Hugging Face's logo

davanstrien
/
test_mae_flysheet

Transformers
PyTorch
TensorBoard
vit_mae
pretraining
masked-auto-encoding
Generated from Trainer
Model card Files
xet
Metrics Community
1
davanstrien HF Staff commited on
Commit
e5cca3e
·
1 Parent(s): a65fc60

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +159 -0
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - image_folder
7
+ model-index:
8
+ - name: test_mae_flysheet
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
+ # test_mae_flysheet
16
+
17
+ This model is a fine-tuned version of [facebook/vit-mae-base](https://huggingface.co/facebook/vit-mae-base) on the image_folder dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2748
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3.75e-05
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
+ - seed: 1337
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_ratio: 0.05
45
+ - num_epochs: 100.0
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 2.284 | 1.0 | 28 | 2.2812 |
53
+ | 2.137 | 2.0 | 56 | 2.0288 |
54
+ | 1.6016 | 3.0 | 84 | 1.2437 |
55
+ | 0.8055 | 4.0 | 112 | 0.7419 |
56
+ | 0.5304 | 5.0 | 140 | 0.5151 |
57
+ | 0.4873 | 6.0 | 168 | 0.4884 |
58
+ | 0.442 | 7.0 | 196 | 0.4441 |
59
+ | 0.4039 | 8.0 | 224 | 0.4159 |
60
+ | 0.3866 | 9.0 | 252 | 0.3975 |
61
+ | 0.391 | 10.0 | 280 | 0.3869 |
62
+ | 0.3549 | 11.0 | 308 | 0.3801 |
63
+ | 0.3462 | 12.0 | 336 | 0.3577 |
64
+ | 0.3402 | 13.0 | 364 | 0.3519 |
65
+ | 0.3357 | 14.0 | 392 | 0.3447 |
66
+ | 0.3474 | 15.0 | 420 | 0.3369 |
67
+ | 0.3254 | 16.0 | 448 | 0.3386 |
68
+ | 0.3033 | 17.0 | 476 | 0.3294 |
69
+ | 0.3047 | 18.0 | 504 | 0.3274 |
70
+ | 0.3103 | 19.0 | 532 | 0.3209 |
71
+ | 0.3067 | 20.0 | 560 | 0.3186 |
72
+ | 0.2959 | 21.0 | 588 | 0.3190 |
73
+ | 0.2899 | 22.0 | 616 | 0.3147 |
74
+ | 0.2872 | 23.0 | 644 | 0.3082 |
75
+ | 0.2956 | 24.0 | 672 | 0.3070 |
76
+ | 0.2865 | 25.0 | 700 | 0.3072 |
77
+ | 0.2947 | 26.0 | 728 | 0.3072 |
78
+ | 0.2811 | 27.0 | 756 | 0.3131 |
79
+ | 0.2935 | 28.0 | 784 | 0.3069 |
80
+ | 0.2814 | 29.0 | 812 | 0.3043 |
81
+ | 0.2753 | 30.0 | 840 | 0.2984 |
82
+ | 0.2823 | 31.0 | 868 | 0.2995 |
83
+ | 0.2962 | 32.0 | 896 | 0.3012 |
84
+ | 0.2869 | 33.0 | 924 | 0.3050 |
85
+ | 0.2833 | 34.0 | 952 | 0.2960 |
86
+ | 0.2892 | 35.0 | 980 | 0.3039 |
87
+ | 0.2764 | 36.0 | 1008 | 0.3010 |
88
+ | 0.2807 | 37.0 | 1036 | 0.2998 |
89
+ | 0.2843 | 38.0 | 1064 | 0.2989 |
90
+ | 0.2808 | 39.0 | 1092 | 0.2970 |
91
+ | 0.2862 | 40.0 | 1120 | 0.2940 |
92
+ | 0.2601 | 41.0 | 1148 | 0.2952 |
