Hugging Face's logo

bmedeiros
/
vit-msn-base-finetuned-lf-invalidation

Image Classification
Transformers
TensorBoard
Safetensors
vit_msn
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bmedeiros commited on
Commit
ef1d5bb
·
verified ·
1 Parent(s): 1bd47f1

Model save

Browse files
Files changed (2) hide show
  1. README.md +155 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/vit-msn-base
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: vit-msn-base-finetuned-lf-invalidation
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: test
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.7617021276595745
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # vit-msn-base-finetuned-lf-invalidation
33
+
34
+ This model is a fine-tuned version of [facebook/vit-msn-base](https://huggingface.co/facebook/vit-msn-base) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.5346
37
+ - Accuracy: 0.7617
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 32
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 128
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 80
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | No log | 0.96 | 6 | 0.6512 | 0.6957 |
72
+ | 0.7053 | 1.92 | 12 | 0.6311 | 0.6809 |
73
+ | 0.7053 | 2.88 | 18 | 0.5361 | 0.7277 |
74
+ | 0.5163 | 4.0 | 25 | 0.3341 | 0.8681 |
75
+ | 0.3242 | 4.96 | 31 | 0.3167 | 0.8809 |
76
+ | 0.3242 | 5.92 | 37 | 0.3960 | 0.8191 |
77
+ | 0.2779 | 6.88 | 43 | 0.3818 | 0.8255 |
78
+ | 0.2348 | 8.0 | 50 | 0.5019 | 0.7362 |
79
+ | 0.2348 | 8.96 | 56 | 0.2944 | 0.8851 |
80
+ | 0.26 | 9.92 | 62 | 0.2414 | 0.9234 |
81
+ | 0.26 | 10.88 | 68 | 0.3664 | 0.8298 |
82
+ | 0.2778 | 12.0 | 75 | 0.2505 | 0.9043 |
83
+ | 0.2271 | 12.96 | 81 | 0.6277 | 0.6298 |
84
+ | 0.2271 | 13.92 | 87 | 0.2753 | 0.8745 |
85
+ | 0.2488 | 14.88 | 93 | 0.6249 | 0.6957 |
86
+ | 0.2729 | 16.0 | 100 | 0.5195 | 0.7149 |
87
+ | 0.2729 | 16.96 | 106 | 0.7984 | 0.5745 |
88
+ | 0.3261 | 17.92 | 112 | 0.4631 | 0.7723 |
89
+ | 0.3261 | 18.88 | 118 | 1.1010 | 0.5149 |
90
+ | 0.2212 | 20.0 | 125 | 0.2337 | 0.9170 |
91
+ | 0.2802 | 20.96 | 131 | 0.4638 | 0.7574 |
92
+ | 0.2802 | 21.92 | 137 | 0.3859 | 0.8362 |
93
+ | 0.2112 | 22.88 | 143 | 0.6708 | 0.6894 |
94
+ | 0.2231 | 24.0 | 150 | 0.3387 | 0.8681 |
95
+ | 0.2231 | 24.96 | 156 | 0.7045 | 0.6553 |
96
+ | 0.2037 | 25.92 | 162 | 0.3958 | 0.8277 |
97
+ | 0.2037 | 26.88 | 168 | 0.5082 | 0.7702 |
98
+ | 0.1845 | 28.0 | 175 | 0.5991 | 0.7234 |
99
+ | 0.1898 | 28.96 | 181 | 0.5108 | 0.7617 |
100
+ | 0.1898 | 29.92 | 187 | 0.2720 | 0.9085 |
101
+ | 0.2118 | 30.88 | 193 | 0.4936 | 0.7851 |
102
