Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_00001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
144462e
·
1 Parent(s): 9e0b956

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: smids_1x_deit_small_sgd_00001_fold4
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: 0.5033333333333333
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_small_sgd_00001_fold4
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: 1.0280
36
+ - Accuracy: 0.5033
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
+ | 1.0927 | 1.0 | 75 | 1.0671 | 0.43 |
69
+ | 1.0963 | 2.0 | 150 | 1.0650 | 0.4317 |
70
+ | 1.0708 | 3.0 | 225 | 1.0630 | 0.43 |
71
+ | 1.0487 | 4.0 | 300 | 1.0611 | 0.4317 |
72
+ | 1.0896 | 5.0 | 375 | 1.0592 | 0.435 |
73
+ | 1.0673 | 6.0 | 450 | 1.0575 | 0.435 |
74
+ | 1.067 | 7.0 | 525 | 1.0559 | 0.4367 |
75
+ | 1.0743 | 8.0 | 600 | 1.0543 | 0.4417 |
76
+ | 1.0607 | 9.0 | 675 | 1.0527 | 0.445 |
77
+ | 1.058 | 10.0 | 750 | 1.0512 | 0.4483 |
78
+ | 1.0598 | 11.0 | 825 | 1.0498 | 0.4483 |
79
+ | 1.0745 | 12.0 | 900 | 1.0485 | 0.45 |
80
+ | 1.0539 | 13.0 | 975 | 1.0472 | 0.45 |
81
+ | 1.0532 | 14.0 | 1050 | 1.0460 | 0.455 |
82
+ | 1.0553 | 15.0 | 1125 | 1.0448 | 0.4567 |
83
+ | 1.0605 | 16.0 | 1200 | 1.0437 | 0.465 |
84
+ | 1.0719 | 17.0 | 1275 | 1.0426 | 0.4667 |
85
+ | 1.0217 | 18.0 | 1350 | 1.0415 | 0.465 |
86
+ | 1.0569 | 19.0 | 1425 | 1.0406 | 0.4617 |
87
+ | 1.0748 | 20.0 | 1500 | 1.0396 | 0.4633 |
88
+ | 1.0485 | 21.0 | 1575 | 1.0388 | 0.4633 |
89
+ | 1.0436 | 22.0 | 1650 | 1.0379 | 0.465 |
90
+ | 1.0728 | 23.0 | 1725 | 1.0371 | 0.47 |
91
+ | 1.0532 | 24.0 | 1800 | 1.0364 | 0.475 |
92
+ | 1.0361 | 25.0 | 1875 | 1.0357 | 0.4767 |
93
+ | 1.0392 | 26.0 | 1950 | 1.0350 | 0.475 |
94
+ | 1.029 | 27.0 | 2025 | 1.0343 | 0.4767 |
95
+ | 1.0447 | 28.0 | 2100 | 1.0337 | 0.4733 |
96
+ | 1.0454 | 29.0 | 2175 | 1.0332 | 0.4783 |
97
+ | 1.0483 | 30.0 | 2250 | 1.0326 | 0.4783 |
98
+ | 1.0373 | 31.0 | 2325 | 1.0321 | 0.4833 |
99
+ | 1.0733 | 32.0 | 2400 | 1.0316 | 0.485 |
100
+ | 1.0534 | 33.0 | 2475 | 1.0312 | 0.4883 |
101
+ | 1.043 | 34.0 | 2550 | 1.0308 | 0.4883 |
102
+ | 1.0232 | 35.0 | 2625 | 1.0304 | 0.4883 |
103
+ | 1.0268 | 36.0 | 2700 | 1.0300 | 0.4917 |
104
+ | 1.0287 | 37.0 | 2775 | 1.0297 | 0.495 |
105
+ | 1.0612 | 38.0 | 2850 | 1.0294 | 0.4967 |
106
+ | 1.0429 | 39.0 | 2925 | 1.0292 | 0.4983 |
107
+ | 1.0312 | 40.0 | 3000 | 1.0290 | 0.4983 |
108
+ | 1.0436 | 41.0 | 3075 | 1.0287 | 0.5 |
109
+ | 1.0377 | 42.0 | 3150 | 1.0286 | 0.5 |
110
+ | 1.046 | 43.0 | 3225 | 1.0284 | 0.5017 |
111
+ | 1.0455 | 44.0 | 3300 | 1.0283 | 0.5033 |
112
+ | 1.0485 | 45.0 | 3375 | 1.0282 | 0.5033 |
113
+ | 1.0401 | 46.0 | 3450 | 1.0281 | 0.5033 |
114
+ | 1.0459 | 47.0 | 3525 | 1.0280 | 0.5033 |
115
+ | 1.0359 | 48.0 | 3600 | 1.0280 | 0.5033 |
116
+ | 1.0504 | 49.0 | 3675 | 1.0280 | 0.5033 |
117
+ | 1.0198 | 50.0 | 3750 | 1.0280 | 0.5033 |
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:df2d11a3dd90c29d7404264117260c84a14b2fb32fbb022c4d487b5983f84856
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb73957b57221361c19a1e7bc30ae8643ef4f6083f8477533f1c1979c979cb2
3
  size 86690164