Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_0001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
08a8e90
·
1 Parent(s): 67262a8

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_0001_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: 0.6733333333333333
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_0001_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: 0.8065
36
+ - Accuracy: 0.6733
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
+ | 1.08 | 1.0 | 75 | 1.0697 | 0.42 |
69
+ | 1.068 | 2.0 | 150 | 1.0540 | 0.4567 |
70
+ | 1.0267 | 3.0 | 225 | 1.0400 | 0.4817 |
71
+ | 0.9978 | 4.0 | 300 | 1.0279 | 0.5117 |
72
+ | 1.0069 | 5.0 | 375 | 1.0166 | 0.5167 |
73
+ | 0.9928 | 6.0 | 450 | 1.0059 | 0.5333 |
74
+ | 0.9852 | 7.0 | 525 | 0.9957 | 0.535 |
75
+ | 0.9289 | 8.0 | 600 | 0.9859 | 0.54 |
76
+ | 0.9567 | 9.0 | 675 | 0.9764 | 0.5533 |
77
+ | 0.9517 | 10.0 | 750 | 0.9672 | 0.5583 |
78
+ | 0.9256 | 11.0 | 825 | 0.9583 | 0.565 |
79
+ | 0.9357 | 12.0 | 900 | 0.9498 | 0.565 |
80
+ | 0.9377 | 13.0 | 975 | 0.9415 | 0.57 |
81
+ | 0.9369 | 14.0 | 1050 | 0.9334 | 0.575 |
82
+ | 0.8836 | 15.0 | 1125 | 0.9259 | 0.5667 |
83
+ | 0.922 | 16.0 | 1200 | 0.9184 | 0.575 |
84
+ | 0.8518 | 17.0 | 1275 | 0.9112 | 0.5833 |
85
+ | 0.8741 | 18.0 | 1350 | 0.9043 | 0.5883 |
86
+ | 0.8604 | 19.0 | 1425 | 0.8978 | 0.5933 |
87
+ | 0.8822 | 20.0 | 1500 | 0.8914 | 0.5983 |
88
+ | 0.8613 | 21.0 | 1575 | 0.8855 | 0.61 |
89
+ | 0.8383 | 22.0 | 1650 | 0.8797 | 0.6117 |
90
+ | 0.8466 | 23.0 | 1725 | 0.8742 | 0.615 |
91
+ | 0.8373 | 24.0 | 1800 | 0.8689 | 0.6217 |
92
+ | 0.8379 | 25.0 | 1875 | 0.8638 | 0.6283 |
93
+ | 0.8435 | 26.0 | 1950 | 0.8590 | 0.6217 |
94
+ | 0.7992 | 27.0 | 2025 | 0.8544 | 0.6267 |
95
+ | 0.8242 | 28.0 | 2100 | 0.8500 | 0.6317 |
96
+ | 0.8405 | 29.0 | 2175 | 0.8460 | 0.635 |
97
+ | 0.8059 | 30.0 | 2250 | 0.8421 | 0.6383 |
98
+ | 0.8193 | 31.0 | 2325 | 0.8384 | 0.6383 |
99
+ | 0.8107 | 32.0 | 2400 | 0.8351 | 0.64 |
100
+ | 0.777 | 33.0 | 2475 | 0.8318 | 0.6433 |
101
+ | 0.799 | 34.0 | 2550 | 0.8288 | 0.6483 |
102
+ | 0.7972 | 35.0 | 2625 | 0.8260 | 0.6533 |
103
+ | 0.8308 | 36.0 | 2700 | 0.8234 | 0.6533 |
104
+ | 0.761 | 37.0 | 2775 | 0.8210 | 0.6567 |
105
+ | 0.8092 | 38.0 | 2850 | 0.8187 | 0.6567 |
106
+ | 0.8047 | 39.0 | 2925 | 0.8167 | 0.66 |
107
+ | 0.7661 | 40.0 | 3000 | 0.8149 | 0.6633 |
108
+ | 0.7897 | 41.0 | 3075 | 0.8132 | 0.6633 |
109
+ | 0.7801 | 42.0 | 3150 | 0.8117 | 0.665 |
110
+ | 0.8176 | 43.0 | 3225 | 0.8105 | 0.6683 |
111
+ | 0.7701 | 44.0 | 3300 | 0.8093 | 0.6717 |
112
+ | 0.8017 | 45.0 | 3375 | 0.8084 | 0.6717 |
113
+ | 0.7892 | 46.0 | 3450 | 0.8077 | 0.6717 |
114
+ | 0.7778 | 47.0 | 3525 | 0.8071 | 0.6717 |
115
+ | 0.7798 | 48.0 | 3600 | 0.8068 | 0.6733 |
116
+ | 0.7777 | 49.0 | 3675 | 0.8066 | 0.6733 |
117
+ | 0.7532 | 50.0 | 3750 | 0.8065 | 0.6733 |
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:ba2a8bbd3e96392044d8a22bcff40419f207a56e8bfb72e2fa34b7b352503c0c
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe45b1d583efcdd6b1a6df4a7e3268f7e202b92b6727e168c97ade078f155a6
3
  size 86690164