Hugging Face's logo

hkivancoral
/
smids_10x_deit_small_sgd_001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
cd7f543
•
1 Parent(s): 0c382db

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: smids_10x_deit_small_sgd_001_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: 0.8766666666666667
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_10x_deit_small_sgd_001_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: 0.3291
36
+ - Accuracy: 0.8767
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
+ | 0.5469 | 1.0 | 750 | 0.5533 | 0.7983 |
69
+ | 0.4148 | 2.0 | 1500 | 0.4326 | 0.8367 |
70
+ | 0.3982 | 3.0 | 2250 | 0.3912 | 0.8467 |
71
+ | 0.355 | 4.0 | 3000 | 0.3693 | 0.8533 |
72
+ | 0.3032 | 5.0 | 3750 | 0.3569 | 0.8583 |
73
+ | 0.2345 | 6.0 | 4500 | 0.3466 | 0.8617 |
74
+ | 0.2053 | 7.0 | 5250 | 0.3412 | 0.865 |
75
+ | 0.2443 | 8.0 | 6000 | 0.3381 | 0.8633 |
76
+ | 0.259 | 9.0 | 6750 | 0.3314 | 0.875 |
77
+ | 0.2146 | 10.0 | 7500 | 0.3275 | 0.8717 |
78
+ | 0.2301 | 11.0 | 8250 | 0.3262 | 0.8733 |
79
+ | 0.298 | 12.0 | 9000 | 0.3264 | 0.8733 |
80
+ | 0.2031 | 13.0 | 9750 | 0.3234 | 0.8783 |
81
+ | 0.1941 | 14.0 | 10500 | 0.3276 | 0.8783 |
82
+ | 0.1822 | 15.0 | 11250 | 0.3209 | 0.88 |
83
+ | 0.2209 | 16.0 | 12000 | 0.3226 | 0.8767 |
84
+ | 0.1294 | 17.0 | 12750 | 0.3179 | 0.8817 |
85
+ | 0.1726 | 18.0 | 13500 | 0.3224 | 0.88 |
86
+ | 0.2222 | 19.0 | 14250 | 0.3196 | 0.8833 |
87
+ | 0.1604 | 20.0 | 15000 | 0.3199 | 0.8817 |
88
+ | 0.1742 | 21.0 | 15750 | 0.3204 | 0.8783 |
89
+ | 0.1599 | 22.0 | 16500 | 0.3188 | 0.88 |
90
+ | 0.1753 | 23.0 | 17250 | 0.3189 | 0.8817 |
91
+ | 0.1975 | 24.0 | 18000 | 0.3189 | 0.8817 |
92
+ | 0.1797 | 25.0 | 18750 | 0.3190 | 0.8817 |
93
+ | 0.1646 | 26.0 | 19500 | 0.3244 | 0.8817 |
94
+ | 0.1585 | 27.0 | 20250 | 0.3244 | 0.885 |
95
+ | 0.1303 | 28.0 | 21000 | 0.3225 | 0.8817 |
96
+ | 0.1144 | 29.0 | 21750 | 0.3207 | 0.8817 |
97
+ | 0.1409 | 30.0 | 22500 | 0.3230 | 0.8817 |
98
+ | 0.1303 | 31.0 | 23250 | 0.3219 | 0.8833 |
99
+ | 0.1405 | 32.0 | 24000 | 0.3260 | 0.8817 |
100
+ | 0.1503 | 33.0 | 24750 | 0.3248 | 0.88 |
101
+ | 0.1402 | 34.0 | 25500 | 0.3257 | 0.8817 |
102
+ | 0.1266 | 35.0 | 26250 | 0.3227 | 0.88 |
103
+ | 0.1495 | 36.0 | 27000 | 0.3271 | 0.8817 |
104
+ | 0.1021 | 37.0 | 27750 | 0.3248 | 0.8833 |
105
+ | 0.1616 | 38.0 | 28500 | 0.3242 | 0.885 |
106
+ | 0.158 | 39.0 | 29250 | 0.3254 | 0.88 |
107
+ | 0.1668 | 40.0 | 30000 | 0.3256 | 0.8833 |
108
+ | 0.1276 | 41.0 | 30750 | 0.3297 | 0.88 |
109
+ | 0.1072 | 42.0 | 31500 | 0.3307 | 0.88 |
110
+ | 0.1457 | 43.0 | 32250 | 0.3289 | 0.8783 |
111
+ | 0.1691 | 44.0 | 33000 | 0.3278 | 0.8817 |
112
+ | 0.1442 | 45.0 | 33750 | 0.3288 | 0.88 |
113
+ | 0.1231 | 46.0 | 34500 | 0.3279 | 0.88 |
114
+ | 0.1011 | 47.0 | 35250 | 0.3276 | 0.8767 |
115
+ | 0.1059 | 48.0 | 36000 | 0.3287 | 0.8767 |
116
+ | 0.1263 | 49.0 | 36750 | 0.3292 | 0.8767 |
117
+ | 0.1053 | 50.0 | 37500 | 0.3291 | 0.8767 |
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 sha256:7fae6bf5f43a430618201ec8d3bdbcd1f6814bcae2753c8eb31198eb70f489dd
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096b7a51bed03f14887f75f927ff26cc83ced2cd54b9adf681902abb83328620
3
  size 86735658