Hugging Face's logo

hkivancoral
/
smids_1x_beit_base_sgd_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
6887ad5
•
1 Parent(s): ed60541

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_fold2
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: 0.8635607321131448
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_fold2
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: 0.3600
36
+ - Accuracy: 0.8636
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
+ | 1.0974 | 1.0 | 75 | 1.0410 | 0.4309 |
69
+ | 1.0056 | 2.0 | 150 | 0.9317 | 0.5424 |
70
+ | 0.8916 | 3.0 | 225 | 0.8446 | 0.5890 |
71
+ | 0.8349 | 4.0 | 300 | 0.7646 | 0.6473 |
72
+ | 0.7414 | 5.0 | 375 | 0.6971 | 0.7022 |
73
+ | 0.6784 | 6.0 | 450 | 0.6337 | 0.7571 |
74
+ | 0.7121 | 7.0 | 525 | 0.5878 | 0.7754 |
75
+ | 0.6558 | 8.0 | 600 | 0.5609 | 0.7787 |
76
+ | 0.6317 | 9.0 | 675 | 0.5312 | 0.8087 |
77
+ | 0.6518 | 10.0 | 750 | 0.5083 | 0.8136 |
78
+ | 0.5234 | 11.0 | 825 | 0.4912 | 0.8203 |
79
+ | 0.5342 | 12.0 | 900 | 0.4745 | 0.8236 |
80
+ | 0.5263 | 13.0 | 975 | 0.4621 | 0.8186 |
81
+ | 0.4728 | 14.0 | 1050 | 0.4552 | 0.8220 |
82
+ | 0.4696 | 15.0 | 1125 | 0.4418 | 0.8336 |
83
+ | 0.4875 | 16.0 | 1200 | 0.4387 | 0.8286 |
84
+ | 0.4719 | 17.0 | 1275 | 0.4281 | 0.8303 |
85
+ | 0.4659 | 18.0 | 1350 | 0.4174 | 0.8386 |
86
+ | 0.4608 | 19.0 | 1425 | 0.4192 | 0.8319 |
87
+ | 0.4678 | 20.0 | 1500 | 0.4085 | 0.8486 |
88
+ | 0.4982 | 21.0 | 1575 | 0.4035 | 0.8519 |
89
+ | 0.4136 | 22.0 | 1650 | 0.3939 | 0.8552 |
90
+ | 0.4205 | 23.0 | 1725 | 0.3934 | 0.8502 |
91
+ | 0.45 | 24.0 | 1800 | 0.3901 | 0.8519 |
92
+ | 0.4234 | 25.0 | 1875 | 0.3886 | 0.8536 |
93
+ | 0.3928 | 26.0 | 1950 | 0.3881 | 0.8486 |
94
+ | 0.4665 | 27.0 | 2025 | 0.3799 | 0.8636 |
95
+ | 0.416 | 28.0 | 2100 | 0.3843 | 0.8519 |
96
+ | 0.386 | 29.0 | 2175 | 0.3779 | 0.8619 |
97
+ | 0.3668 | 30.0 | 2250 | 0.3747 | 0.8552 |
98
+ | 0.3858 | 31.0 | 2325 | 0.3781 | 0.8602 |
99
+ | 0.3907 | 32.0 | 2400 | 0.3740 | 0.8602 |
100
+ | 0.4156 | 33.0 | 2475 | 0.3701 | 0.8619 |
101
+ | 0.4094 | 34.0 | 2550 | 0.3679 | 0.8619 |
102
+ | 0.3888 | 35.0 | 2625 | 0.3683 | 0.8586 |
103
+ | 0.3956 | 36.0 | 2700 | 0.3659 | 0.8636 |
104
+ | 0.3691 | 37.0 | 2775 | 0.3660 | 0.8636 |
105
+ | 0.4229 | 38.0 | 2850 | 0.3645 | 0.8669 |
106
+ | 0.308 | 39.0 | 2925 | 0.3651 | 0.8636 |
107
+ | 0.382 | 40.0 | 3000 | 0.3644 | 0.8602 |
108
+ | 0.4135 | 41.0 | 3075 | 0.3618 | 0.8652 |
109
+ | 0.3791 | 42.0 | 3150 | 0.3629 | 0.8636 |
110
+ | 0.3729 | 43.0 | 3225 | 0.3622 | 0.8586 |
111
+ | 0.3719 | 44.0 | 3300 | 0.3628 | 0.8669 |
112
+ | 0.3571 | 45.0 | 3375 | 0.3604 | 0.8636 |
113
+ | 0.3721 | 46.0 | 3450 | 0.3598 | 0.8652 |
114
+ | 0.381 | 47.0 | 3525 | 0.3604 | 0.8636 |
115
+ | 0.3882 | 48.0 | 3600 | 0.3603 | 0.8636 |
116
+ | 0.3411 | 49.0 | 3675 | 0.3601 | 0.8636 |
117
+ | 0.3299 | 50.0 | 3750 | 0.3600 | 0.8636 |
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 sha256:62d8d3d05400c719f2e15a13a2645eb8471555a79e0194f2c32acee1b70a7c96
3
  size 343083404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89233c3b2acf2812ab798c69802bc5e9ca9b8992ca540570e65064302f4feaaa
3
  size 343083404