Hugging Face's logo

hkivancoral
/
hushem_5x_deit_small_sgd_0001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
32fe188
•
1 Parent(s): faba13b

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_deit_small_sgd_0001_fold2
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: 0.3333333333333333
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
+ # hushem_5x_deit_small_sgd_0001_fold2
32
+
33
+ This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.3896
36
+ - Accuracy: 0.3333
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: 0.0001
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
+ | 1.5183 | 1.0 | 27 | 1.5038 | 0.1778 |
69
+ | 1.502 | 2.0 | 54 | 1.4946 | 0.2 |
70
+ | 1.5109 | 3.0 | 81 | 1.4859 | 0.2222 |
71
+ | 1.5446 | 4.0 | 108 | 1.4781 | 0.2444 |
72
+ | 1.4687 | 5.0 | 135 | 1.4710 | 0.2444 |
73
+ | 1.4554 | 6.0 | 162 | 1.4641 | 0.2889 |
74
+ | 1.4113 | 7.0 | 189 | 1.4582 | 0.2889 |
75
+ | 1.4434 | 8.0 | 216 | 1.4525 | 0.2667 |
76
+ | 1.4243 | 9.0 | 243 | 1.4473 | 0.2667 |
77
+ | 1.4268 | 10.0 | 270 | 1.4425 | 0.2889 |
78
+ | 1.386 | 11.0 | 297 | 1.4382 | 0.2889 |
79
+ | 1.4235 | 12.0 | 324 | 1.4341 | 0.2667 |
80
+ | 1.4228 | 13.0 | 351 | 1.4304 | 0.2667 |
81
+ | 1.4091 | 14.0 | 378 | 1.4269 | 0.2889 |
82
+ | 1.4135 | 15.0 | 405 | 1.4239 | 0.2667 |
83
+ | 1.4228 | 16.0 | 432 | 1.4210 | 0.2889 |
84
+ | 1.4188 | 17.0 | 459 | 1.4184 | 0.2889 |
85
+ | 1.3824 | 18.0 | 486 | 1.4159 | 0.3333 |
86
+ | 1.3861 | 19.0 | 513 | 1.4136 | 0.3111 |
87
+ | 1.393 | 20.0 | 540 | 1.4115 | 0.3111 |
88
+ | 1.4051 | 21.0 | 567 | 1.4096 | 0.3111 |
89
+ | 1.373 | 22.0 | 594 | 1.4077 | 0.3333 |
90
+ | 1.3737 | 23.0 | 621 | 1.4060 | 0.3333 |
91
+ | 1.3668 | 24.0 | 648 | 1.4044 | 0.3556 |
92
+ | 1.362 | 25.0 | 675 | 1.4030 | 0.3556 |
93
+ | 1.3931 | 26.0 | 702 | 1.4016 | 0.3556 |
94
+ | 1.3504 | 27.0 | 729 | 1.4003 | 0.3556 |
95
+ | 1.3706 | 28.0 | 756 | 1.3992 | 0.3556 |
96
+ | 1.359 | 29.0 | 783 | 1.3981 | 0.3556 |
97
+ | 1.3774 | 30.0 | 810 | 1.3972 | 0.3556 |
98
+ | 1.3678 | 31.0 | 837 | 1.3963 | 0.3556 |
99
+ | 1.3418 | 32.0 | 864 | 1.3955 | 0.3556 |
100
+ | 1.3702 | 33.0 | 891 | 1.3947 | 0.3556 |
101
+ | 1.3589 | 34.0 | 918 | 1.3940 | 0.3556 |
102
+ | 1.3212 | 35.0 | 945 | 1.3933 | 0.3333 |
103
+ | 1.3648 | 36.0 | 972 | 1.3928 | 0.3333 |
104
+ | 1.3509 | 37.0 | 999 | 1.3922 | 0.3333 |
105
+ | 1.3506 | 38.0 | 1026 | 1.3917 | 0.3333 |
106
+ | 1.3673 | 39.0 | 1053 | 1.3913 | 0.3333 |
107
+ | 1.3657 | 40.0 | 1080 | 1.3910 | 0.3333 |
108
+ | 1.3651 | 41.0 | 1107 | 1.3906 | 0.3333 |
109
+ | 1.3688 | 42.0 | 1134 | 1.3904 | 0.3333 |
110
+ | 1.3871 | 43.0 | 1161 | 1.3901 | 0.3333 |
111
+ | 1.3307 | 44.0 | 1188 | 1.3899 | 0.3333 |
112
+ | 1.3505 | 45.0 | 1215 | 1.3898 | 0.3333 |
113
+ | 1.3367 | 46.0 | 1242 | 1.3897 | 0.3333 |
114
+ | 1.3605 | 47.0 | 1269 | 1.3896 | 0.3333 |
115
+ | 1.3556 | 48.0 | 1296 | 1.3896 | 0.3333 |
116
+ | 1.3876 | 49.0 | 1323 | 1.3896 | 0.3333 |
117
+ | 1.3357 | 50.0 | 1350 | 1.3896 | 0.3333 |
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 sha256:65a0a42d75e70af21a367502a739a059ed8d0f6a4ea0d3f41f3f7a7189e97eca
3
  size 86691704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f0d93405124bcbe01dcb9053fccfb0f03f6f09e53fbbc3faacfc41b448e683
3
  size 86691704