Hugging Face's logo

moreover18
/
hf_images_model1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
moreover18 commited on
Commit
ee409d0
•
1 Parent(s): 44cce29

End of training

Browse files
Files changed (1) hide show
  1. README.md +146 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - image_folder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hf_images_model1
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: image_folder
18
+ type: image_folder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9178265524625268
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
+ # hf_images_model1
32
+
33
+ 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 image_folder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2058
36
+ - Accuracy: 0.9178
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: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
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: 3
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.7057 | 0.04 | 10 | 0.7027 | 0.4644 |
71
+ | 0.6808 | 0.09 | 20 | 0.6615 | 0.6590 |
72
+ | 0.6278 | 0.13 | 30 | 0.5969 | 0.7441 |
73
+ | 0.5674 | 0.17 | 40 | 0.5134 | 0.8183 |
74
+ | 0.4761 | 0.21 | 50 | 0.4146 | 0.875 |
75
+ | 0.3777 | 0.26 | 60 | 0.3362 | 0.8796 |
76
+ | 0.303 | 0.3 | 70 | 0.2906 | 0.8854 |
77
+ | 0.2385 | 0.34 | 80 | 0.2694 | 0.8937 |
78
+ | 0.2452 | 0.39 | 90 | 0.2515 | 0.9012 |
79
+ | 0.2771 | 0.43 | 100 | 0.2441 | 0.9050 |
80
+ | 0.2332 | 0.47 | 110 | 0.2510 | 0.8975 |
81
+ | 0.2495 | 0.51 | 120 | 0.2398 | 0.9052 |
82
+ | 0.2611 | 0.56 | 130 | 0.2384 | 0.9063 |
83
+ | 0.2292 | 0.6 | 140 | 0.2931 | 0.8865 |
84
+ | 0.2518 | 0.64 | 150 | 0.2537 | 0.8994 |
85
+ | 0.211 | 0.69 | 160 | 0.2619 | 0.8953 |
86
+ | 0.2514 | 0.73 | 170 | 0.2236 | 0.9090 |
87
+ | 0.2272 | 0.77 | 180 | 0.2254 | 0.9085 |
88
+ | 0.2263 | 0.81 | 190 | 0.2141 | 0.9181 |
89
+ | 0.2524 | 0.86 | 200 | 0.2038 | 0.9194 |
90
+ | 0.2024 | 0.9 | 210 | 0.2038 | 0.9165 |
91
+ | 0.2355 | 0.94 | 220 | 0.2215 | 0.9103 |
92
+ | 0.2431 | 0.99 | 230 | 0.2116 | 0.9178 |
93
+ | 0.1921 | 1.03 | 240 | 0.2105 | 0.9111 |
94
+ | 0.1845 | 1.07 | 250 | 0.2107 | 0.9117 |
95
+ | 0.1838 | 1.11 | 260 | 0.2070 | 0.9119 |
96
+ | 0.1824 | 1.16 | 270 | 0.2110 | 0.9130 |
97
+ | 0.1706 | 1.2 | 280 | 0.2177 | 0.9154 |
98
+ | 0.1826 | 1.24 | 290 | 0.2058 | 0.9160 |
99
+ | 0.1816 | 1.28 | 300 | 0.2081 | 0.9176 |
100
+ | 0.1901 | 1.33 | 310 | 0.2187 | 0.9149 |
101
+ | 0.2112 | 1.37 | 320 | 0.2107 | 0.9181 |
102
+ | 0.22 | 1.41 | 330 | 0.2065 | 0.9173 |
103
+ | 0.2105 | 1.46 | 340 | 0.2090 | 0.9170 |
104
+ | 0.2016 | 1.5 | 350 | 0.2044 | 0.9141 |
105
+ | 0.2055 | 1.54 | 360 | 0.2029 | 0.9173 |
106
+ | 0.1507 | 1.58 | 370 | 0.2103 | 0.9192 |
107
+ | 0.1705 | 1.63 | 380 | 0.1960 | 0.9184 |
108
+ | 0.1605 | 1.67 | 390 | 0.2070 | 0.9154 |
109
+ | 0.2011 | 1.71 | 400 | 0.2096 | 0.9160 |
110
+ | 0.1832 | 1.76 | 410 | 0.2023 | 0.9176 |
111
+ | 0.1756 | 1.8 | 420 | 0.2005 | 0.9189 |
112
+ | 0.1874 | 1.84 | 430 | 0.2050 | 0.9135 |
113
+ | 0.1497 | 1.88 | 440 | 0.1936 | 0.9240 |
114
+ | 0.1891 | 1.93 | 450 | 0.1991 | 0.9208 |
115
+ | 0.1595 | 1.97 | 460 | 0.2014 | 0.9194 |
116
+ | 0.2028 | 2.01 | 470 | 0.1994 | 0.9184 |
117
+ | 0.1794 | 2.06 | 480 | 0.2068 | 0.9146 |
118
+ | 0.1404 | 2.1 | 490 | 0.2046 | 0.9181 |
119
+ | 0.1615 | 2.14 | 500 | 0.1955 | 0.9243 |
120
+ | 0.1555 | 2.18 | 510 | 0.2027 | 0.9202 |
121
+ | 0.151 | 2.23 | 520 | 0.1893 | 0.9261 |
122
+ | 0.1676 | 2.27 | 530 | 0.2046 | 0.9192 |
123
+ | 0.1744 | 2.31 | 540 | 0.1967 | 0.9218 |
124
+ | 0.1644 | 2.36 | 550 | 0.1970 | 0.9226 |
125
+ | 0.2048 | 2.4 | 560 | 0.1930 | 0.9243 |
126
+ | 0.1649 | 2.44 | 570 | 0.1986 | 0.9218 |
127
+ | 0.1435 | 2.48 | 580 | 0.1956 | 0.9213 |
128
+ | 0.1598 | 2.53 | 590 | 0.1986 | 0.9197 |
129
+ | 0.1513 | 2.57 | 600 | 0.2020 | 0.9173 |
130
+ | 0.1769 | 2.61 | 610 | 0.2005 | 0.9170 |
131
+ | 0.1488 | 2.66 | 620 | 0.2033 | 0.9197 |
132
+ | 0.1636 | 2.7 | 630 | 0.1964 | 0.9216 |
133
+ | 0.1583 | 2.74 | 640 | 0.1985 | 0.9189 |
134
+ | 0.1294 | 2.78 | 650 | 0.2109 | 0.9151 |
135
+ | 0.1585 | 2.83 | 660 | 0.2000 | 0.9186 |
136
+ | 0.1531 | 2.87 | 670 | 0.2078 | 0.9178 |
137
+ | 0.1294 | 2.91 | 680 | 0.1891 | 0.9272 |
138
+ | 0.1612 | 2.96 | 690 | 0.2058 | 0.9178 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.33.0
144
+ - Pytorch 2.0.0
145
+ - Datasets 2.1.0
146
+ - Tokenizers 0.13.3