Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_sgd_0001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
4b1118c
•
1 Parent(s): bc010c3

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_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: 0.6783333333333333
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_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: 0.7968
36
+ - Accuracy: 0.6783
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
+ | 1.0626 | 1.0 | 75 | 1.0608 | 0.4483 |
69
+ | 1.0568 | 2.0 | 150 | 1.0464 | 0.4867 |
70
+ | 1.0365 | 3.0 | 225 | 1.0338 | 0.505 |
71
+ | 1.0078 | 4.0 | 300 | 1.0223 | 0.5333 |
72
+ | 0.9982 | 5.0 | 375 | 1.0117 | 0.5367 |
73
+ | 0.9993 | 6.0 | 450 | 1.0016 | 0.5483 |
74
+ | 0.9996 | 7.0 | 525 | 0.9918 | 0.5533 |
75
+ | 0.9666 | 8.0 | 600 | 0.9822 | 0.5583 |
76
+ | 0.9644 | 9.0 | 675 | 0.9728 | 0.5617 |
77
+ | 0.9545 | 10.0 | 750 | 0.9636 | 0.575 |
78
+ | 0.9539 | 11.0 | 825 | 0.9547 | 0.5817 |
79
+ | 0.9365 | 12.0 | 900 | 0.9461 | 0.5867 |
80
+ | 0.9407 | 13.0 | 975 | 0.9377 | 0.5983 |
81
+ | 0.9254 | 14.0 | 1050 | 0.9295 | 0.6067 |
82
+ | 0.8947 | 15.0 | 1125 | 0.9216 | 0.61 |
83
+ | 0.8953 | 16.0 | 1200 | 0.9139 | 0.615 |
84
+ | 0.8981 | 17.0 | 1275 | 0.9064 | 0.6217 |
85
+ | 0.8879 | 18.0 | 1350 | 0.8991 | 0.625 |
86
+ | 0.8717 | 19.0 | 1425 | 0.8924 | 0.625 |
87
+ | 0.894 | 20.0 | 1500 | 0.8856 | 0.6233 |
88
+ | 0.8798 | 21.0 | 1575 | 0.8793 | 0.6267 |
89
+ | 0.8697 | 22.0 | 1650 | 0.8733 | 0.6283 |
90
+ | 0.8459 | 23.0 | 1725 | 0.8674 | 0.6283 |
91
+ | 0.8379 | 24.0 | 1800 | 0.8619 | 0.6317 |
92
+ | 0.8435 | 25.0 | 1875 | 0.8567 | 0.63 |
93
+ | 0.8249 | 26.0 | 1950 | 0.8516 | 0.6367 |
94
+ | 0.8188 | 27.0 | 2025 | 0.8468 | 0.6433 |
95
+ | 0.8401 | 28.0 | 2100 | 0.8423 | 0.645 |
96
+ | 0.8328 | 29.0 | 2175 | 0.8381 | 0.6483 |
97
+ | 0.8111 | 30.0 | 2250 | 0.8341 | 0.66 |
98
+ | 0.8031 | 31.0 | 2325 | 0.8302 | 0.6633 |
99
+ | 0.8167 | 32.0 | 2400 | 0.8267 | 0.665 |
100
+ | 0.8141 | 33.0 | 2475 | 0.8233 | 0.6667 |
101
+ | 0.7864 | 34.0 | 2550 | 0.8201 | 0.6717 |
102
+ | 0.7796 | 35.0 | 2625 | 0.8172 | 0.6717 |
103
+ | 0.767 | 36.0 | 2700 | 0.8145 | 0.675 |
104
+ | 0.759 | 37.0 | 2775 | 0.8119 | 0.675 |
105
+ | 0.7758 | 38.0 | 2850 | 0.8096 | 0.675 |
106
+ | 0.7909 | 39.0 | 2925 | 0.8075 | 0.675 |
107
+ | 0.7767 | 40.0 | 3000 | 0.8055 | 0.6767 |
108
+ | 0.7913 | 41.0 | 3075 | 0.8038 | 0.6767 |
109
+ | 0.7892 | 42.0 | 3150 | 0.8023 | 0.6783 |
110
+ | 0.787 | 43.0 | 3225 | 0.8010 | 0.6783 |
111
+ | 0.7743 | 44.0 | 3300 | 0.7998 | 0.6783 |
112
+ | 0.7658 | 45.0 | 3375 | 0.7988 | 0.6783 |
113
+ | 0.8086 | 46.0 | 3450 | 0.7980 | 0.6817 |
114
+ | 0.7797 | 47.0 | 3525 | 0.7974 | 0.68 |
115
+ | 0.7878 | 48.0 | 3600 | 0.7970 | 0.6783 |
116
+ | 0.77 | 49.0 | 3675 | 0.7968 | 0.6783 |
117
+ | 0.742 | 50.0 | 3750 | 0.7968 | 0.6783 |
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 sha256:9237f5fda36a99615b167f98ac79c316ceb963dfd587192da73ff9f1392e6830
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b36ab926e96da383ca07c26bf1804cb7c5843ca2edc314031336186aab85a8f
3
  size 86690164