Hugging Face's logo

hkivancoral
/
hushem_40x_deit_small_sgd_0001_fold5

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
hkivancoral commited on
Commit
0f9a43a
·
1 Parent(s): db0ca42

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_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: 0.4634146341463415
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_0001_fold5
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: 1.1092
36
+ - Accuracy: 0.4634
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
+ | 1.7467 | 1.0 | 220 | 1.6098 | 0.2683 |
69
+ | 1.5306 | 2.0 | 440 | 1.5314 | 0.2683 |
70
+ | 1.3989 | 3.0 | 660 | 1.5004 | 0.2439 |
71
+ | 1.3588 | 4.0 | 880 | 1.4811 | 0.2195 |
72
+ | 1.3953 | 5.0 | 1100 | 1.4639 | 0.2683 |
73
+ | 1.3096 | 6.0 | 1320 | 1.4476 | 0.2439 |
74
+ | 1.2743 | 7.0 | 1540 | 1.4329 | 0.2683 |
75
+ | 1.2405 | 8.0 | 1760 | 1.4190 | 0.2927 |
76
+ | 1.253 | 9.0 | 1980 | 1.4052 | 0.3171 |
77
+ | 1.2253 | 10.0 | 2200 | 1.3912 | 0.3171 |
78
+ | 1.1663 | 11.0 | 2420 | 1.3767 | 0.3659 |
79
+ | 1.1699 | 12.0 | 2640 | 1.3616 | 0.3659 |
80
+ | 1.1615 | 13.0 | 2860 | 1.3463 | 0.3659 |
81
+ | 1.0999 | 14.0 | 3080 | 1.3303 | 0.3902 |
82
+ | 1.1286 | 15.0 | 3300 | 1.3148 | 0.3659 |
83
+ | 1.1333 | 16.0 | 3520 | 1.2990 | 0.3659 |
84
+ | 1.075 | 17.0 | 3740 | 1.2842 | 0.3659 |
85
+ | 1.0779 | 18.0 | 3960 | 1.2709 | 0.3659 |
86
+ | 1.0652 | 19.0 | 4180 | 1.2579 | 0.3659 |
87
+ | 1.0475 | 20.0 | 4400 | 1.2462 | 0.3659 |
88
+ | 1.0095 | 21.0 | 4620 | 1.2350 | 0.3902 |
89
+ | 1.0607 | 22.0 | 4840 | 1.2247 | 0.3902 |
90
+ | 1.0243 | 23.0 | 5060 | 1.2151 | 0.4146 |
91
+ | 1.0174 | 24.0 | 5280 | 1.2064 | 0.4146 |
92
+ | 0.9654 | 25.0 | 5500 | 1.1977 | 0.3902 |
93
+ | 1.017 | 26.0 | 5720 | 1.1899 | 0.4146 |
94
+ | 1.0002 | 27.0 | 5940 | 1.1820 | 0.3902 |
95
+ | 1.0191 | 28.0 | 6160 | 1.1750 | 0.3902 |
96
+ | 0.9876 | 29.0 | 6380 | 1.1683 | 0.3902 |
97
+ | 0.9526 | 30.0 | 6600 | 1.1623 | 0.4146 |
98
+ | 0.9957 | 31.0 | 6820 | 1.1566 | 0.4390 |
99
+ | 0.9778 | 32.0 | 7040 | 1.1513 | 0.4390 |
100
+ | 0.9223 | 33.0 | 7260 | 1.1464 | 0.4634 |
101
+ | 0.9281 | 34.0 | 7480 | 1.1418 | 0.4634 |
102
+ | 0.9107 | 35.0 | 7700 | 1.1376 | 0.4634 |
103
+ | 0.9485 | 36.0 | 7920 | 1.1336 | 0.4634 |
104
+ | 0.9035 | 37.0 | 8140 | 1.1298 | 0.4634 |
105
+ | 0.9223 | 38.0 | 8360 | 1.1266 | 0.4634 |
106
+ | 0.9312 | 39.0 | 8580 | 1.1235 | 0.4634 |
107
+ | 0.8782 | 40.0 | 8800 | 1.1209 | 0.4634 |
108
+ | 0.9252 | 41.0 | 9020 | 1.1184 | 0.4634 |
109
+ | 0.8989 | 42.0 | 9240 | 1.1164 | 0.4634 |
110
+ | 0.8959 | 43.0 | 9460 | 1.1145 | 0.4634 |
111
+ | 0.8589 | 44.0 | 9680 | 1.1130 | 0.4634 |
112
+ | 0.8899 | 45.0 | 9900 | 1.1117 | 0.4634 |
113
+ | 0.8915 | 46.0 | 10120 | 1.1107 | 0.4634 |
114
+ | 0.9043 | 47.0 | 10340 | 1.1100 | 0.4634 |
115
+ | 0.8309 | 48.0 | 10560 | 1.1095 | 0.4634 |
116
+ | 0.8724 | 49.0 | 10780 | 1.1093 | 0.4634 |
117
+ | 0.9011 | 50.0 | 11000 | 1.1092 | 0.4634 |
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:baac6a997381ade6438ab30328e215b2e8a1676be66a93e9c7e96fccd65c235a
3
  size 86737194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ee78bd2143b46e1b1c85eb831a821befefbe4485cb9cd4900a4ca43cfa8992
3
  size 86737194