Hugging Face's logo

hkivancoral
/
smids_5x_beit_base_sgd_00001_fold5

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
0851e80
•
1 Parent(s): 4f4d567

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_5x_beit_base_sgd_00001_fold5
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.40166666666666667
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
+ # smids_5x_beit_base_sgd_00001_fold5
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.1301
36
+ - Accuracy: 0.4017
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: 1e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 50
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 1.2159 | 1.0 | 375 | 1.3104 | 0.3133 |
69
+ | 1.2415 | 2.0 | 750 | 1.3020 | 0.3233 |
70
+ | 1.2057 | 3.0 | 1125 | 1.2939 | 0.3233 |
71
+ | 1.176 | 4.0 | 1500 | 1.2863 | 0.3267 |
72
+ | 1.2191 | 5.0 | 1875 | 1.2790 | 0.3267 |
73
+ | 1.1863 | 6.0 | 2250 | 1.2719 | 0.3333 |
74
+ | 1.2037 | 7.0 | 2625 | 1.2651 | 0.34 |
75
+ | 1.177 | 8.0 | 3000 | 1.2586 | 0.3483 |
76
+ | 1.1576 | 9.0 | 3375 | 1.2521 | 0.35 |
77
+ | 1.0865 | 10.0 | 3750 | 1.2459 | 0.3517 |
78
+ | 1.1578 | 11.0 | 4125 | 1.2399 | 0.3533 |
79
+ | 1.1516 | 12.0 | 4500 | 1.2341 | 0.355 |
80
+ | 1.1216 | 13.0 | 4875 | 1.2282 | 0.355 |
81
+ | 1.1365 | 14.0 | 5250 | 1.2228 | 0.3583 |
82
+ | 1.1282 | 15.0 | 5625 | 1.2175 | 0.3583 |
83
+ | 1.1187 | 16.0 | 6000 | 1.2123 | 0.3633 |
84
+ | 1.1048 | 17.0 | 6375 | 1.2074 | 0.365 |
85
+ | 1.1548 | 18.0 | 6750 | 1.2025 | 0.365 |
86
+ | 1.1271 | 19.0 | 7125 | 1.1978 | 0.3683 |
87
+ | 1.1003 | 20.0 | 7500 | 1.1934 | 0.3717 |
88
+ | 1.0771 | 21.0 | 7875 | 1.1891 | 0.3733 |
89
+ | 1.0833 | 22.0 | 8250 | 1.1849 | 0.3767 |
90
+ | 1.1002 | 23.0 | 8625 | 1.1809 | 0.3783 |
91
+ | 1.0994 | 24.0 | 9000 | 1.1772 | 0.3833 |
92
+ | 1.0715 | 25.0 | 9375 | 1.1735 | 0.385 |
93
+ | 1.1029 | 26.0 | 9750 | 1.1700 | 0.3867 |
94
+ | 1.1056 | 27.0 | 10125 | 1.1666 | 0.3867 |
95
+ | 1.022 | 28.0 | 10500 | 1.1633 | 0.3883 |
96
+ | 1.0343 | 29.0 | 10875 | 1.1602 | 0.3867 |
97
+ | 1.0325 | 30.0 | 11250 | 1.1573 | 0.3883 |
98
+ | 1.0378 | 31.0 | 11625 | 1.1546 | 0.3883 |
99
+ | 1.0659 | 32.0 | 12000 | 1.1519 | 0.3867 |
100
+ | 1.0282 | 33.0 | 12375 | 1.1495 | 0.3867 |
101
+ | 1.0519 | 34.0 | 12750 | 1.1472 | 0.3883 |
102
+ | 1.0399 | 35.0 | 13125 | 1.1451 | 0.3883 |
103
+ | 1.0632 | 36.0 | 13500 | 1.1430 | 0.39 |
104
+ | 1.015 | 37.0 | 13875 | 1.1411 | 0.39 |
105
+ | 1.0714 | 38.0 | 14250 | 1.1394 | 0.39 |
106
+ | 0.9921 | 39.0 | 14625 | 1.1379 | 0.3917 |
107
+ | 1.0391 | 40.0 | 15000 | 1.1365 | 0.3917 |
108
+ | 1.0121 | 41.0 | 15375 | 1.1352 | 0.395 |
109
+ | 1.0675 | 42.0 | 15750 | 1.1341 | 0.3967 |
110
+ | 1.0815 | 43.0 | 16125 | 1.1331 | 0.3967 |
111
+ | 1.0054 | 44.0 | 16500 | 1.1322 | 0.3967 |
112
+ | 1.0674 | 45.0 | 16875 | 1.1316 | 0.3983 |
113
+ | 1.0115 | 46.0 | 17250 | 1.1310 | 0.4 |
114
+ | 1.0426 | 47.0 | 17625 | 1.1306 | 0.4017 |
115
+ | 1.0416 | 48.0 | 18000 | 1.1303 | 0.4017 |
116
+ | 1.0297 | 49.0 | 18375 | 1.1302 | 0.4017 |
117
+ | 1.0431 | 50.0 | 18750 | 1.1301 | 0.4017 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0ae6e48487abee91599724ff69731a4768c01c61c5204241306f4c44eb76aa6
3
  size 343133766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5906f5edf45f46d10783d09c82515322d5bd586f1e2053b1b161785ddefcf8ce
3
  size 343133766