Hugging Face's logo

sudo-s
/
modeversion1_m7_e4

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sudo-s commited on
Commit
455dda4
•
1 Parent(s): 3b5c7eb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +127 -0
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: modeversion1_m7_e4
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
+ # modeversion1_m7_e4
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 the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0902
20
+ - Accuracy: 0.9731
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: 0.0002
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 4
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 4.073 | 0.06 | 100 | 3.9370 | 0.1768 |
53
+ | 3.4186 | 0.12 | 200 | 3.2721 | 0.2590 |
54
+ | 2.6745 | 0.18 | 300 | 2.6465 | 0.3856 |
55
+ | 2.2806 | 0.23 | 400 | 2.2600 | 0.4523 |
56
+ | 1.9275 | 0.29 | 500 | 1.9653 | 0.5109 |
57
+ | 1.6958 | 0.35 | 600 | 1.6815 | 0.6078 |
58
+ | 1.2797 | 0.41 | 700 | 1.4514 | 0.6419 |
59
+ | 1.3772 | 0.47 | 800 | 1.3212 | 0.6762 |
60
+ | 1.1765 | 0.53 | 900 | 1.1476 | 0.7028 |
61
+ | 1.0152 | 0.59 | 1000 | 1.0357 | 0.7313 |
62
+ | 0.7861 | 0.64 | 1100 | 1.0230 | 0.7184 |
63
+ | 1.0262 | 0.7 | 1200 | 0.9469 | 0.7386 |
64
+ | 0.8905 | 0.76 | 1300 | 0.8184 | 0.7756 |
65
+ | 0.6919 | 0.82 | 1400 | 0.8083 | 0.7711 |
66
+ | 0.7494 | 0.88 | 1500 | 0.7601 | 0.7825 |
67
+ | 0.5078 | 0.94 | 1600 | 0.6884 | 0.8056 |
68
+ | 0.7134 | 1.0 | 1700 | 0.6311 | 0.8160 |
69
+ | 0.4328 | 1.06 | 1800 | 0.5740 | 0.8252 |
70
+ | 0.4971 | 1.11 | 1900 | 0.5856 | 0.8290 |
71
+ | 0.5207 | 1.17 | 2000 | 0.6219 | 0.8167 |
72
+ | 0.4027 | 1.23 | 2100 | 0.5703 | 0.8266 |
73
+ | 0.5605 | 1.29 | 2200 | 0.5217 | 0.8372 |
74
+ | 0.2723 | 1.35 | 2300 | 0.4805 | 0.8565 |
75
+ | 0.401 | 1.41 | 2400 | 0.4811 | 0.8490 |
76
+ | 0.3419 | 1.47 | 2500 | 0.4619 | 0.8608 |
77
+ | 0.301 | 1.52 | 2600 | 0.4318 | 0.8712 |
78
+ | 0.2872 | 1.58 | 2700 | 0.4698 | 0.8573 |
79
+ | 0.2451 | 1.64 | 2800 | 0.4210 | 0.8729 |
80
+ | 0.2211 | 1.7 | 2900 | 0.3645 | 0.8851 |
81
+ | 0.3145 | 1.76 | 3000 | 0.4139 | 0.8715 |
82
+ | 0.2001 | 1.82 | 3100 | 0.3605 | 0.8864 |
83
+ | 0.3095 | 1.88 | 3200 | 0.4274 | 0.8675 |
84
+ | 0.1915 | 1.93 | 3300 | 0.2910 | 0.9101 |
85
+ | 0.2465 | 1.99 | 3400 | 0.2726 | 0.9103 |
86
+ | 0.1218 | 2.05 | 3500 | 0.2742 | 0.9129 |
87
+ | 0.0752 | 2.11 | 3600 | 0.2572 | 0.9183 |
88
+ | 0.1067 | 2.17 | 3700 | 0.2584 | 0.9203 |
89
+ | 0.0838 | 2.23 | 3800 | 0.2458 | 0.9212 |
90
+ | 0.1106 | 2.29 | 3900 | 0.2412 | 0.9237 |
91
+ | 0.092 | 2.34 | 4000 | 0.2232 | 0.9277 |
92
+ | 0.1056 | 2.4 | 4100 | 0.2817 | 0.9077 |
93
+ | 0.0696 | 2.46 | 4200 | 0.2334 | 0.9285 |
94
+ | 0.0444 | 2.52 | 4300 | 0.2142 | 0.9363 |
95
+ | 0.1046 | 2.58 | 4400 | 0.2036 | 0.9352 |
96
+ | 0.066 | 2.64 | 4500 | 0.2115 | 0.9365 |
97
+ | 0.0649 | 2.7 | 4600 | 0.1730 | 0.9448 |
98
+ | 0.0513 | 2.75 | 4700 | 0.2148 | 0.9339 |
99
+ | 0.0917 | 2.81 | 4800 | 0.1810 | 0.9438 |
100
+ | 0.0879 | 2.87 | 4900 | 0.1971 | 0.9388 |
101
+ | 0.1052 | 2.93 | 5000 | 0.1602 | 0.9508 |
102
+ | 0.0362 | 2.99 | 5100 | 0.1475 | 0.9556 |
103
+ | 0.041 | 3.05 | 5200 | 0.1328 | 0.9585 |
104
+ | 0.0156 | 3.11 | 5300 | 0.1389 | 0.9571 |
105
+ | 0.0047 | 3.17 | 5400 | 0.1224 | 0.9638 |
106
+ | 0.0174 | 3.22 | 5500 | 0.1193 | 0.9651 |
107
+ | 0.0087 | 3.28 | 5600 | 0.1276 | 0.9622 |
108
+ | 0.0084 | 3.34 | 5700 | 0.1134 | 0.9662 |
109
+ | 0.0141 | 3.4 | 5800 | 0.1239 | 0.9631 |
110
+ | 0.0291 | 3.46 | 5900 | 0.1199 | 0.9645 |
111
+ | 0.0049 | 3.52 | 6000 | 0.1103 | 0.9679 |
112
+ | 0.0055 | 3.58 | 6100 | 0.1120 | 0.9662 |
113
+ | 0.0061 | 3.63 | 6200 | 0.1071 | 0.9668 |
114
+ | 0.0054 | 3.69 | 6300 | 0.1032 | 0.9697 |
115
+ | 0.0041 | 3.75 | 6400 | 0.0961 | 0.9711 |
116
+ | 0.0018 | 3.81 | 6500 | 0.0930 | 0.9718 |
117
+ | 0.0032 | 3.87 | 6600 | 0.0918 | 0.9730 |
118
+ | 0.0048 | 3.93 | 6700 | 0.0906 | 0.9732 |
119
+ | 0.002 | 3.99 | 6800 | 0.0902 | 0.9731 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.20.1
125
+ - Pytorch 1.12.0
126
+ - Datasets 2.3.2
127
+ - Tokenizers 0.12.1