Hugging Face's logo

hkivancoral
/
hushem_40x_deit_tiny_adamax_0001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
5213335
•
1 Parent(s): 3f46e62

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_40x_deit_tiny_adamax_0001_fold5
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: 0.8536585365853658
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_tiny_adamax_0001_fold5
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: 0.9183
36
+ - Accuracy: 0.8537
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
+ | 0.0769 | 1.0 | 220 | 0.5269 | 0.8293 |
69
+ | 0.0227 | 2.0 | 440 | 0.7159 | 0.8293 |
70
+ | 0.0008 | 3.0 | 660 | 1.1921 | 0.7805 |
71
+ | 0.0031 | 4.0 | 880 | 0.8277 | 0.8537 |
72
+ | 0.0006 | 5.0 | 1100 | 0.9658 | 0.8049 |
73
+ | 0.0 | 6.0 | 1320 | 0.5880 | 0.8780 |
74
+ | 0.0007 | 7.0 | 1540 | 0.9103 | 0.8293 |
75
+ | 0.0006 | 8.0 | 1760 | 0.4548 | 0.8780 |
76
+ | 0.0029 | 9.0 | 1980 | 1.0525 | 0.8293 |
77
+ | 0.0 | 10.0 | 2200 | 0.8563 | 0.8293 |
78
+ | 0.0 | 11.0 | 2420 | 0.7625 | 0.8537 |
79
+ | 0.0 | 12.0 | 2640 | 0.7582 | 0.8537 |
80
+ | 0.0 | 13.0 | 2860 | 0.7509 | 0.8537 |
81
+ | 0.0 | 14.0 | 3080 | 0.7628 | 0.8537 |
82
+ | 0.0 | 15.0 | 3300 | 0.7694 | 0.8537 |
83
+ | 0.0 | 16.0 | 3520 | 0.7739 | 0.8537 |
84
+ | 0.0 | 17.0 | 3740 | 0.7753 | 0.8537 |
85
+ | 0.0 | 18.0 | 3960 | 0.7841 | 0.8780 |
86
+ | 0.0 | 19.0 | 4180 | 0.7863 | 0.8780 |
87
+ | 0.0 | 20.0 | 4400 | 0.8002 | 0.8537 |
88
+ | 0.0 | 21.0 | 4620 | 0.7935 | 0.8537 |
89
+ | 0.0 | 22.0 | 4840 | 0.8153 | 0.8537 |
90
+ | 0.0 | 23.0 | 5060 | 0.8135 | 0.8537 |
91
+ | 0.0 | 24.0 | 5280 | 0.8169 | 0.8537 |
92
+ | 0.0 | 25.0 | 5500 | 0.8219 | 0.8537 |
93
+ | 0.0 | 26.0 | 5720 | 0.8262 | 0.8537 |
94
+ | 0.0 | 27.0 | 5940 | 0.8371 | 0.8537 |
95
+ | 0.0 | 28.0 | 6160 | 0.8311 | 0.8537 |
96
+ | 0.0 | 29.0 | 6380 | 0.8379 | 0.8537 |
97
+ | 0.0 | 30.0 | 6600 | 0.8615 | 0.8537 |
98
+ | 0.0 | 31.0 | 6820 | 0.8776 | 0.8537 |
99
+ | 0.0 | 32.0 | 7040 | 0.8507 | 0.8537 |
100
+ | 0.0 | 33.0 | 7260 | 0.8611 | 0.8537 |
101
+ | 0.0 | 34.0 | 7480 | 0.8621 | 0.8537 |
102
+ | 0.0 | 35.0 | 7700 | 0.8793 | 0.8537 |
103
+ | 0.0 | 36.0 | 7920 | 0.8811 | 0.8537 |
104
+ | 0.0 | 37.0 | 8140 | 0.8839 | 0.8537 |
105
+ | 0.0 | 38.0 | 8360 | 0.8830 | 0.8537 |
106
+ | 0.0 | 39.0 | 8580 | 0.8720 | 0.8537 |
107
+ | 0.0 | 40.0 | 8800 | 0.8855 | 0.8537 |
108
+ | 0.0 | 41.0 | 9020 | 0.8862 | 0.8537 |
109
+ | 0.0 | 42.0 | 9240 | 0.9183 | 0.8537 |
110
+ | 0.0 | 43.0 | 9460 | 0.8971 | 0.8537 |
111
+ | 0.0 | 44.0 | 9680 | 0.9190 | 0.8537 |
112
+ | 0.0 | 45.0 | 9900 | 0.9193 | 0.8537 |
113
+ | 0.0 | 46.0 | 10120 | 0.9157 | 0.8537 |
114
+ | 0.0 | 47.0 | 10340 | 0.9115 | 0.8537 |
115
+ | 0.0 | 48.0 | 10560 | 0.9160 | 0.8537 |
116
+ | 0.0 | 49.0 | 10780 | 0.9155 | 0.8537 |
117
+ | 0.0 | 50.0 | 11000 | 0.9183 | 0.8537 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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:e78be73094f96a4e2231669e13ef95ca77e15b0a2adeebfe734cd001b7d74a16
3
  size 22168618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a264d3e7d30fb8986e87a02a3ed15ebbcca96fce9aff138b89521a66f45b1605
3
  size 22168618