Hugging Face's logo

sudo-s
/
new_exper3

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
sudo-s commited on
Commit
f54f344
·
1 Parent(s): 65fc21a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: new_exper3
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
+ # new_exper3
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: 0.3068
20
+ - Accuracy: 0.9318
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: 0.0001
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: 8
46
+ - mixed_precision_training: Apex, opt level O1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 4.093 | 0.16 | 100 | 4.1045 | 0.1885 |
53
+ | 3.5057 | 0.31 | 200 | 3.4448 | 0.3231 |
54
+ | 2.9116 | 0.47 | 300 | 2.9483 | 0.4537 |
55
+ | 2.561 | 0.63 | 400 | 2.5700 | 0.5258 |
56
+ | 2.1611 | 0.78 | 500 | 2.1721 | 0.6145 |
57
+ | 1.715 | 0.94 | 600 | 1.8255 | 0.6407 |
58
+ | 1.2752 | 1.1 | 700 | 1.5340 | 0.7051 |
59
+ | 1.2487 | 1.25 | 800 | 1.3533 | 0.7201 |
60
+ | 1.0333 | 1.41 | 900 | 1.1474 | 0.7826 |
61
+ | 0.8856 | 1.56 | 1000 | 1.0914 | 0.7645 |
62
+ | 0.7512 | 1.72 | 1100 | 0.8893 | 0.8119 |
63
+ | 0.747 | 1.88 | 1200 | 0.8370 | 0.8304 |
64
+ | 0.5082 | 2.03 | 1300 | 0.7131 | 0.8566 |
65
+ | 0.4449 | 2.19 | 1400 | 0.6573 | 0.8547 |
66
+ | 0.2912 | 2.35 | 1500 | 0.6184 | 0.8597 |
67
+ | 0.285 | 2.5 | 1600 | 0.5974 | 0.8570 |
68
+ | 0.2267 | 2.66 | 1700 | 0.5621 | 0.8647 |
69
+ | 0.2553 | 2.82 | 1800 | 0.5044 | 0.8816 |
70
+ | 0.2029 | 2.97 | 1900 | 0.4342 | 0.8955 |
71
+ | 0.1763 | 3.13 | 2000 | 0.4487 | 0.8905 |
72
+ | 0.1418 | 3.29 | 2100 | 0.4173 | 0.9005 |
73
+ | 0.0563 | 3.44 | 2200 | 0.3870 | 0.9048 |
74
+ | 0.0579 | 3.6 | 2300 | 0.3849 | 0.9036 |
75
+ | 0.166 | 3.76 | 2400 | 0.3933 | 0.9025 |
76
+ | 0.11 | 3.91 | 2500 | 0.3918 | 0.9056 |
77
+ | 0.0356 | 4.07 | 2600 | 0.3298 | 0.9202 |
78
+ | 0.0513 | 4.23 | 2700 | 0.3371 | 0.9210 |
79
+ | 0.0762 | 4.38 | 2800 | 0.3253 | 0.9225 |
80
+ | 0.018 | 4.54 | 2900 | 0.3467 | 0.9148 |
81
+ | 0.0263 | 4.69 | 3000 | 0.3544 | 0.9144 |
82
+ | 0.0205 | 4.85 | 3100 | 0.3340 | 0.9221 |
83
+ | 0.0237 | 5.01 | 3200 | 0.3353 | 0.9144 |
84
+ | 0.013 | 5.16 | 3300 | 0.3218 | 0.9229 |
85
+ | 0.0116 | 5.32 | 3400 | 0.3088 | 0.9291 |
86
+ | 0.0119 | 5.48 | 3500 | 0.3047 | 0.9279 |
87
+ | 0.0098 | 5.63 | 3600 | 0.3063 | 0.9283 |
88
+ | 0.0086 | 5.79 | 3700 | 0.3074 | 0.9268 |
89
+ | 0.0081 | 5.95 | 3800 | 0.3220 | 0.9237 |
90
+ | 0.0078 | 6.1 | 3900 | 0.3064 | 0.9268 |
91
+ | 0.0074 | 6.26 | 4000 | 0.3062 | 0.9279 |
92
+ | 0.0068 | 6.42 | 4100 | 0.3051 | 0.9291 |
93
+ | 0.006 | 6.57 | 4200 | 0.3000 | 0.9298 |
94
+ | 0.0075 | 6.73 | 4300 | 0.3010 | 0.9310 |
95
+ | 0.0057 | 6.89 | 4400 | 0.3037 | 0.9298 |
96
+ | 0.0058 | 7.04 | 4500 | 0.3071 | 0.9279 |
97
+ | 0.0075 | 7.2 | 4600 | 0.3075 | 0.9283 |
98
+ | 0.0066 | 7.36 | 4700 | 0.3077 | 0.9295 |
99
+ | 0.0056 | 7.51 | 4800 | 0.3084 | 0.9295 |
100
+ | 0.0053 | 7.67 | 4900 | 0.3064 | 0.9310 |
101
+ | 0.0057 | 7.82 | 5000 | 0.3068 | 0.9318 |
102
+ | 0.0055 | 7.98 | 5100 | 0.3068 | 0.9318 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.19.4
108
+ - Pytorch 1.5.1
109
+ - Datasets 2.3.2
110
+ - Tokenizers 0.12.1