Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_sgd_001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
6d91862
•
1 Parent(s): e98176a

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: hushem_5x_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: 0.4222222222222222
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_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: 1.3348
36
+ - Accuracy: 0.4222
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
+ | 1.4407 | 1.0 | 27 | 1.4410 | 0.2667 |
69
+ | 1.382 | 2.0 | 54 | 1.4092 | 0.2667 |
70
+ | 1.3657 | 3.0 | 81 | 1.3896 | 0.2889 |
71
+ | 1.3344 | 4.0 | 108 | 1.3798 | 0.3111 |
72
+ | 1.2537 | 5.0 | 135 | 1.3657 | 0.3111 |
73
+ | 1.2237 | 6.0 | 162 | 1.3512 | 0.3333 |
74
+ | 1.2007 | 7.0 | 189 | 1.3419 | 0.3333 |
75
+ | 1.1972 | 8.0 | 216 | 1.3343 | 0.3556 |
76
+ | 1.1733 | 9.0 | 243 | 1.3294 | 0.3556 |
77
+ | 1.1145 | 10.0 | 270 | 1.3216 | 0.3778 |
78
+ | 1.1155 | 11.0 | 297 | 1.3166 | 0.3778 |
79
+ | 1.036 | 12.0 | 324 | 1.3103 | 0.3778 |
80
+ | 1.0595 | 13.0 | 351 | 1.3110 | 0.3778 |
81
+ | 1.0374 | 14.0 | 378 | 1.3072 | 0.3556 |
82
+ | 1.0659 | 15.0 | 405 | 1.3094 | 0.3778 |
83
+ | 1.034 | 16.0 | 432 | 1.3075 | 0.3778 |
84
+ | 0.954 | 17.0 | 459 | 1.3079 | 0.3778 |
85
+ | 0.9531 | 18.0 | 486 | 1.3085 | 0.3778 |
86
+ | 0.957 | 19.0 | 513 | 1.3124 | 0.3778 |
87
+ | 0.8978 | 20.0 | 540 | 1.3062 | 0.3778 |
88
+ | 0.885 | 21.0 | 567 | 1.3090 | 0.3778 |
89
+ | 0.8819 | 22.0 | 594 | 1.3143 | 0.3778 |
90
+ | 0.8801 | 23.0 | 621 | 1.3162 | 0.3778 |
91
+ | 0.857 | 24.0 | 648 | 1.3096 | 0.3778 |
92
+ | 0.8479 | 25.0 | 675 | 1.3101 | 0.3778 |
93
+ | 0.8743 | 26.0 | 702 | 1.3127 | 0.4 |
94
+ | 0.8288 | 27.0 | 729 | 1.3204 | 0.4 |
95
+ | 0.8104 | 28.0 | 756 | 1.3212 | 0.4 |
96
+ | 0.8245 | 29.0 | 783 | 1.3255 | 0.4 |
97
+ | 0.8139 | 30.0 | 810 | 1.3165 | 0.4 |
98
+ | 0.796 | 31.0 | 837 | 1.3232 | 0.4 |
99
+ | 0.7919 | 32.0 | 864 | 1.3216 | 0.4 |
100
+ | 0.7796 | 33.0 | 891 | 1.3211 | 0.4 |
101
+ | 0.7571 | 34.0 | 918 | 1.3245 | 0.4222 |
102
+ | 0.7521 | 35.0 | 945 | 1.3258 | 0.4222 |
103
+ | 0.7479 | 36.0 | 972 | 1.3280 | 0.4222 |
104
+ | 0.7621 | 37.0 | 999 | 1.3305 | 0.4222 |
105
+ | 0.7058 | 38.0 | 1026 | 1.3305 | 0.4222 |
106
+ | 0.71 | 39.0 | 1053 | 1.3319 | 0.4222 |
107
+ | 0.7228 | 40.0 | 1080 | 1.3314 | 0.4222 |
108
+ | 0.7146 | 41.0 | 1107 | 1.3317 | 0.4222 |
109
+ | 0.7189 | 42.0 | 1134 | 1.3333 | 0.4222 |
110
+ | 0.7405 | 43.0 | 1161 | 1.3338 | 0.4222 |
111
+ | 0.6872 | 44.0 | 1188 | 1.3335 | 0.4222 |
112
+ | 0.6996 | 45.0 | 1215 | 1.3344 | 0.4222 |
113
+ | 0.6979 | 46.0 | 1242 | 1.3345 | 0.4222 |
114
+ | 0.7035 | 47.0 | 1269 | 1.3347 | 0.4222 |
115
+ | 0.703 | 48.0 | 1296 | 1.3347 | 0.4222 |
116
+ | 0.7245 | 49.0 | 1323 | 1.3348 | 0.4222 |
117
+ | 0.7019 | 50.0 | 1350 | 1.3348 | 0.4222 |
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 sha256:2ed8ad6f032639712a1e4de0b023965a7bd4b92d6dbcdad79519b0e742cdfeb2
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ca4980d02389d68d46d341db8385a276fcd3a38b537e764bda477bcc3bcbcf
3
  size 22123464