Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
5d8f89c
•
1 Parent(s): 0107efb

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_001_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: 0.855
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_001_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: 0.3554
36
+ - Accuracy: 0.855
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
+ | 0.9725 | 1.0 | 75 | 0.9578 | 0.58 |
69
+ | 0.8549 | 2.0 | 150 | 0.8545 | 0.6367 |
70
+ | 0.7685 | 3.0 | 225 | 0.7653 | 0.6967 |
71
+ | 0.7189 | 4.0 | 300 | 0.6967 | 0.7383 |
72
+ | 0.6469 | 5.0 | 375 | 0.6428 | 0.7567 |
73
+ | 0.5993 | 6.0 | 450 | 0.5995 | 0.7667 |
74
+ | 0.5809 | 7.0 | 525 | 0.5645 | 0.7717 |
75
+ | 0.5382 | 8.0 | 600 | 0.5378 | 0.7817 |
76
+ | 0.5132 | 9.0 | 675 | 0.5146 | 0.7933 |
77
+ | 0.5002 | 10.0 | 750 | 0.4976 | 0.7817 |
78
+ | 0.5258 | 11.0 | 825 | 0.4771 | 0.8033 |
79
+ | 0.4262 | 12.0 | 900 | 0.4625 | 0.8183 |
80
+ | 0.4371 | 13.0 | 975 | 0.4503 | 0.8217 |
81
+ | 0.4112 | 14.0 | 1050 | 0.4406 | 0.8217 |
82
+ | 0.3773 | 15.0 | 1125 | 0.4328 | 0.8183 |
83
+ | 0.3566 | 16.0 | 1200 | 0.4255 | 0.82 |
84
+ | 0.3898 | 17.0 | 1275 | 0.4160 | 0.83 |
85
+ | 0.3699 | 18.0 | 1350 | 0.4107 | 0.8233 |
86
+ | 0.3811 | 19.0 | 1425 | 0.4043 | 0.84 |
87
+ | 0.3869 | 20.0 | 1500 | 0.4001 | 0.8317 |
88
+ | 0.363 | 21.0 | 1575 | 0.3965 | 0.8383 |
89
+ | 0.3336 | 22.0 | 1650 | 0.3912 | 0.8433 |
90
+ | 0.334 | 23.0 | 1725 | 0.3876 | 0.8433 |
91
+ | 0.3158 | 24.0 | 1800 | 0.3862 | 0.845 |
92
+ | 0.309 | 25.0 | 1875 | 0.3831 | 0.8433 |
93
+ | 0.3223 | 26.0 | 1950 | 0.3821 | 0.84 |
94
+ | 0.3225 | 27.0 | 2025 | 0.3783 | 0.8417 |
95
+ | 0.3412 | 28.0 | 2100 | 0.3753 | 0.845 |
96
+ | 0.3183 | 29.0 | 2175 | 0.3735 | 0.8433 |
97
+ | 0.3062 | 30.0 | 2250 | 0.3707 | 0.8417 |
98
+ | 0.2914 | 31.0 | 2325 | 0.3702 | 0.8417 |
99
+ | 0.2994 | 32.0 | 2400 | 0.3684 | 0.84 |
100
+ | 0.3197 | 33.0 | 2475 | 0.3663 | 0.8467 |
101
+ | 0.2992 | 34.0 | 2550 | 0.3643 | 0.85 |
102
+ | 0.3245 | 35.0 | 2625 | 0.3629 | 0.8517 |
103
+ | 0.2966 | 36.0 | 2700 | 0.3625 | 0.8483 |
104
+ | 0.2581 | 37.0 | 2775 | 0.3619 | 0.8467 |
105
+ | 0.3008 | 38.0 | 2850 | 0.3609 | 0.8483 |
106
+ | 0.2884 | 39.0 | 2925 | 0.3604 | 0.85 |
107
+ | 0.3019 | 40.0 | 3000 | 0.3593 | 0.85 |
108
+ | 0.3288 | 41.0 | 3075 | 0.3590 | 0.8517 |
109
+ | 0.3129 | 42.0 | 3150 | 0.3580 | 0.855 |
110
+ | 0.2899 | 43.0 | 3225 | 0.3573 | 0.855 |
111
+ | 0.2709 | 44.0 | 3300 | 0.3568 | 0.855 |
112
+ | 0.2859 | 45.0 | 3375 | 0.3565 | 0.8533 |
113
+ | 0.3026 | 46.0 | 3450 | 0.3561 | 0.8533 |
114
+ | 0.2643 | 47.0 | 3525 | 0.3557 | 0.855 |
115
+ | 0.2626 | 48.0 | 3600 | 0.3556 | 0.855 |
116
+ | 0.2672 | 49.0 | 3675 | 0.3555 | 0.855 |
117
+ | 0.2682 | 50.0 | 3750 | 0.3554 | 0.855 |
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 sha256:950b0ae40bec763c8501c76989cbcad19fb6092dc20340602e5b7e6928a27322
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987520a7e6b415090ed557c8ca888ff25a82ad74bf404e479a202eecaef407f9
3
  size 86690164