Hugging Face's logo

hkivancoral
/
smids_3x_deit_tiny_sgd_001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
1e85bb5
·
1 Parent(s): bff2bdd

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: facebook/deit-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_tiny_sgd_001_fold1
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: 0.8731218697829716
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_3x_deit_tiny_sgd_001_fold1
32
+
33
+ This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.3078
36
+ - Accuracy: 0.8731
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: 0.001
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
+ | 0.9352 | 1.0 | 226 | 0.9208 | 0.5376 |
69
+ | 0.6928 | 2.0 | 452 | 0.7389 | 0.6861 |
70
+ | 0.5623 | 3.0 | 678 | 0.6105 | 0.7429 |
71
+ | 0.5246 | 4.0 | 904 | 0.5485 | 0.7563 |
72
+ | 0.5426 | 5.0 | 1130 | 0.4979 | 0.7880 |
73
+ | 0.4977 | 6.0 | 1356 | 0.4581 | 0.8080 |
74
+ | 0.3766 | 7.0 | 1582 | 0.4327 | 0.8130 |
75
+ | 0.4038 | 8.0 | 1808 | 0.4167 | 0.8097 |
76
+ | 0.3541 | 9.0 | 2034 | 0.3987 | 0.8431 |
77
+ | 0.3195 | 10.0 | 2260 | 0.3857 | 0.8247 |
78
+ | 0.3215 | 11.0 | 2486 | 0.3815 | 0.8297 |
79
+ | 0.2707 | 12.0 | 2712 | 0.3604 | 0.8414 |
80
+ | 0.2756 | 13.0 | 2938 | 0.3575 | 0.8364 |
81
+ | 0.2853 | 14.0 | 3164 | 0.3492 | 0.8414 |
82
+ | 0.3202 | 15.0 | 3390 | 0.3434 | 0.8447 |
83
+ | 0.3213 | 16.0 | 3616 | 0.3398 | 0.8497 |
84
+ | 0.246 | 17.0 | 3842 | 0.3305 | 0.8581 |
85
+ | 0.2485 | 18.0 | 4068 | 0.3288 | 0.8564 |
86
+ | 0.2691 | 19.0 | 4294 | 0.3315 | 0.8598 |
87
+ | 0.2123 | 20.0 | 4520 | 0.3213 | 0.8648 |
88
+ | 0.2607 | 21.0 | 4746 | 0.3252 | 0.8564 |
89
+ | 0.2646 | 22.0 | 4972 | 0.3186 | 0.8664 |
90
+ | 0.2851 | 23.0 | 5198 | 0.3202 | 0.8631 |
91
+ | 0.2373 | 24.0 | 5424 | 0.3144 | 0.8748 |
92
+ | 0.1908 | 25.0 | 5650 | 0.3143 | 0.8698 |
93
+ | 0.2924 | 26.0 | 5876 | 0.3120 | 0.8698 |
94
+ | 0.1662 | 27.0 | 6102 | 0.3113 | 0.8748 |
95
+ | 0.2215 | 28.0 | 6328 | 0.3120 | 0.8681 |
96
+ | 0.1838 | 29.0 | 6554 | 0.3136 | 0.8698 |
97
+ | 0.2131 | 30.0 | 6780 | 0.3140 | 0.8731 |
98
+ | 0.2074 | 31.0 | 7006 | 0.3100 | 0.8715 |
99
+ | 0.194 | 32.0 | 7232 | 0.3083 | 0.8748 |
100
+ | 0.1635 | 33.0 | 7458 | 0.3091 | 0.8748 |
101
+ | 0.1521 | 34.0 | 7684 | 0.3083 | 0.8748 |
102
+ | 0.2333 | 35.0 | 7910 | 0.3078 | 0.8748 |
103
+ | 0.1942 | 36.0 | 8136 | 0.3076 | 0.8731 |
104
+ | 0.242 | 37.0 | 8362 | 0.3062 | 0.8748 |
105
+ | 0.2131 | 38.0 | 8588 | 0.3090 | 0.8748 |
106
+ | 0.2044 | 39.0 | 8814 | 0.3079 | 0.8748 |
107
+ | 0.1565 | 40.0 | 9040 | 0.3082 | 0.8731 |
108
+ | 0.1709 | 41.0 | 9266 | 0.3089 | 0.8748 |
109
+ | 0.2023 | 42.0 | 9492 | 0.3080 | 0.8748 |
110
+ | 0.2299 | 43.0 | 9718 | 0.3077 | 0.8731 |
111
+ | 0.1365 | 44.0 | 9944 | 0.3081 | 0.8765 |
112
+ | 0.1955 | 45.0 | 10170 | 0.3078 | 0.8748 |
113
+ | 0.2025 | 46.0 | 10396 | 0.3089 | 0.8781 |
114
+ | 0.1982 | 47.0 | 10622 | 0.3076 | 0.8731 |
115
+ | 0.1881 | 48.0 | 10848 | 0.3078 | 0.8731 |
116
+ | 0.1389 | 49.0 | 11074 | 0.3077 | 0.8731 |
117
+ | 0.1646 | 50.0 | 11300 | 0.3078 | 0.8731 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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:e8954c4110cf088ecd6694b7a585892b112d16b5ee732a2a60fa6f4ffbf79c40
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b96d0e69f9d20a6110c335cf879f43dbe84bf542ebb38ef41e01b4d7b63505
3
  size 22167850