Hugging Face's logo

hkivancoral
/
hushem_40x_deit_small_sgd_001_fold3

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
9655d17
•
1 Parent(s): 73d00e0

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_40x_deit_small_sgd_001_fold3
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: 0.8837209302325582
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_40x_deit_small_sgd_001_fold3
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: 0.3304
36
+ - Accuracy: 0.8837
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
+ | 1.2372 | 1.0 | 217 | 1.2798 | 0.3488 |
69
+ | 1.0621 | 2.0 | 434 | 1.1335 | 0.5814 |
70
+ | 0.8881 | 3.0 | 651 | 1.0243 | 0.5814 |
71
+ | 0.7868 | 4.0 | 868 | 0.9174 | 0.6279 |
72
+ | 0.6948 | 5.0 | 1085 | 0.8587 | 0.6279 |
73
+ | 0.5714 | 6.0 | 1302 | 0.7810 | 0.7209 |
74
+ | 0.4585 | 7.0 | 1519 | 0.7011 | 0.8140 |
75
+ | 0.4277 | 8.0 | 1736 | 0.6580 | 0.7907 |
76
+ | 0.3688 | 9.0 | 1953 | 0.6164 | 0.8140 |
77
+ | 0.2836 | 10.0 | 2170 | 0.5578 | 0.8140 |
78
+ | 0.2148 | 11.0 | 2387 | 0.5322 | 0.8140 |
79
+ | 0.2211 | 12.0 | 2604 | 0.5199 | 0.8140 |
80
+ | 0.2014 | 13.0 | 2821 | 0.4865 | 0.8140 |
81
+ | 0.1799 | 14.0 | 3038 | 0.4815 | 0.8140 |
82
+ | 0.1565 | 15.0 | 3255 | 0.4749 | 0.7907 |
83
+ | 0.1129 | 16.0 | 3472 | 0.4440 | 0.8372 |
84
+ | 0.0992 | 17.0 | 3689 | 0.4542 | 0.7907 |
85
+ | 0.1 | 18.0 | 3906 | 0.4290 | 0.8140 |
86
+ | 0.0944 | 19.0 | 4123 | 0.4149 | 0.8140 |
87
+ | 0.0856 | 20.0 | 4340 | 0.4111 | 0.8372 |
88
+ | 0.0816 | 21.0 | 4557 | 0.4115 | 0.8140 |
89
+ | 0.0563 | 22.0 | 4774 | 0.3956 | 0.7907 |
90
+ | 0.0625 | 23.0 | 4991 | 0.3834 | 0.7907 |
91
+ | 0.0683 | 24.0 | 5208 | 0.3893 | 0.7907 |
92
+ | 0.0454 | 25.0 | 5425 | 0.3773 | 0.8140 |
93
+ | 0.0571 | 26.0 | 5642 | 0.3874 | 0.7907 |
94
+ | 0.0322 | 27.0 | 5859 | 0.3743 | 0.8140 |
95
+ | 0.0339 | 28.0 | 6076 | 0.3713 | 0.8372 |
96
+ | 0.0345 | 29.0 | 6293 | 0.3616 | 0.8372 |
97
+ | 0.0434 | 30.0 | 6510 | 0.3686 | 0.8372 |
98
+ | 0.0377 | 31.0 | 6727 | 0.3495 | 0.8605 |
99
+ | 0.0295 | 32.0 | 6944 | 0.3476 | 0.8372 |
100
+ | 0.0279 | 33.0 | 7161 | 0.3534 | 0.8605 |
101
+ | 0.0232 | 34.0 | 7378 | 0.3489 | 0.8372 |
102
+ | 0.0275 | 35.0 | 7595 | 0.3346 | 0.8837 |
103
+ | 0.0214 | 36.0 | 7812 | 0.3309 | 0.8605 |
104
+ | 0.018 | 37.0 | 8029 | 0.3342 | 0.8605 |
105
+ | 0.0167 | 38.0 | 8246 | 0.3289 | 0.8837 |
106
+ | 0.0196 | 39.0 | 8463 | 0.3389 | 0.8605 |
107
+ | 0.0269 | 40.0 | 8680 | 0.3388 | 0.8605 |
108
+ | 0.0126 | 41.0 | 8897 | 0.3309 | 0.8605 |
109
+ | 0.0119 | 42.0 | 9114 | 0.3316 | 0.8837 |
110
+ | 0.0174 | 43.0 | 9331 | 0.3268 | 0.8837 |
111
+ | 0.0199 | 44.0 | 9548 | 0.3304 | 0.8837 |
112
+ | 0.0115 | 45.0 | 9765 | 0.3378 | 0.8605 |
113
+ | 0.0138 | 46.0 | 9982 | 0.3301 | 0.8837 |
114
+ | 0.0107 | 47.0 | 10199 | 0.3312 | 0.8605 |
115
+ | 0.0108 | 48.0 | 10416 | 0.3294 | 0.9070 |
116
+ | 0.0125 | 49.0 | 10633 | 0.3301 | 0.8837 |
117
+ | 0.0148 | 50.0 | 10850 | 0.3304 | 0.8837 |
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 sha256:2f60d0b41fab3f3dfe3d3d33ea5e91619ba5db6034ec72ea7f3751b1a000a22c
3
  size 86737194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2338eb132ea44461ae337774d21b455ab02226520eb9719776e7de6f78e553
3
  size 86737194