rshrott commited on
Commit
bac8f19
1 Parent(s): a9992a5

Model save

Browse files
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - renovation
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: renovation
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: renovation
18
+ type: renovation
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.7342681258549931
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
+ # renovation
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 renovation dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.1201
36
+ - Accuracy: 0.7343
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: 0.0002
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 4
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.0475 | 0.07 | 100 | 1.0332 | 0.5824 |
69
+ | 0.8651 | 0.14 | 200 | 0.9322 | 0.6204 |
70
+ | 1.0022 | 0.21 | 300 | 1.2150 | 0.5147 |
71
+ | 1.0636 | 0.27 | 400 | 0.9523 | 0.6252 |
72
+ | 0.8311 | 0.34 | 500 | 0.8440 | 0.6556 |
73
+ | 0.88 | 0.41 | 600 | 0.8707 | 0.6495 |
74
+ | 0.8881 | 0.48 | 700 | 0.8903 | 0.6334 |
75
+ | 0.7522 | 0.55 | 800 | 0.8479 | 0.6577 |
76
+ | 0.798 | 0.62 | 900 | 0.7739 | 0.6843 |
77
+ | 0.7317 | 0.68 | 1000 | 0.7856 | 0.6795 |
78
+ | 0.8372 | 0.75 | 1100 | 0.8884 | 0.6354 |
79
+ | 0.6629 | 0.82 | 1200 | 0.7573 | 0.6871 |
80
+ | 0.7767 | 0.89 | 1300 | 0.7543 | 0.6860 |
81
+ | 0.9246 | 0.96 | 1400 | 0.7896 | 0.6635 |
82
+ | 0.5026 | 1.03 | 1500 | 0.7872 | 0.6813 |
83
+ | 0.7599 | 1.1 | 1600 | 0.7861 | 0.6758 |
84
+ | 0.5764 | 1.16 | 1700 | 0.8088 | 0.6802 |
85
+ | 0.4329 | 1.23 | 1800 | 0.7281 | 0.7059 |
86
+ | 0.6271 | 1.3 | 1900 | 0.7291 | 0.7117 |
87
+ | 0.5498 | 1.37 | 2000 | 0.7745 | 0.7059 |
88
+ | 0.5247 | 1.44 | 2100 | 0.8002 | 0.6891 |
89
+ | 0.4891 | 1.51 | 2200 | 0.7014 | 0.7100 |
90
+ | 0.5211 | 1.57 | 2300 | 0.7725 | 0.6864 |
91
+ | 0.659 | 1.64 | 2400 | 0.7477 | 0.7086 |
92
+ | 0.4878 | 1.71 | 2500 | 0.7129 | 0.7052 |
93
+ | 0.4941 | 1.78 | 2600 | 0.6830 | 0.7220 |
94
+ | 0.4648 | 1.85 | 2700 | 0.7182 | 0.7028 |
95
+ | 0.5501 | 1.92 | 2800 | 0.7191 | 0.7144 |
96
+ | 0.5491 | 1.98 | 2900 | 0.7132 | 0.7155 |
97
+ | 0.2373 | 2.05 | 3000 | 0.7831 | 0.7096 |
98
+ | 0.2756 | 2.12 | 3100 | 0.7965 | 0.7247 |
99
+ | 0.2299 | 2.19 | 3200 | 0.8241 | 0.7220 |
100
+ | 0.2323 | 2.26 | 3300 | 0.8286 | 0.7110 |
101
+ | 0.1979 | 2.33 | 3400 | 0.7993 | 0.7302 |
102
+ | 0.2507 | 2.4 | 3500 | 0.8477 | 0.7189 |
103
+ | 0.205 | 2.46 | 3600 | 0.8197 | 0.7124 |
104
+ | 0.35 | 2.53 | 3700 | 0.8348 | 0.7127 |
105
+ | 0.3372 | 2.6 | 3800 | 0.8999 | 0.7199 |
106
+ | 0.1968 | 2.67 | 3900 | 0.8263 | 0.7274 |
107
+ | 0.1443 | 2.74 | 4000 | 0.8704 | 0.7244 |
108
+ | 0.1933 | 2.81 | 4100 | 0.8270 | 0.7244 |
109
+ | 0.2044 | 2.87 | 4200 | 0.8323 | 0.7274 |
110
+ | 0.2709 | 2.94 | 4300 | 0.8494 | 0.7295 |
111
+ | 0.1021 | 3.01 | 4400 | 0.8573 | 0.7336 |
112
+ | 0.0393 | 3.08 | 4500 | 0.9333 | 0.7377 |
113
+ | 0.0973 | 3.15 | 4600 | 0.9646 | 0.7336 |
114
+ | 0.0317 | 3.22 | 4700 | 0.9820 | 0.7336 |
115
+ | 0.0458 | 3.29 | 4800 | 1.0716 | 0.7326 |
116
+ | 0.164 | 3.35 | 4900 | 1.0889 | 0.7312 |
117
+ | 0.0578 | 3.42 | 5000 | 1.1011 | 0.7312 |
118
+ | 0.0563 | 3.49 | 5100 | 1.1010 | 0.7356 |
119
+ | 0.0318 | 3.56 | 5200 | 1.0923 | 0.7343 |
120
+ | 0.0255 | 3.63 | 5300 | 1.1156 | 0.7332 |
121
+ | 0.0169 | 3.7 | 5400 | 1.1050 | 0.7415 |
122
+ | 0.0629 | 3.76 | 5500 | 1.1132 | 0.7373 |
123
+ | 0.0627 | 3.83 | 5600 | 1.1110 | 0.7380 |
124
+ | 0.0078 | 3.9 | 5700 | 1.1117 | 0.7350 |
125
+ | 0.027 | 3.97 | 5800 | 1.1201 | 0.7343 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 4.39.1
131
+ - Pytorch 2.2.1+cu121
132
+ - Datasets 2.18.0
133
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c5ba63a31f26475cdf4d0e2758fe26bc509e85da5ee27a4a98f32cc87cf53de
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3599ec0e707226b7b2f7d71f927b3729f2b6f28095aa1d51efeb39764a1352ae
3
  size 343236280
runs/Mar24_20-47-53_b7cac2bb04d7/events.out.tfevents.1711313274.b7cac2bb04d7.525.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26f417813288bd1c00db3fa3319763b21e09261b0c242df80aa2097f708b231c
3
- size 145792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757d8a05141051603452fbabadb9db0677157c012ec3cc06c0b83666c1aa69d1
3
+ size 146990