+ | 0.2097 | 32.0 | 200 | 0.3748 | 0.8404 |
103
+ | 0.2097 | 32.96 | 206 | 0.5048 | 0.7766 |
104
+ | 0.1704 | 33.92 | 212 | 0.4368 | 0.7957 |
105
+ | 0.1704 | 34.88 | 218 | 0.6959 | 0.6830 |
106
+ | 0.1962 | 36.0 | 225 | 1.0097 | 0.5957 |
107
+ | 0.1686 | 36.96 | 231 | 0.4992 | 0.7915 |
108
+ | 0.1686 | 37.92 | 237 | 0.5374 | 0.7574 |
109
+ | 0.1855 | 38.88 | 243 | 0.3710 | 0.8340 |
110
+ | 0.1528 | 40.0 | 250 | 0.3631 | 0.8447 |
111
+ | 0.1528 | 40.96 | 256 | 0.5589 | 0.7681 |
112
+ | 0.1523 | 41.92 | 262 | 0.5147 | 0.7809 |
113
+ | 0.1523 | 42.88 | 268 | 0.5299 | 0.7638 |
114
+ | 0.1709 | 44.0 | 275 | 0.5937 | 0.7447 |
115
+ | 0.1527 | 44.96 | 281 | 0.5969 | 0.7383 |
116
+ | 0.1527 | 45.92 | 287 | 0.6439 | 0.7255 |
117
+ | 0.1397 | 46.88 | 293 | 0.7721 | 0.6723 |
118
+ | 0.1538 | 48.0 | 300 | 0.5768 | 0.7702 |
119
+ | 0.1538 | 48.96 | 306 | 0.5801 | 0.7596 |
120
+ | 0.1466 | 49.92 | 312 | 0.5673 | 0.7574 |
121
+ | 0.1466 | 50.88 | 318 | 0.6469 | 0.7085 |
122
+ | 0.1302 | 52.0 | 325 | 0.7276 | 0.6957 |
123
+ | 0.1565 | 52.96 | 331 | 0.8247 | 0.6723 |
124
+ | 0.1565 | 53.92 | 337 | 0.4811 | 0.7979 |
125
+ | 0.1267 | 54.88 | 343 | 0.6373 | 0.7021 |
126
+ | 0.1424 | 56.0 | 350 | 0.7252 | 0.6723 |
127
+ | 0.1424 | 56.96 | 356 | 0.5697 | 0.7489 |
128
+ | 0.1053 | 57.92 | 362 | 0.7067 | 0.6957 |
129
+ | 0.1053 | 58.88 | 368 | 0.6577 | 0.7064 |
130
+ | 0.1301 | 60.0 | 375 | 0.5326 | 0.7745 |
131
+ | 0.0906 | 60.96 | 381 | 0.5468 | 0.7851 |
132
+ | 0.0906 | 61.92 | 387 | 0.4413 | 0.8277 |
133
+ | 0.0974 | 62.88 | 393 | 0.5479 | 0.7660 |
134
+ | 0.1133 | 64.0 | 400 | 0.7109 | 0.7043 |
135
+ | 0.1133 | 64.96 | 406 | 0.5735 | 0.7617 |
136
+ | 0.1189 | 65.92 | 412 | 0.4084 | 0.8298 |
137
+ | 0.1189 | 66.88 | 418 | 0.5716 | 0.7489 |
138
+ | 0.1064 | 68.0 | 425 | 0.5537 | 0.7553 |
139
+ | 0.1084 | 68.96 | 431 | 0.4569 | 0.8021 |
140
+ | 0.1084 | 69.92 | 437 | 0.5227 | 0.7617 |
141
+ | 0.1054 | 70.88 | 443 | 0.5995 | 0.7277 |
142
+ | 0.1005 | 72.0 | 450 | 0.5560 | 0.7638 |
143
+ | 0.1005 | 72.96 | 456 | 0.4550 | 0.8064 |
144
+ | 0.1028 | 73.92 | 462 | 0.4404 | 0.8234 |
145
+ | 0.1028 | 74.88 | 468 | 0.4761 | 0.7957 |
146
+ | 0.0917 | 76.0 | 475 | 0.5278 | 0.7681 |
147
+ | 0.1009 | 76.8 | 480 | 0.5346 | 0.7617 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.44.2
153
+ - Pytorch 2.4.1+cu121
154
+ - Datasets 3.2.0
155
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cc2af5d06570b6aafaee0de97f036d1d0c5d64827fa3006cdd52cb569e25936
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c7fd926b9d89b0f98ba0590e99733de09a2ea1157e773ce4d52822154b2ea5c
3
  size 343223968