update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# V3_Image_classification__points_durs__google_vit-base-patch16-224-in21k
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0411
|
20 |
+
- Accuracy: 0.9927
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 50
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 0.6667 | 1.0 | 15 | 0.5893 | 0.9121 |
|
55 |
+
| 0.4394 | 2.0 | 30 | 0.3294 | 0.9487 |
|
56 |
+
| 0.2685 | 3.0 | 45 | 0.1365 | 0.9707 |
|
57 |
+
| 0.0936 | 4.0 | 60 | 0.0752 | 0.9853 |
|
58 |
+
| 0.0517 | 5.0 | 75 | 0.0553 | 0.9890 |
|
59 |
+
| 0.0436 | 6.0 | 90 | 0.0556 | 0.9890 |
|
60 |
+
| 0.018 | 7.0 | 105 | 0.0557 | 0.9890 |
|
61 |
+
| 0.0189 | 8.0 | 120 | 0.0457 | 0.9890 |
|
62 |
+
| 0.013 | 9.0 | 135 | 0.0343 | 0.9927 |
|
63 |
+
| 0.0115 | 10.0 | 150 | 0.0270 | 0.9963 |
|
64 |
+
| 0.0101 | 11.0 | 165 | 0.0355 | 0.9927 |
|
65 |
+
| 0.0085 | 12.0 | 180 | 0.0356 | 0.9927 |
|
66 |
+
| 0.0079 | 13.0 | 195 | 0.0259 | 0.9963 |
|
67 |
+
| 0.0069 | 14.0 | 210 | 0.0345 | 0.9927 |
|
68 |
+
| 0.0066 | 15.0 | 225 | 0.0360 | 0.9927 |
|
69 |
+
| 0.0061 | 16.0 | 240 | 0.0359 | 0.9927 |
|
70 |
+
| 0.0059 | 17.0 | 255 | 0.0360 | 0.9927 |
|
71 |
+
| 0.0055 | 18.0 | 270 | 0.0368 | 0.9927 |
|
72 |
+
| 0.0054 | 19.0 | 285 | 0.0375 | 0.9927 |
|
73 |
+
| 0.0051 | 20.0 | 300 | 0.0375 | 0.9927 |
|
74 |
+
| 0.0049 | 21.0 | 315 | 0.0380 | 0.9927 |
|
75 |
+
| 0.0047 | 22.0 | 330 | 0.0380 | 0.9927 |
|
76 |
+
| 0.0046 | 23.0 | 345 | 0.0383 | 0.9927 |
|
77 |
+
| 0.0044 | 24.0 | 360 | 0.0386 | 0.9927 |
|
78 |
+
| 0.0043 | 25.0 | 375 | 0.0388 | 0.9927 |
|
79 |
+
| 0.0041 | 26.0 | 390 | 0.0388 | 0.9927 |
|
80 |
+
| 0.0041 | 27.0 | 405 | 0.0391 | 0.9927 |
|
81 |
+
| 0.0039 | 28.0 | 420 | 0.0392 | 0.9927 |
|
82 |
+
| 0.0038 | 29.0 | 435 | 0.0396 | 0.9927 |
|
83 |
+
| 0.0037 | 30.0 | 450 | 0.0397 | 0.9927 |
|
84 |
+
| 0.0037 | 31.0 | 465 | 0.0397 | 0.9927 |
|
85 |
+
| 0.0036 | 32.0 | 480 | 0.0399 | 0.9927 |
|
86 |
+
| 0.0035 | 33.0 | 495 | 0.0401 | 0.9927 |
|
87 |
+
| 0.0034 | 34.0 | 510 | 0.0402 | 0.9927 |
|
88 |
+
| 0.0034 | 35.0 | 525 | 0.0403 | 0.9927 |
|
89 |
+
| 0.0033 | 36.0 | 540 | 0.0403 | 0.9927 |
|
90 |
+
| 0.0033 | 37.0 | 555 | 0.0405 | 0.9927 |
|
91 |
+
| 0.0032 | 38.0 | 570 | 0.0406 | 0.9927 |
|
92 |
+
| 0.0032 | 39.0 | 585 | 0.0406 | 0.9927 |
|
93 |
+
| 0.0031 | 40.0 | 600 | 0.0407 | 0.9927 |
|
94 |
+
| 0.0031 | 41.0 | 615 | 0.0408 | 0.9927 |
|
95 |
+
| 0.0031 | 42.0 | 630 | 0.0408 | 0.9927 |
|
96 |
+
| 0.003 | 43.0 | 645 | 0.0409 | 0.9927 |
|
97 |
+
| 0.003 | 44.0 | 660 | 0.0410 | 0.9927 |
|
98 |
+
| 0.003 | 45.0 | 675 | 0.0410 | 0.9927 |
|
99 |
+
| 0.003 | 46.0 | 690 | 0.0410 | 0.9927 |
|
100 |
+
| 0.003 | 47.0 | 705 | 0.0410 | 0.9927 |
|
101 |
+
| 0.0029 | 48.0 | 720 | 0.0411 | 0.9927 |
|
102 |
+
| 0.0029 | 49.0 | 735 | 0.0411 | 0.9927 |
|
103 |
+
| 0.0029 | 50.0 | 750 | 0.0411 | 0.9927 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.30.0
|
109 |
+
- Pytorch 2.1.1
|
110 |
+
- Datasets 2.15.0
|
111 |
+
- Tokenizers 0.13.3
|