 0.4372 | 0.8188 |
|
77 |
+
| 0.1266 | 16.0 | 80 | 0.4495 | 0.8123 |
|
78 |
+
| 0.1089 | 18.0 | 90 | 0.4877 | 0.8091 |
|
79 |
+
| 0.0837 | 20.0 | 100 | 0.5318 | 0.8058 |
|
80 |
+
| 0.0687 | 22.0 | 110 | 0.5300 | 0.7961 |
|
81 |
+
| 0.0667 | 24.0 | 120 | 0.6253 | 0.7994 |
|
82 |
+
| 0.0581 | 26.0 | 130 | 0.5495 | 0.8220 |
|
83 |
+
| 0.0574 | 28.0 | 140 | 0.5646 | 0.8188 |
|
84 |
+
| 0.0564 | 30.0 | 150 | 0.5990 | 0.8252 |
|
85 |
+
| 0.0492 | 32.0 | 160 | 0.6436 | 0.8155 |
|
86 |
+
| 0.0406 | 34.0 | 170 | 0.6225 | 0.8091 |
|
87 |
+
| 0.0411 | 36.0 | 180 | 0.6168 | 0.8123 |
|
88 |
+
| 0.0381 | 38.0 | 190 | 0.6731 | 0.8123 |
|
89 |
+
| 0.0358 | 40.0 | 200 | 0.6198 | 0.7961 |
|
90 |
+
| 0.0354 | 42.0 | 210 | 0.6216 | 0.8091 |
|
91 |
+
| 0.0358 | 44.0 | 220 | 0.6933 | 0.8091 |
|
92 |
+
| 0.037 | 46.0 | 230 | 0.6488 | 0.8188 |
|
93 |
+
| 0.0344 | 48.0 | 240 | 0.6546 | 0.8220 |
|
94 |
+
| 0.0335 | 50.0 | 250 | 0.6399 | 0.7994 |
|
95 |
+
| 0.0297 | 52.0 | 260 | 0.6553 | 0.8123 |
|
96 |
+
| 0.0318 | 54.0 | 270 | 0.6996 | 0.7896 |
|
97 |
+
| 0.0254 | 56.0 | 280 | 0.6809 | 0.7961 |
|
98 |
+
| 0.0322 | 58.0 | 290 | 0.7048 | 0.7896 |
|
99 |
+
| 0.024 | 60.0 | 300 | 0.6869 | 0.8123 |
|
100 |
+
| 0.0255 | 62.0 | 310 | 0.7099 | 0.8058 |
|
101 |
+
| 0.0266 | 64.0 | 320 | 0.6894 | 0.8091 |
|
102 |
+
| 0.0243 | 66.0 | 330 | 0.7604 | 0.8091 |
|
103 |
+
| 0.0232 | 68.0 | 340 | 0.6983 | 0.8123 |
|
104 |
+
| 0.019 | 70.0 | 350 | 0.6834 | 0.8091 |
|
105 |
+
| 0.0235 | 72.0 | 360 | 0.7102 | 0.8091 |
|
106 |
+
| 0.0262 | 74.0 | 370 | 0.6902 | 0.8155 |
|
107 |
+
| 0.0206 | 76.0 | 380 | 0.6662 | 0.8091 |
|
108 |
+
| 0.0238 | 78.0 | 390 | 0.7109 | 0.8220 |
|
109 |
+
| 0.0202 | 80.0 | 400 | 0.7061 | 0.8058 |
|
110 |
+
| 0.0204 | 82.0 | 410 | 0.7291 | 0.8155 |
|
111 |
+
| 0.0231 | 84.0 | 420 | 0.7103 | 0.8091 |
|
112 |
+
| 0.0217 | 86.0 | 430 | 0.7050 | 0.8123 |
|
113 |
+
| 0.021 | 88.0 | 440 | 0.7037 | 0.8155 |
|
114 |
+
| 0.0207 | 90.0 | 450 | 0.6996 | 0.8058 |
|
115 |
+
| 0.0163 | 92.0 | 460 | 0.7137 | 0.8091 |
|
116 |
+
| 0.0181 | 94.0 | 470 | 0.7153 | 0.8155 |
|
117 |
+
| 0.0225 | 96.0 | 480 | 0.7105 | 0.8123 |
|
118 |
+
| 0.0185 | 98.0 | 490 | 0.7140 | 0.8155 |
|
119 |
+
| 0.0219 | 100.0 | 500 | 0.7157 | 0.8188 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.35.0
|
125 |
+
- Pytorch 2.1.0+cu121
|
126 |
+
- Datasets 2.14.4
|
127 |
+
- Tokenizers 0.14.1
|