Model save
Browse files
README.md
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/vit-base-patch16-224
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: vit-base-oxford-iiit-pets
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# vit-base-oxford-iiit-pets
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1798
|
22 |
+
- Accuracy: 0.9310
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0003
|
42 |
+
- train_batch_size: 512
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 100
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| No log | 1.0 | 12 | 2.6101 | 0.5223 |
|
54 |
+
| No log | 2.0 | 24 | 1.7190 | 0.8227 |
|
55 |
+
| No log | 3.0 | 36 | 1.0833 | 0.8890 |
|
56 |
+
| No log | 4.0 | 48 | 0.7011 | 0.9120 |
|
57 |
+
| No log | 5.0 | 60 | 0.5052 | 0.9242 |
|
58 |
+
| No log | 6.0 | 72 | 0.4097 | 0.9310 |
|
59 |
+
| No log | 7.0 | 84 | 0.3560 | 0.9350 |
|
60 |
+
| No log | 8.0 | 96 | 0.3237 | 0.9337 |
|
61 |
+
| 1.1364 | 9.0 | 108 | 0.3008 | 0.9378 |
|
62 |
+
| 1.1364 | 10.0 | 120 | 0.2833 | 0.9364 |
|
63 |
+
| 1.1364 | 11.0 | 132 | 0.2694 | 0.9391 |
|
64 |
+
| 1.1364 | 12.0 | 144 | 0.2586 | 0.9391 |
|
65 |
+
| 1.1364 | 13.0 | 156 | 0.2498 | 0.9418 |
|
66 |
+
| 1.1364 | 14.0 | 168 | 0.2423 | 0.9405 |
|
67 |
+
| 1.1364 | 15.0 | 180 | 0.2359 | 0.9405 |
|
68 |
+
| 1.1364 | 16.0 | 192 | 0.2303 | 0.9459 |
|
69 |
+
| 0.2326 | 17.0 | 204 | 0.2259 | 0.9405 |
|
70 |
+
| 0.2326 | 18.0 | 216 | 0.2222 | 0.9405 |
|
71 |
+
| 0.2326 | 19.0 | 228 | 0.2178 | 0.9432 |
|
72 |
+
| 0.2326 | 20.0 | 240 | 0.2146 | 0.9445 |
|
73 |
+
| 0.2326 | 21.0 | 252 | 0.2114 | 0.9432 |
|
74 |
+
| 0.2326 | 22.0 | 264 | 0.2087 | 0.9445 |
|
75 |
+
| 0.2326 | 23.0 | 276 | 0.2061 | 0.9432 |
|
76 |
+
| 0.2326 | 24.0 | 288 | 0.2040 | 0.9459 |
|
77 |
+
| 0.1651 | 25.0 | 300 | 0.2018 | 0.9459 |
|
78 |
+
| 0.1651 | 26.0 | 312 | 0.2000 | 0.9445 |
|
79 |
+
| 0.1651 | 27.0 | 324 | 0.1985 | 0.9459 |
|
80 |
+
| 0.1651 | 28.0 | 336 | 0.1968 | 0.9472 |
|
81 |
+
| 0.1651 | 29.0 | 348 | 0.1948 | 0.9459 |
|
82 |
+
| 0.1651 | 30.0 | 360 | 0.1939 | 0.9459 |
|
83 |
+
| 0.1651 | 31.0 | 372 | 0.1924 | 0.9459 |
|
84 |
+
| 0.1651 | 32.0 | 384 | 0.1915 | 0.9459 |
|
85 |
+
| 0.1651 | 33.0 | 396 | 0.1909 | 0.9459 |
|
86 |
+
| 0.134 | 34.0 | 408 | 0.1894 | 0.9472 |
|
87 |
+
| 0.134 | 35.0 | 420 | 0.1883 | 0.9459 |
|
88 |
+
| 0.134 | 36.0 | 432 | 0.1877 | 0.9472 |
|
89 |
+
| 0.134 | 37.0 | 444 | 0.1866 | 0.9486 |
|
90 |
+
| 0.134 | 38.0 | 456 | 0.1863 | 0.9472 |
|
91 |
+
| 0.134 | 39.0 | 468 | 0.1851 | 0.9486 |
|
92 |
+
| 0.134 | 40.0 | 480 | 0.1843 | 0.9472 |
|
93 |
+
| 0.134 | 41.0 | 492 | 0.1837 | 0.9472 |
|
94 |
+
| 0.1128 | 42.0 | 504 | 0.1831 | 0.9459 |
|
95 |
+
| 0.1128 | 43.0 | 516 | 0.1828 | 0.9472 |
|
96 |
+
| 0.1128 | 44.0 | 528 | 0.1822 | 0.9472 |
|
97 |
+
| 0.1128 | 45.0 | 540 | 0.1816 | 0.9472 |
|
98 |
+
| 0.1128 | 46.0 | 552 | 0.1808 | 0.9459 |
|
99 |
+
| 0.1128 | 47.0 | 564 | 0.1804 | 0.9459 |
|
100 |
+
| 0.1128 | 48.0 | 576 | 0.1802 | 0.9459 |
|
101 |
+
| 0.1128 | 49.0 | 588 | 0.1796 | 0.9459 |
|
102 |
+
| 0.0999 | 50.0 | 600 | 0.1793 | 0.9472 |
|
103 |
+
| 0.0999 | 51.0 | 612 | 0.1792 | 0.9486 |
|
104 |
+
| 0.0999 | 52.0 | 624 | 0.1787 | 0.9472 |
|
105 |
+
| 0.0999 | 53.0 | 636 | 0.1784 | 0.9472 |
|
106 |
+
