Hugging Face's logo

hkivancoral
/
hushem_5x_beit_base_sgd_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
aa5bd7a
•
1 Parent(s): ed42cc8

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_sgd_001_fold3
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: 0.5813953488372093
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_sgd_001_fold3
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: 1.0930
36
+ - Accuracy: 0.5814
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
+ | 1.5405 | 1.0 | 28 | 1.5276 | 0.2791 |
69
+ | 1.4164 | 2.0 | 56 | 1.4818 | 0.2558 |
70
+ | 1.3492 | 3.0 | 84 | 1.4545 | 0.3023 |
71
+ | 1.3001 | 4.0 | 112 | 1.4313 | 0.3256 |
72
+ | 1.2739 | 5.0 | 140 | 1.4088 | 0.3256 |
73
+ | 1.2528 | 6.0 | 168 | 1.3949 | 0.3488 |
74
+ | 1.2748 | 7.0 | 196 | 1.3862 | 0.3953 |
75
+ | 1.2477 | 8.0 | 224 | 1.3731 | 0.3953 |
76
+ | 1.1334 | 9.0 | 252 | 1.3517 | 0.4419 |
77
+ | 1.2313 | 10.0 | 280 | 1.3394 | 0.4419 |
78
+ | 1.1559 | 11.0 | 308 | 1.3288 | 0.4651 |
79
+ | 1.1429 | 12.0 | 336 | 1.3194 | 0.4884 |
80
+ | 1.1222 | 13.0 | 364 | 1.3129 | 0.4884 |
81
+ | 1.1193 | 14.0 | 392 | 1.3031 | 0.4884 |
82
+ | 1.1208 | 15.0 | 420 | 1.2891 | 0.4884 |
83
+ | 1.0856 | 16.0 | 448 | 1.2837 | 0.5116 |
84
+ | 1.0813 | 17.0 | 476 | 1.2664 | 0.4884 |
85
+ | 1.0315 | 18.0 | 504 | 1.2593 | 0.5116 |
86
+ | 1.0461 | 19.0 | 532 | 1.2499 | 0.5349 |
87
+ | 1.0 | 20.0 | 560 | 1.2343 | 0.5349 |
88
+ | 1.0154 | 21.0 | 588 | 1.2288 | 0.5581 |
89
+ | 1.0308 | 22.0 | 616 | 1.2111 | 0.5116 |
90
+ | 0.9899 | 23.0 | 644 | 1.2091 | 0.5349 |
91
+ | 0.9581 | 24.0 | 672 | 1.2017 | 0.4651 |
92
+ | 0.9805 | 25.0 | 700 | 1.1984 | 0.5116 |
93
+ | 0.9484 | 26.0 | 728 | 1.1851 | 0.5116 |
94
+ | 0.9269 | 27.0 | 756 | 1.1745 | 0.5116 |
95
+ | 0.9482 | 28.0 | 784 | 1.1663 | 0.5581 |
96
+ | 0.9417 | 29.0 | 812 | 1.1640 | 0.5116 |
97
+ | 0.8927 | 30.0 | 840 | 1.1540 | 0.5349 |
98
+ | 0.9018 | 31.0 | 868 | 1.1499 | 0.5349 |
99
+ | 0.9337 | 32.0 | 896 | 1.1514 | 0.5116 |
100
+ | 0.8897 | 33.0 | 924 | 1.1407 | 0.5349 |
101
+ | 0.9018 | 34.0 | 952 | 1.1332 | 0.5349 |
102
+ | 0.9545 | 35.0 | 980 | 1.1289 | 0.5581 |
103
+ | 0.8798 | 36.0 | 1008 | 1.1231 | 0.5581 |
104
+ | 0.8701 | 37.0 | 1036 | 1.1207 | 0.5349 |
105
+ | 0.8661 | 38.0 | 1064 | 1.1127 | 0.5581 |
106
+ | 0.8977 | 39.0 | 1092 | 1.1103 | 0.5349 |
107
+ | 0.9369 | 40.0 | 1120 | 1.1062 | 0.5814 |
108
+ | 0.8919 | 41.0 | 1148 | 1.1024 | 0.5814 |
109
+ | 0.8962 | 42.0 | 1176 | 1.0983 | 0.5814 |
110
+ | 0.8751 | 43.0 | 1204 | 1.0966 | 0.5814 |
111
+ | 0.895 | 44.0 | 1232 | 1.0957 | 0.5814 |
112
+ | 0.863 | 45.0 | 1260 | 1.0942 | 0.5814 |
113
+ | 0.8655 | 46.0 | 1288 | 1.0940 | 0.5814 |
114
+ | 0.8681 | 47.0 | 1316 | 1.0932 | 0.5814 |
115
+ | 0.8242 | 48.0 | 1344 | 1.0930 | 0.5814 |
116
+ | 0.8859 | 49.0 | 1372 | 1.0930 | 0.5814 |
117
+ | 0.8974 | 50.0 | 1400 | 1.0930 | 0.5814 |
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 sha256:5e8b27f22c097a924238ad1b1fa5e0997f55ba736aaf1083411d4e8ce5aa3366
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee24cd0859b4f8ea6c233c94a368bf039fc1ac93859c990c871cfaaddf051344
3
  size 343086480