93
+ | 0.2742 | 42.0 | 1176 | 0.2940 |
94
+ | 0.2791 | 43.0 | 1204 | 0.2997 |
95
+ | 0.2759 | 44.0 | 1232 | 0.2951 |
96
+ | 0.2819 | 45.0 | 1260 | 0.2896 |
97
+ | 0.287 | 46.0 | 1288 | 0.2938 |
98
+ | 0.2711 | 47.0 | 1316 | 0.2973 |
99
+ | 0.2782 | 48.0 | 1344 | 0.2946 |
100
+ | 0.2674 | 49.0 | 1372 | 0.2913 |
101
+ | 0.268 | 50.0 | 1400 | 0.2944 |
102
+ | 0.2624 | 51.0 | 1428 | 0.2940 |
103
+ | 0.2842 | 52.0 | 1456 | 0.2978 |
104
+ | 0.2753 | 53.0 | 1484 | 0.2951 |
105
+ | 0.2733 | 54.0 | 1512 | 0.2880 |
106
+ | 0.2782 | 55.0 | 1540 | 0.2969 |
107
+ | 0.2789 | 56.0 | 1568 | 0.2919 |
108
+ | 0.2815 | 57.0 | 1596 | 0.2916 |
109
+ | 0.2629 | 58.0 | 1624 | 0.2947 |
110
+ | 0.2716 | 59.0 | 1652 | 0.2828 |
111
+ | 0.2623 | 60.0 | 1680 | 0.2924 |
112
+ | 0.2773 | 61.0 | 1708 | 0.2765 |
113
+ | 0.268 | 62.0 | 1736 | 0.2754 |
114
+ | 0.2839 | 63.0 | 1764 | 0.2744 |
115
+ | 0.2684 | 64.0 | 1792 | 0.2744 |
116
+ | 0.2865 | 65.0 | 1820 | 0.2716 |
117
+ | 0.2845 | 66.0 | 1848 | 0.2769 |
118
+ | 0.2663 | 67.0 | 1876 | 0.2754 |
119
+ | 0.269 | 68.0 | 1904 | 0.2737 |
120
+ | 0.2681 | 69.0 | 1932 | 0.2697 |
121
+ | 0.2748 | 70.0 | 1960 | 0.2779 |
122
+ | 0.2769 | 71.0 | 1988 | 0.2728 |
123
+ | 0.2805 | 72.0 | 2016 | 0.2729 |
124
+ | 0.2771 | 73.0 | 2044 | 0.2728 |
125
+ | 0.2717 | 74.0 | 2072 | 0.2749 |
126
+ | 0.267 | 75.0 | 2100 | 0.2732 |
127
+ | 0.2812 | 76.0 | 2128 | 0.2743 |
128
+ | 0.2749 | 77.0 | 2156 | 0.2739 |
129
+ | 0.2746 | 78.0 | 2184 | 0.2730 |
130
+ | 0.2707 | 79.0 | 2212 | 0.2743 |
131
+ | 0.2644 | 80.0 | 2240 | 0.2740 |
132
+ | 0.2691 | 81.0 | 2268 | 0.2727 |
133
+ | 0.2679 | 82.0 | 2296 | 0.2771 |
134
+ | 0.2748 | 83.0 | 2324 | 0.2744 |
135
+ | 0.2744 | 84.0 | 2352 | 0.2703 |
136
+ | 0.2715 | 85.0 | 2380 | 0.2733 |
137
+ | 0.2682 | 86.0 | 2408 | 0.2715 |
138
+ | 0.2641 | 87.0 | 2436 | 0.2722 |
139
+ | 0.274 | 88.0 | 2464 | 0.2748 |
140
+ | 0.2669 | 89.0 | 2492 | 0.2753 |
141
+ | 0.2707 | 90.0 | 2520 | 0.2724 |
142
+ | 0.2755 | 91.0 | 2548 | 0.2703 |
143
+ | 0.2769 | 92.0 | 2576 | 0.2737 |
144
+ | 0.2659 | 93.0 | 2604 | 0.2721 |
145
+ | 0.2674 | 94.0 | 2632 | 0.2763 |
146
+ | 0.2723 | 95.0 | 2660 | 0.2723 |
147
+ | 0.2723 | 96.0 | 2688 | 0.2744 |
148
+ | 0.272 | 97.0 | 2716 | 0.2686 |
149
+ | 0.27 | 98.0 | 2744 | 0.2728 |
150
+ | 0.2721 | 99.0 | 2772 | 0.2743 |
151
+ | 0.2692 | 100.0 | 2800 | 0.2748 |
152
+
153
+
154
+ ### Framework versions
155
+
156
+ - Transformers 4.18.0.dev0
157
+ - Pytorch 1.10.0+cu111
158
+ - Datasets 1.18.4
159
+ - Tokenizers 0.11.6