Hugging Face's logo

hkivancoral
/
smids_1x_beit_base_adamax_001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
ed7b2a1
•
1 Parent(s): 90b714f

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: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_1x_beit_base_adamax_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: 0.775
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_beit_base_adamax_001_fold4
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.7646
36
+ - Accuracy: 0.775
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
+ | 0.9222 | 1.0 | 75 | 0.8216 | 0.5567 |
69
+ | 0.8457 | 2.0 | 150 | 0.8398 | 0.57 |
70
+ | 0.8147 | 3.0 | 225 | 0.7493 | 0.6333 |
71
+ | 0.7701 | 4.0 | 300 | 0.7606 | 0.6117 |
72
+ | 0.8026 | 5.0 | 375 | 0.8189 | 0.565 |
73
+ | 0.6963 | 6.0 | 450 | 0.6808 | 0.665 |
74
+ | 0.7638 | 7.0 | 525 | 0.6641 | 0.7017 |
75
+ | 0.6601 | 8.0 | 600 | 0.6495 | 0.6833 |
76
+ | 0.6719 | 9.0 | 675 | 0.7134 | 0.66 |
77
+ | 0.5461 | 10.0 | 750 | 0.5791 | 0.7483 |
78
+ | 0.547 | 11.0 | 825 | 0.5859 | 0.7633 |
79
+ | 0.4912 | 12.0 | 900 | 0.5937 | 0.735 |
80
+ | 0.5352 | 13.0 | 975 | 0.5233 | 0.7667 |
81
+ | 0.4434 | 14.0 | 1050 | 0.5543 | 0.7617 |
82
+ | 0.4927 | 15.0 | 1125 | 0.7581 | 0.6767 |
83
+ | 0.4312 | 16.0 | 1200 | 0.5587 | 0.7667 |
84
+ | 0.3899 | 17.0 | 1275 | 0.6422 | 0.7633 |
85
+ | 0.3786 | 18.0 | 1350 | 0.6068 | 0.7783 |
86
+ | 0.4006 | 19.0 | 1425 | 0.6778 | 0.7617 |
87
+ | 0.3094 | 20.0 | 1500 | 0.6494 | 0.775 |
88
+ | 0.3319 | 21.0 | 1575 | 0.6363 | 0.765 |
89
+ | 0.2928 | 22.0 | 1650 | 0.7276 | 0.7817 |
90
+ | 0.2846 | 23.0 | 1725 | 0.8156 | 0.7733 |
91
+ | 0.1736 | 24.0 | 1800 | 0.7838 | 0.785 |
92
+ | 0.2416 | 25.0 | 1875 | 0.8283 | 0.775 |
93
+ | 0.1805 | 26.0 | 1950 | 0.8042 | 0.7867 |
94
+ | 0.1895 | 27.0 | 2025 | 1.0411 | 0.7933 |
95
+ | 0.0832 | 28.0 | 2100 | 1.0766 | 0.7983 |
96
+ | 0.099 | 29.0 | 2175 | 1.1178 | 0.7683 |
97
+ | 0.0916 | 30.0 | 2250 | 1.3040 | 0.775 |
98
+ | 0.128 | 31.0 | 2325 | 1.2237 | 0.7983 |
99
+ | 0.0775 | 32.0 | 2400 | 1.1999 | 0.79 |
100
+ | 0.0706 | 33.0 | 2475 | 1.4034 | 0.78 |
101
+ | 0.0546 | 34.0 | 2550 | 1.4009 | 0.785 |
102
+ | 0.0453 | 35.0 | 2625 | 1.2357 | 0.7917 |
103
+ | 0.0136 | 36.0 | 2700 | 1.4685 | 0.79 |
104
+ | 0.0534 | 37.0 | 2775 | 1.8215 | 0.7717 |
105
+ | 0.0751 | 38.0 | 2850 | 1.6150 | 0.7833 |
106
+ | 0.0013 | 39.0 | 2925 | 1.7207 | 0.7917 |
107
+ | 0.0466 | 40.0 | 3000 | 1.4737 | 0.785 |
108
+ | 0.0122 | 41.0 | 3075 | 1.5635 | 0.7783 |
109
+ | 0.0071 | 42.0 | 3150 | 1.6935 | 0.7783 |
110
+ | 0.0119 | 43.0 | 3225 | 1.6935 | 0.7833 |
111
+ | 0.0065 | 44.0 | 3300 | 1.7015 | 0.7883 |
112
+ | 0.0254 | 45.0 | 3375 | 1.7329 | 0.7867 |
113
+ | 0.0205 | 46.0 | 3450 | 1.6886 | 0.785 |
114
+ | 0.0082 | 47.0 | 3525 | 1.7094 | 0.7833 |
115
+ | 0.0134 | 48.0 | 3600 | 1.7793 | 0.78 |
116
+ | 0.005 | 49.0 | 3675 | 1.7866 | 0.7767 |
117
+ | 0.0132 | 50.0 | 3750 | 1.7646 | 0.775 |
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 sha256:7789b14d6922d5848f157fbaec574e84d517a2572e7158440eb747bcd0ec8422
3
  size 343083404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79e2f9bbd20db2c4a5aacb5f381b77566734e818c0f826131839cc79a05768c
3
  size 343083404