Hugging Face's logo

hkivancoral
/
hushem_5x_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
7534239
·
1 Parent(s): e6140f7

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: hushem_5x_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: 0.7380952380952381
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
+ # hushem_5x_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: 2.1895
36
+ - Accuracy: 0.7381
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
+ | 1.398 | 1.0 | 28 | 1.3161 | 0.2619 |
69
+ | 1.3348 | 2.0 | 56 | 1.1486 | 0.5 |
70
+ | 1.2598 | 3.0 | 84 | 1.2723 | 0.4762 |
71
+ | 1.0258 | 4.0 | 112 | 2.5380 | 0.3571 |
72
+ | 0.9514 | 5.0 | 140 | 0.7752 | 0.6667 |
73
+ | 0.9022 | 6.0 | 168 | 0.7061 | 0.7381 |
74
+ | 0.894 | 7.0 | 196 | 0.9563 | 0.6190 |
75
+ | 0.9803 | 8.0 | 224 | 0.6994 | 0.7381 |
76
+ | 0.8819 | 9.0 | 252 | 0.6742 | 0.7619 |
77
+ | 0.8414 | 10.0 | 280 | 0.7881 | 0.6667 |
78
+ | 0.8005 | 11.0 | 308 | 0.9825 | 0.7143 |
79
+ | 0.8103 | 12.0 | 336 | 0.6127 | 0.7619 |
80
+ | 0.8302 | 13.0 | 364 | 0.8926 | 0.7143 |
81
+ | 0.7477 | 14.0 | 392 | 0.8951 | 0.6190 |
82
+ | 0.7772 | 15.0 | 420 | 0.6142 | 0.7619 |
83
+ | 0.6718 | 16.0 | 448 | 0.6386 | 0.7619 |
84
+ | 0.6971 | 17.0 | 476 | 0.8030 | 0.6429 |
85
+ | 0.6705 | 18.0 | 504 | 0.8028 | 0.6667 |
86
+ | 0.6156 | 19.0 | 532 | 0.8667 | 0.6429 |
87
+ | 0.4804 | 20.0 | 560 | 0.6053 | 0.7381 |
88
+ | 0.3939 | 21.0 | 588 | 0.8598 | 0.7381 |
89
+ | 0.485 | 22.0 | 616 | 0.7061 | 0.7381 |
90
+ | 0.4778 | 23.0 | 644 | 1.0522 | 0.6190 |
91
+ | 0.4222 | 24.0 | 672 | 0.8683 | 0.7381 |
92
+ | 0.2892 | 25.0 | 700 | 1.0772 | 0.7143 |
93
+ | 0.3633 | 26.0 | 728 | 0.8242 | 0.7857 |
94
+ | 0.4528 | 27.0 | 756 | 1.4370 | 0.6667 |
95
+ | 0.2621 | 28.0 | 784 | 1.0095 | 0.8095 |
96
+ | 0.1921 | 29.0 | 812 | 1.3782 | 0.7143 |
97
+ | 0.1811 | 30.0 | 840 | 1.8693 | 0.7143 |
98
+ | 0.1481 | 31.0 | 868 | 1.8742 | 0.7619 |
99
+ | 0.1394 | 32.0 | 896 | 1.7130 | 0.7143 |
100
+ | 0.0623 | 33.0 | 924 | 1.6326 | 0.7619 |
101
+ | 0.1726 | 34.0 | 952 | 1.5273 | 0.7381 |
102
+ | 0.1641 | 35.0 | 980 | 1.3046 | 0.8333 |
103
+ | 0.0573 | 36.0 | 1008 | 2.1424 | 0.6667 |
104
+ | 0.0574 | 37.0 | 1036 | 2.1687 | 0.7143 |
105
+ | 0.0558 | 38.0 | 1064 | 1.6907 | 0.7619 |
106
+ | 0.0165 | 39.0 | 1092 | 2.0112 | 0.7619 |
107
+ | 0.052 | 40.0 | 1120 | 1.7998 | 0.7619 |
108
+ | 0.0524 | 41.0 | 1148 | 2.3373 | 0.7143 |
109
+ | 0.0976 | 42.0 | 1176 | 2.2060 | 0.7381 |
110
+ | 0.0064 | 43.0 | 1204 | 2.2711 | 0.7619 |
111
+ | 0.0205 | 44.0 | 1232 | 2.4091 | 0.7619 |
112
+ | 0.0254 | 45.0 | 1260 | 2.3470 | 0.7381 |
113
+ | 0.0473 | 46.0 | 1288 | 2.3652 | 0.7381 |
114
+ | 0.0464 | 47.0 | 1316 | 2.2959 | 0.7381 |
115
+ | 0.0006 | 48.0 | 1344 | 2.1947 | 0.7381 |
116
+ | 0.0143 | 49.0 | 1372 | 2.1895 | 0.7381 |
117
+ | 0.0223 | 50.0 | 1400 | 2.1895 | 0.7381 |
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 sha256:97ee7ccf749240e6260b76b0c7c6890072fe68940a370413febff3ba419774b8
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33954babc2199893f188741a5275a6d2a9b0ed86efcee328995ae04d7544b836
3
  size 343086480