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: V4_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 |
+
# V4_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: 0.2221
|
20 |
+
- Accuracy: 0.9560
|
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 |
+
| 0.6743 | 1.0 | 13 | 0.6315 | 0.7566 |
|
55 |
+
| 0.6051 | 2.0 | 26 | 0.4384 | 0.9150 |
|
56 |
+
| 0.4588 | 3.0 | 39 | 0.2402 | 0.9326 |
|
57 |
+
| 0.1818 | 4.0 | 52 | 0.1702 | 0.9384 |
|
58 |
+
| 0.1102 | 5.0 | 65 | 0.1409 | 0.9413 |
|
59 |
+
| 0.0733 | 6.0 | 78 | 0.1516 | 0.9501 |
|
60 |
+
| 0.0423 | 7.0 | 91 | 0.1613 | 0.9560 |
|
61 |
+
| 0.0286 | 8.0 | 104 | 0.1843 | 0.9501 |
|
62 |
+
| 0.0192 | 9.0 | 117 | 0.1672 | 0.9560 |
|
63 |
+
| 0.0159 | 10.0 | 130 | 0.1703 | 0.9589 |
|
64 |
+
| 0.0173 | 11.0 | 143 | 0.1729 | 0.9560 |
|
65 |
+
| 0.0143 | 12.0 | 156 | 0.1786 | 0.9560 |
|
66 |
+
| 0.0105 | 13.0 | 169 | 0.1821 | 0.9560 |
|
67 |
+
| 0.0091 | 14.0 | 182 | 0.1827 | 0.9589 |
|
68 |
+
| 0.0096 | 15.0 | 195 | 0.1859 | 0.9560 |
|
69 |
+
| 0.0081 | 16.0 | 208 | 0.1989 | 0.9560 |
|
70 |
+
| 0.0075 | 17.0 | 221 | 0.2012 | 0.9560 |
|
71 |
+
| 0.0347 | 18.0 | 234 | 0.2507 | 0.9384 |
|
72 |
+
| 0.0232 | 19.0 | 247 | 0.2271 | 0.9413 |
|
73 |
+
| 0.0065 | 20.0 | 260 | 0.1950 | 0.9589 |
|
74 |
+
| 0.0102 | 21.0 | 273 | 0.2378 | 0.9472 |
|
75 |
+
| 0.0064 | 22.0 | 286 | 0.2265 | 0.9501 |
|
76 |
+
| 0.0058 | 23.0 | 299 | 0.2033 | 0.9560 |
|
77 |
+
| 0.0055 | 24.0 | 312 | 0.2402 | 0.9501 |
|
78 |
+
| 0.005 | 25.0 | 325 | 0.2500 | 0.9443 |
|
79 |
+
| 0.0054 | 26.0 | 338 | 0.2450 | 0.9472 |
|
80 |
+
| 0.0048 | 27.0 | 351 | 0.2431 | 0.9501 |
|
81 |
+
| 0.0047 | 28.0 | 364 | 0.2439 | 0.9472 |
|
82 |
+
| 0.0046 | 29.0 | 377 | 0.2445 | 0.9472 |
|
83 |
+
| 0.0044 | 30.0 | 390 | 0.2434 | 0.9472 |
|
84 |
+
| 0.0042 | 31.0 | 403 | 0.2441 | 0.9472 |
|
85 |
+
| 0.0042 | 32.0 | 416 | 0.2426 | 0.9472 |
|
86 |
+
| 0.0042 | 33.0 | 429 | 0.2414 | 0.9472 |
|
87 |
+
| 0.004 | 34.0 | 442 | 0.2383 | 0.9472 |
|
88 |
+
| 0.004 | 35.0 | 455 | 0.2349 | 0.9472 |
|
89 |
+
| 0.0039 | 36.0 | 468 | 0.2340 | 0.9472 |
|
90 |
+
| 0.0038 | 37.0 | 481 | 0.2325 | 0.9472 |
|
91 |
+
| 0.0037 | 38.0 | 494 | 0.2311 | 0.9501 |
|
92 |
+
| 0.0038 | 39.0 | 507 | 0.2280 | 0.9501 |
|
93 |
+
| 0.0037 | 40.0 | 520 | 0.2263 | 0.9531 |
|
94 |
+
| 0.0036 | 41.0 | 533 | 0.2248 | 0.9531 |
|
95 |
+
| 0.0036 | 42.0 | 546 | 0.2242 | 0.9531 |
|
96 |
+
| 0.0036 | 43.0 | 559 | 0.2236 | 0.9531 |
|
97 |
+
| 0.0035 | 44.0 | 572 | 0.2231 | 0.9560 |
|
98 |
+
| 0.0035 | 45.0 | 585 | 0.2224 | 0.9560 |
|
99 |
+
| 0.0035 | 46.0 | 598 | 0.2223 | 0.9560 |
|
100 |
+
| 0.0035 | 47.0 | 611 | 0.2220 | 0.9560 |
|
101 |
+
| 0.0035 | 48.0 | 624 | 0.2221 | 0.9560 |
|
102 |
+
| 0.0034 | 49.0 | 637 | 0.2221 | 0.9560 |
|
103 |
+
| 0.0035 | 50.0 | 650 | 0.2221 | 0.9560 |
|
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
|