Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_00001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
972b5fe
·
1 Parent(s): f12a24a

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_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: 0.47
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_fold3
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: 1.0491
36
+ - Accuracy: 0.47
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
+ | 1.0941 | 1.0 | 75 | 1.0867 | 0.3867 |
69
+ | 1.1031 | 2.0 | 150 | 1.0847 | 0.3883 |
70
+ | 1.0678 | 3.0 | 225 | 1.0827 | 0.39 |
71
+ | 1.0493 | 4.0 | 300 | 1.0809 | 0.395 |
72
+ | 1.0783 | 5.0 | 375 | 1.0791 | 0.4017 |
73
+ | 1.0689 | 6.0 | 450 | 1.0774 | 0.4083 |
74
+ | 1.0606 | 7.0 | 525 | 1.0758 | 0.4117 |
75
+ | 1.0286 | 8.0 | 600 | 1.0743 | 0.4117 |
76
+ | 1.0504 | 9.0 | 675 | 1.0729 | 0.415 |
77
+ | 1.0349 | 10.0 | 750 | 1.0714 | 0.415 |
78
+ | 1.0372 | 11.0 | 825 | 1.0701 | 0.4167 |
79
+ | 1.0665 | 12.0 | 900 | 1.0688 | 0.4233 |
80
+ | 1.0542 | 13.0 | 975 | 1.0676 | 0.4233 |
81
+ | 1.0662 | 14.0 | 1050 | 1.0664 | 0.4267 |
82
+ | 1.0308 | 15.0 | 1125 | 1.0653 | 0.4283 |
83
+ | 1.0599 | 16.0 | 1200 | 1.0642 | 0.4283 |
84
+ | 1.0281 | 17.0 | 1275 | 1.0632 | 0.43 |
85
+ | 1.0433 | 18.0 | 1350 | 1.0622 | 0.4383 |
86
+ | 1.0474 | 19.0 | 1425 | 1.0612 | 0.4433 |
87
+ | 1.0662 | 20.0 | 1500 | 1.0603 | 0.4467 |
88
+ | 1.0359 | 21.0 | 1575 | 1.0595 | 0.4417 |
89
+ | 1.0248 | 22.0 | 1650 | 1.0587 | 0.4417 |
90
+ | 1.0401 | 23.0 | 1725 | 1.0579 | 0.445 |
91
+ | 1.0329 | 24.0 | 1800 | 1.0572 | 0.4467 |
92
+ | 1.053 | 25.0 | 1875 | 1.0565 | 0.4533 |
93
+ | 1.0305 | 26.0 | 1950 | 1.0558 | 0.4533 |
94
+ | 1.0308 | 27.0 | 2025 | 1.0552 | 0.455 |
95
+ | 1.0523 | 28.0 | 2100 | 1.0546 | 0.4567 |
96
+ | 1.0577 | 29.0 | 2175 | 1.0541 | 0.4583 |
97
+ | 1.0456 | 30.0 | 2250 | 1.0535 | 0.4583 |
98
+ | 1.0268 | 31.0 | 2325 | 1.0531 | 0.4583 |
99
+ | 1.0567 | 32.0 | 2400 | 1.0526 | 0.4617 |
100
+ | 1.0191 | 33.0 | 2475 | 1.0522 | 0.465 |
101
+ | 1.0381 | 34.0 | 2550 | 1.0518 | 0.47 |
102
+ | 1.0572 | 35.0 | 2625 | 1.0514 | 0.47 |
103
+ | 1.0481 | 36.0 | 2700 | 1.0511 | 0.47 |
104
+ | 1.022 | 37.0 | 2775 | 1.0508 | 0.4683 |
105
+ | 1.0366 | 38.0 | 2850 | 1.0505 | 0.4683 |
106
+ | 1.029 | 39.0 | 2925 | 1.0502 | 0.4683 |
107
+ | 1.0115 | 40.0 | 3000 | 1.0500 | 0.47 |
108
+ | 1.0512 | 41.0 | 3075 | 1.0498 | 0.47 |
109
+ | 1.0219 | 42.0 | 3150 | 1.0496 | 0.47 |
110
+ | 1.046 | 43.0 | 3225 | 1.0495 | 0.47 |
111
+ | 1.0476 | 44.0 | 3300 | 1.0494 | 0.47 |
112
+ | 1.0512 | 45.0 | 3375 | 1.0493 | 0.47 |
113
+ | 1.0286 | 46.0 | 3450 | 1.0492 | 0.47 |
114
+ | 1.0307 | 47.0 | 3525 | 1.0491 | 0.47 |
115
+ | 1.0266 | 48.0 | 3600 | 1.0491 | 0.47 |
116
+ | 1.0403 | 49.0 | 3675 | 1.0491 | 0.47 |
117
+ | 1.011 | 50.0 | 3750 | 1.0491 | 0.47 |
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 sha256:2241217ce1e6032eccdb409b6bf6af30079c90bb2a69c6c9a302a068dcd5e110
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2b5a14cbce25d9efa5d1340ce930e80fede5bef9e50309e84a72d7996152d5
3
  size 86690164