Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_00001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
d0a6439
•
1 Parent(s): e36026f

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +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_1x_deit_tiny_sgd_00001_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: 0.38898163606010017
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_1x_deit_tiny_sgd_00001_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: 1.1750
36
+ - Accuracy: 0.3890
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
+ | 1.3532 | 1.0 | 76 | 1.3243 | 0.3506 |
69
+ | 1.4232 | 2.0 | 152 | 1.3155 | 0.3489 |
70
+ | 1.3221 | 3.0 | 228 | 1.3073 | 0.3489 |
71
+ | 1.3312 | 4.0 | 304 | 1.2992 | 0.3489 |
72
+ | 1.2834 | 5.0 | 380 | 1.2918 | 0.3539 |
73
+ | 1.3512 | 6.0 | 456 | 1.2848 | 0.3573 |
74
+ | 1.3029 | 7.0 | 532 | 1.2778 | 0.3573 |
75
+ | 1.3216 | 8.0 | 608 | 1.2712 | 0.3606 |
76
+ | 1.2731 | 9.0 | 684 | 1.2652 | 0.3656 |
77
+ | 1.2932 | 10.0 | 760 | 1.2593 | 0.3639 |
78
+ | 1.3065 | 11.0 | 836 | 1.2537 | 0.3606 |
79
+ | 1.2874 | 12.0 | 912 | 1.2484 | 0.3606 |
80
+ | 1.2669 | 13.0 | 988 | 1.2434 | 0.3623 |
81
+ | 1.2861 | 14.0 | 1064 | 1.2386 | 0.3639 |
82
+ | 1.3203 | 15.0 | 1140 | 1.2340 | 0.3639 |
83
+ | 1.3343 | 16.0 | 1216 | 1.2296 | 0.3639 |
84
+ | 1.3239 | 17.0 | 1292 | 1.2256 | 0.3656 |
85
+ | 1.2639 | 18.0 | 1368 | 1.2217 | 0.3639 |
86
+ | 1.2169 | 19.0 | 1444 | 1.2180 | 0.3673 |
87
+ | 1.1959 | 20.0 | 1520 | 1.2146 | 0.3689 |
88
+ | 1.2012 | 21.0 | 1596 | 1.2114 | 0.3723 |
89
+ | 1.1569 | 22.0 | 1672 | 1.2083 | 0.3706 |
90
+ | 1.2377 | 23.0 | 1748 | 1.2054 | 0.3656 |
91
+ | 1.2417 | 24.0 | 1824 | 1.2027 | 0.3673 |
92
+ | 1.2459 | 25.0 | 1900 | 1.2001 | 0.3689 |
93
+ | 1.2355 | 26.0 | 1976 | 1.1977 | 0.3673 |
94
+ | 1.2821 | 27.0 | 2052 | 1.1955 | 0.3656 |
95
+ | 1.2546 | 28.0 | 2128 | 1.1935 | 0.3706 |
96
+ | 1.2602 | 29.0 | 2204 | 1.1915 | 0.3689 |
97
+ | 1.1654 | 30.0 | 2280 | 1.1896 | 0.3723 |
98
+ | 1.2138 | 31.0 | 2356 | 1.1879 | 0.3740 |
99
+ | 1.2289 | 32.0 | 2432 | 1.1863 | 0.3756 |
100
+ | 1.1744 | 33.0 | 2508 | 1.1849 | 0.3756 |
101
+ | 1.2018 | 34.0 | 2584 | 1.1835 | 0.3756 |
102
+ | 1.2411 | 35.0 | 2660 | 1.1823 | 0.3773 |
103
+ | 1.2021 | 36.0 | 2736 | 1.1812 | 0.3840 |
104
+ | 1.172 | 37.0 | 2812 | 1.1802 | 0.3840 |
105
+ | 1.2015 | 38.0 | 2888 | 1.1792 | 0.3840 |
106
+ | 1.2305 | 39.0 | 2964 | 1.1784 | 0.3840 |
107
+ | 1.1165 | 40.0 | 3040 | 1.1777 | 0.3840 |
108
+ | 1.2641 | 41.0 | 3116 | 1.1771 | 0.3856 |
109
+ | 1.2228 | 42.0 | 3192 | 1.1765 | 0.3856 |
110
+ | 1.1905 | 43.0 | 3268 | 1.1761 | 0.3856 |
111
+ | 1.1893 | 44.0 | 3344 | 1.1757 | 0.3873 |
112
+ | 1.2905 | 45.0 | 3420 | 1.1755 | 0.3873 |
113
+ | 1.194 | 46.0 | 3496 | 1.1753 | 0.3873 |
114
+ | 1.1805 | 47.0 | 3572 | 1.1751 | 0.3873 |
115
+ | 1.1703 | 48.0 | 3648 | 1.1750 | 0.3873 |
116
+ | 1.2028 | 49.0 | 3724 | 1.1750 | 0.3890 |
117
+ | 1.2474 | 50.0 | 3800 | 1.1750 | 0.3890 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be4dc0fd747850263d617488cd737417da34b98ecd1de16f6076b6c32369ad17
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77fb4507d48cfbe4b308d40958ec816b9ddf1a7cbfa29ebf2916e15b9fa18d8
3
  size 22122692