| 0.0999 | 54.0 | 648 | 0.1780 | 0.9459 |
|
107 |
+
| 0.0999 | 55.0 | 660 | 0.1778 | 0.9445 |
|
108 |
+
| 0.0999 | 56.0 | 672 | 0.1772 | 0.9445 |
|
109 |
+
| 0.0999 | 57.0 | 684 | 0.1769 | 0.9472 |
|
110 |
+
| 0.0999 | 58.0 | 696 | 0.1768 | 0.9472 |
|
111 |
+
| 0.0894 | 59.0 | 708 | 0.1766 | 0.9472 |
|
112 |
+
| 0.0894 | 60.0 | 720 | 0.1763 | 0.9472 |
|
113 |
+
| 0.0894 | 61.0 | 732 | 0.1762 | 0.9486 |
|
114 |
+
| 0.0894 | 62.0 | 744 | 0.1760 | 0.9472 |
|
115 |
+
| 0.0894 | 63.0 | 756 | 0.1755 | 0.9459 |
|
116 |
+
| 0.0894 | 64.0 | 768 | 0.1752 | 0.9459 |
|
117 |
+
| 0.0894 | 65.0 | 780 | 0.1749 | 0.9459 |
|
118 |
+
| 0.0894 | 66.0 | 792 | 0.1749 | 0.9459 |
|
119 |
+
| 0.0828 | 67.0 | 804 | 0.1746 | 0.9472 |
|
120 |
+
| 0.0828 | 68.0 | 816 | 0.1745 | 0.9459 |
|
121 |
+
| 0.0828 | 69.0 | 828 | 0.1745 | 0.9459 |
|
122 |
+
| 0.0828 | 70.0 | 840 | 0.1744 | 0.9459 |
|
123 |
+
| 0.0828 | 71.0 | 852 | 0.1740 | 0.9459 |
|
124 |
+
| 0.0828 | 72.0 | 864 | 0.1741 | 0.9459 |
|
125 |
+
| 0.0828 | 73.0 | 876 | 0.1737 | 0.9459 |
|
126 |
+
| 0.0828 | 74.0 | 888 | 0.1739 | 0.9459 |
|
127 |
+
| 0.0778 | 75.0 | 900 | 0.1739 | 0.9459 |
|
128 |
+
| 0.0778 | 76.0 | 912 | 0.1737 | 0.9459 |
|
129 |
+
| 0.0778 | 77.0 | 924 | 0.1735 | 0.9459 |
|
130 |
+
| 0.0778 | 78.0 | 936 | 0.1733 | 0.9459 |
|
131 |
+
| 0.0778 | 79.0 | 948 | 0.1732 | 0.9459 |
|
132 |
+
| 0.0778 | 80.0 | 960 | 0.1732 | 0.9459 |
|
133 |
+
| 0.0778 | 81.0 | 972 | 0.1730 | 0.9459 |
|
134 |
+
| 0.0778 | 82.0 | 984 | 0.1730 | 0.9459 |
|
135 |
+
| 0.0778 | 83.0 | 996 | 0.1730 | 0.9459 |
|
136 |
+
| 0.0738 | 84.0 | 1008 | 0.1729 | 0.9459 |
|
137 |
+
| 0.0738 | 85.0 | 1020 | 0.1727 | 0.9459 |
|
138 |
+
| 0.0738 | 86.0 | 1032 | 0.1726 | 0.9459 |
|
139 |
+
| 0.0738 | 87.0 | 1044 | 0.1726 | 0.9459 |
|
140 |
+
| 0.0738 | 88.0 | 1056 | 0.1726 | 0.9459 |
|
141 |
+
| 0.0738 | 89.0 | 1068 | 0.1726 | 0.9459 |
|
142 |
+
| 0.0738 | 90.0 | 1080 | 0.1725 | 0.9459 |
|
143 |
+
| 0.0738 | 91.0 | 1092 | 0.1724 | 0.9459 |
|
144 |
+
| 0.0715 | 92.0 | 1104 | 0.1724 | 0.9459 |
|
145 |
+
| 0.0715 | 93.0 | 1116 | 0.1723 | 0.9459 |
|
146 |
+
| 0.0715 | 94.0 | 1128 | 0.1723 | 0.9459 |
|
147 |
+
| 0.0715 | 95.0 | 1140 | 0.1723 | 0.9459 |
|
148 |
+
| 0.0715 | 96.0 | 1152 | 0.1722 | 0.9459 |
|
149 |
+
| 0.0715 | 97.0 | 1164 | 0.1722 | 0.9459 |
|
150 |
+
| 0.0715 | 98.0 | 1176 | 0.1722 | 0.9459 |
|
151 |
+
| 0.0715 | 99.0 | 1188 | 0.1722 | 0.9459 |
|
152 |
+
| 0.0701 | 100.0 | 1200 | 0.1722 | 0.9459 |
|
153 |
+
|
154 |
+
|
155 |
+
### Framework versions
|
156 |
+
|
157 |
+
- Transformers 4.44.2
|
158 |
+
- Pytorch 2.4.1
|
159 |
+
- Datasets 3.0.0
|
160 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343331644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e5785ac8ad0f75bac802f90cb1536aed4239fec93f59278c4ab8cdd01b9a77a
|
3 |
size 343331644
|
runs/Sep13_12-47-50_UOL-PBWS1004455/events.out.tfevents.1726228074.UOL-PBWS1004455.40332.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e52b805f51a9a94d52b15270f9fdab3fe446587cd6e0b2864f73aafd91dfe6
|
3 |
+
size 41801
|
runs/Sep13_12-47-50_UOL-PBWS1004455/events.out.tfevents.1726231264.UOL-PBWS1004455.40332.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b292e3a456f3ea1f91f57fd0c34d2097e000d6078b119d8fac3e9e956ab18df
|
3 |
+
size 411
|