Hugging Face's logo

hkivancoral
/
smids_1x_beit_base_sgd_001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
bbade22
•
1 Parent(s): 6a7b4dc

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_sgd_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: 0.8533333333333334
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_sgd_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: 0.3889
36
+ - Accuracy: 0.8533
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
+ | 1.0889 | 1.0 | 75 | 1.0669 | 0.4483 |
69
+ | 0.8655 | 2.0 | 150 | 0.8559 | 0.645 |
70
+ | 0.7785 | 3.0 | 225 | 0.7294 | 0.7017 |
71
+ | 0.7379 | 4.0 | 300 | 0.6722 | 0.7167 |
72
+ | 0.7102 | 5.0 | 375 | 0.6344 | 0.7367 |
73
+ | 0.679 | 6.0 | 450 | 0.6029 | 0.7583 |
74
+ | 0.6616 | 7.0 | 525 | 0.5757 | 0.7667 |
75
+ | 0.6078 | 8.0 | 600 | 0.5519 | 0.7983 |
76
+ | 0.6427 | 9.0 | 675 | 0.5357 | 0.7867 |
77
+ | 0.5452 | 10.0 | 750 | 0.5237 | 0.7983 |
78
+ | 0.5678 | 11.0 | 825 | 0.5091 | 0.7933 |
79
+ | 0.5374 | 12.0 | 900 | 0.4984 | 0.8083 |
80
+ | 0.5811 | 13.0 | 975 | 0.4866 | 0.8033 |
81
+ | 0.5027 | 14.0 | 1050 | 0.4734 | 0.81 |
82
+ | 0.4787 | 15.0 | 1125 | 0.4709 | 0.805 |
83
+ | 0.4828 | 16.0 | 1200 | 0.4644 | 0.8117 |
84
+ | 0.4631 | 17.0 | 1275 | 0.4587 | 0.81 |
85
+ | 0.4343 | 18.0 | 1350 | 0.4468 | 0.82 |
86
+ | 0.4904 | 19.0 | 1425 | 0.4435 | 0.82 |
87
+ | 0.4433 | 20.0 | 1500 | 0.4398 | 0.8167 |
88
+ | 0.4461 | 21.0 | 1575 | 0.4318 | 0.8283 |
89
+ | 0.3894 | 22.0 | 1650 | 0.4361 | 0.8217 |
90
+ | 0.4398 | 23.0 | 1725 | 0.4269 | 0.8333 |
91
+ | 0.4433 | 24.0 | 1800 | 0.4213 | 0.835 |
92
+ | 0.4253 | 25.0 | 1875 | 0.4182 | 0.8333 |
93
+ | 0.4141 | 26.0 | 1950 | 0.4208 | 0.835 |
94
+ | 0.4307 | 27.0 | 2025 | 0.4086 | 0.8433 |
95
+ | 0.4132 | 28.0 | 2100 | 0.4078 | 0.8417 |
96
+ | 0.41 | 29.0 | 2175 | 0.4074 | 0.8467 |
97
+ | 0.4398 | 30.0 | 2250 | 0.4048 | 0.8383 |
98
+ | 0.3394 | 31.0 | 2325 | 0.4047 | 0.8383 |
99
+ | 0.4174 | 32.0 | 2400 | 0.4015 | 0.8433 |
100
+ | 0.4379 | 33.0 | 2475 | 0.3992 | 0.8433 |
101
+ | 0.3836 | 34.0 | 2550 | 0.3988 | 0.845 |
102
+ | 0.3824 | 35.0 | 2625 | 0.3986 | 0.845 |
103
+ | 0.3571 | 36.0 | 2700 | 0.3978 | 0.8433 |
104
+ | 0.348 | 37.0 | 2775 | 0.3932 | 0.8483 |
105
+ | 0.3852 | 38.0 | 2850 | 0.3961 | 0.8433 |
106
+ | 0.4099 | 39.0 | 2925 | 0.3932 | 0.8483 |
107
+ | 0.4003 | 40.0 | 3000 | 0.3917 | 0.8533 |
108
+ | 0.3921 | 41.0 | 3075 | 0.3931 | 0.8483 |
109
+ | 0.3545 | 42.0 | 3150 | 0.3904 | 0.8533 |
110
+ | 0.3816 | 43.0 | 3225 | 0.3916 | 0.8467 |
111
+ | 0.3789 | 44.0 | 3300 | 0.3906 | 0.8533 |
112
+ | 0.373 | 45.0 | 3375 | 0.3905 | 0.85 |
113
+ | 0.3767 | 46.0 | 3450 | 0.3894 | 0.8533 |
114
+ | 0.3814 | 47.0 | 3525 | 0.3896 | 0.8517 |
115
+ | 0.3984 | 48.0 | 3600 | 0.3899 | 0.85 |
116
+ | 0.3749 | 49.0 | 3675 | 0.3891 | 0.8533 |
117
+ | 0.3605 | 50.0 | 3750 | 0.3889 | 0.8533 |
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 sha256:9b7d85121911669f61020a495c5da03c66408cd2f6fc8be8197731fbe7389326
3
  size 343083404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a976b40798a7cc4bef29ec53c74ea393cee91e9fe1b3f74c363c434ebc37285
3
  size 343083404