Hugging Face's logo

hkivancoral
/
hushem_5x_beit_base_rms_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
78f745b
·
1 Parent(s): ce364bd

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov29_04-05-25_ac8792add2e0/events.out.tfevents.1701230726.ac8792add2e0.2336.15 +2 -2
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_rms_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: 0.627906976744186
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_rms_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: 1.4768
36
+ - Accuracy: 0.6279
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
+ | 1.51 | 1.0 | 28 | 1.6351 | 0.2558 |
69
+ | 1.3869 | 2.0 | 56 | 1.4127 | 0.2558 |
70
+ | 1.3848 | 3.0 | 84 | 1.3895 | 0.2558 |
71
+ | 1.4113 | 4.0 | 112 | 1.3824 | 0.2558 |
72
+ | 1.3569 | 5.0 | 140 | 1.4121 | 0.2326 |
73
+ | 1.4625 | 6.0 | 168 | 1.3739 | 0.2326 |
74
+ | 1.3804 | 7.0 | 196 | 1.2185 | 0.5349 |
75
+ | 1.1352 | 8.0 | 224 | 1.1411 | 0.4884 |
76
+ | 1.0899 | 9.0 | 252 | 1.2426 | 0.3953 |
77
+ | 1.0945 | 10.0 | 280 | 1.1820 | 0.3488 |
78
+ | 1.1149 | 11.0 | 308 | 1.4574 | 0.3023 |
79
+ | 0.9942 | 12.0 | 336 | 1.4728 | 0.3256 |
80
+ | 1.0204 | 13.0 | 364 | 0.9801 | 0.5581 |
81
+ | 0.9987 | 14.0 | 392 | 1.0096 | 0.5349 |
82
+ | 1.0664 | 15.0 | 420 | 1.0007 | 0.5814 |
83
+ | 0.9463 | 16.0 | 448 | 1.2188 | 0.3953 |
84
+ | 0.9756 | 17.0 | 476 | 1.1284 | 0.5116 |
85
+ | 0.9698 | 18.0 | 504 | 1.4394 | 0.4419 |
86
+ | 1.061 | 19.0 | 532 | 1.1162 | 0.4884 |
87
+ | 0.8426 | 20.0 | 560 | 1.9296 | 0.3721 |
88
+ | 0.876 | 21.0 | 588 | 1.0070 | 0.5581 |
89
+ | 0.8908 | 22.0 | 616 | 1.2196 | 0.5349 |
90
+ | 0.8599 | 23.0 | 644 | 0.9502 | 0.6047 |
91
+ | 0.8338 | 24.0 | 672 | 0.8737 | 0.6279 |
92
+ | 0.785 | 25.0 | 700 | 1.1006 | 0.5814 |
93
+ | 0.82 | 26.0 | 728 | 1.0398 | 0.5814 |
94
+ | 0.8016 | 27.0 | 756 | 1.6671 | 0.3256 |
95
+ | 0.8574 | 28.0 | 784 | 1.1704 | 0.6279 |
96
+ | 0.8104 | 29.0 | 812 | 1.0502 | 0.6279 |
97
+ | 0.7421 | 30.0 | 840 | 0.9270 | 0.5814 |
98
+ | 0.7093 | 31.0 | 868 | 1.8057 | 0.4186 |
99
+ | 0.7469 | 32.0 | 896 | 0.9665 | 0.5814 |
100
+ | 0.7175 | 33.0 | 924 | 0.8190 | 0.6512 |
101
+ | 0.7129 | 34.0 | 952 | 1.0680 | 0.6279 |
102
+ | 0.7793 | 35.0 | 980 | 1.0966 | 0.5581 |
103
+ | 0.6879 | 36.0 | 1008 | 0.9990 | 0.5814 |
104
+ | 0.7016 | 37.0 | 1036 | 1.7556 | 0.4884 |
105
+ | 0.6238 | 38.0 | 1064 | 1.5792 | 0.4651 |
106
+ | 0.6025 | 39.0 | 1092 | 1.1502 | 0.6047 |
107
+ | 0.7264 | 40.0 | 1120 | 1.3317 | 0.5349 |
108
+ | 0.6063 | 41.0 | 1148 | 1.5492 | 0.5116 |
109
+ | 0.5816 | 42.0 | 1176 | 1.5787 | 0.5814 |
110
+ | 0.4627 | 43.0 | 1204 | 1.1301 | 0.6047 |
111
+ | 0.4652 | 44.0 | 1232 | 1.5008 | 0.6279 |
112
+ | 0.3885 | 45.0 | 1260 | 1.3167 | 0.6279 |
113
+ | 0.4003 | 46.0 | 1288 | 1.3851 | 0.6512 |
114
+ | 0.3882 | 47.0 | 1316 | 1.4601 | 0.6047 |
115
+ | 0.353 | 48.0 | 1344 | 1.4699 | 0.6279 |
116
+ | 0.3487 | 49.0 | 1372 | 1.4768 | 0.6279 |
117
+ | 0.2789 | 50.0 | 1400 | 1.4768 | 0.6279 |
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:d781d2a49479c5111c738cd689477fecf4ce839c5e71fbb2fbd3087312dcead9
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539a2201c2d85267c80d6ac5e7edb85b860267f71263ac7f7199ba01f86bdd57
3
  size 343086480
runs/Nov29_04-05-25_ac8792add2e0/events.out.tfevents.1701230726.ac8792add2e0.2336.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdc5c4f36bf1cbc09e7b5fff3bf7b5536fbb65d2ab77092b8d65fabefd5da801
3
- size 42998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27eb5db7348acaea3808fed2023a4f72a138b07e604b36aa98b60eaa28881610
3
+ size 43352