Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_sgd_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
088fc5b
·
1 Parent(s): 9f4f5c3

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_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: 0.5581395348837209
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_fold3
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: 1.0019
36
+ - Accuracy: 0.5581
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
+ | 1.5059 | 1.0 | 28 | 1.5596 | 0.3023 |
69
+ | 1.3905 | 2.0 | 56 | 1.4722 | 0.3023 |
70
+ | 1.3398 | 3.0 | 84 | 1.4240 | 0.3023 |
71
+ | 1.3159 | 4.0 | 112 | 1.3834 | 0.3488 |
72
+ | 1.2162 | 5.0 | 140 | 1.3509 | 0.3721 |
73
+ | 1.2552 | 6.0 | 168 | 1.3214 | 0.3721 |
74
+ | 1.2492 | 7.0 | 196 | 1.3011 | 0.3721 |
75
+ | 1.2051 | 8.0 | 224 | 1.2801 | 0.3953 |
76
+ | 1.1592 | 9.0 | 252 | 1.2612 | 0.3953 |
77
+ | 1.1549 | 10.0 | 280 | 1.2440 | 0.3953 |
78
+ | 1.1103 | 11.0 | 308 | 1.2292 | 0.3953 |
79
+ | 1.1084 | 12.0 | 336 | 1.2159 | 0.3953 |
80
+ | 1.0301 | 13.0 | 364 | 1.2021 | 0.3953 |
81
+ | 1.0455 | 14.0 | 392 | 1.1867 | 0.4419 |
82
+ | 1.0462 | 15.0 | 420 | 1.1750 | 0.4419 |
83
+ | 1.0114 | 16.0 | 448 | 1.1653 | 0.4419 |
84
+ | 0.9862 | 17.0 | 476 | 1.1504 | 0.4651 |
85
+ | 0.9557 | 18.0 | 504 | 1.1422 | 0.4651 |
86
+ | 0.9635 | 19.0 | 532 | 1.1339 | 0.4651 |
87
+ | 0.9341 | 20.0 | 560 | 1.1250 | 0.4419 |
88
+ | 0.9142 | 21.0 | 588 | 1.1124 | 0.4651 |
89
+ | 0.9058 | 22.0 | 616 | 1.1036 | 0.4651 |
90
+ | 0.9242 | 23.0 | 644 | 1.0941 | 0.4884 |
91
+ | 0.8383 | 24.0 | 672 | 1.0875 | 0.5349 |
92
+ | 0.9017 | 25.0 | 700 | 1.0842 | 0.5116 |
93
+ | 0.8456 | 26.0 | 728 | 1.0767 | 0.5349 |
94
+ | 0.8584 | 27.0 | 756 | 1.0674 | 0.5349 |
95
+ | 0.8615 | 28.0 | 784 | 1.0594 | 0.5349 |
96
+ | 0.8302 | 29.0 | 812 | 1.0523 | 0.5581 |
97
+ | 0.8218 | 30.0 | 840 | 1.0467 | 0.5581 |
98
+ | 0.7666 | 31.0 | 868 | 1.0425 | 0.5581 |
99
+ | 0.8374 | 32.0 | 896 | 1.0358 | 0.5581 |
100
+ | 0.8102 | 33.0 | 924 | 1.0386 | 0.5581 |
101
+ | 0.803 | 34.0 | 952 | 1.0300 | 0.5581 |
102
+ | 0.8593 | 35.0 | 980 | 1.0290 | 0.5349 |
103
+ | 0.781 | 36.0 | 1008 | 1.0257 | 0.5349 |
104
+ | 0.769 | 37.0 | 1036 | 1.0205 | 0.5349 |
105
+ | 0.7568 | 38.0 | 1064 | 1.0221 | 0.5349 |
106
+ | 0.7521 | 39.0 | 1092 | 1.0159 | 0.5349 |
107
+ | 0.7774 | 40.0 | 1120 | 1.0130 | 0.5349 |
108
+ | 0.7906 | 41.0 | 1148 | 1.0102 | 0.5349 |
109
+ | 0.7478 | 42.0 | 1176 | 1.0092 | 0.5349 |
110
+ | 0.7422 | 43.0 | 1204 | 1.0064 | 0.5349 |
111
+ | 0.7561 | 44.0 | 1232 | 1.0041 | 0.5349 |
112
+ | 0.7139 | 45.0 | 1260 | 1.0022 | 0.5349 |
113
+ | 0.7352 | 46.0 | 1288 | 1.0021 | 0.5581 |
114
+ | 0.7448 | 47.0 | 1316 | 1.0021 | 0.5581 |
115
+ | 0.7592 | 48.0 | 1344 | 1.0020 | 0.5581 |
116
+ | 0.7313 | 49.0 | 1372 | 1.0019 | 0.5581 |
117
+ | 0.6642 | 50.0 | 1400 | 1.0019 | 0.5581 |
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 sha256:0063abd1f5361aac28716acc4cb99144ac138cff8f3a14f426a1fcec553a589e
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0bbb8bbff5b89d5629c8bbd8adf19badeffe8a210ab670ddcace83a93d7d56
3
  size 22123464