Hugging Face's logo

hkivancoral
/
hushem_5x_beit_base_sgd_00001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
35a3b65
•
1 Parent(s): 79b946c

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov29_02-29-23_ac8792add2e0/events.out.tfevents.1701224963.ac8792add2e0.2336.12 +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_sgd_00001_fold5
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: 0.24390243902439024
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_00001_fold5
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: 1.6137
36
+ - Accuracy: 0.2439
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: 1e-05
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
+ | 1.5748 | 1.0 | 28 | 1.6349 | 0.2439 |
69
+ | 1.5498 | 2.0 | 56 | 1.6339 | 0.2439 |
70
+ | 1.5458 | 3.0 | 84 | 1.6329 | 0.2439 |
71
+ | 1.5997 | 4.0 | 112 | 1.6319 | 0.2439 |
72
+ | 1.5518 | 5.0 | 140 | 1.6310 | 0.2439 |
73
+ | 1.6078 | 6.0 | 168 | 1.6301 | 0.2439 |
74
+ | 1.6054 | 7.0 | 196 | 1.6292 | 0.2439 |
75
+ | 1.5635 | 8.0 | 224 | 1.6284 | 0.2439 |
76
+ | 1.5412 | 9.0 | 252 | 1.6276 | 0.2439 |
77
+ | 1.5684 | 10.0 | 280 | 1.6268 | 0.2439 |
78
+ | 1.5211 | 11.0 | 308 | 1.6261 | 0.2439 |
79
+ | 1.5857 | 12.0 | 336 | 1.6254 | 0.2439 |
80
+ | 1.5804 | 13.0 | 364 | 1.6248 | 0.2439 |
81
+ | 1.5778 | 14.0 | 392 | 1.6241 | 0.2439 |
82
+ | 1.5905 | 15.0 | 420 | 1.6235 | 0.2439 |
83
+ | 1.5552 | 16.0 | 448 | 1.6228 | 0.2439 |
84
+ | 1.5712 | 17.0 | 476 | 1.6222 | 0.2439 |
85
+ | 1.5113 | 18.0 | 504 | 1.6216 | 0.2439 |
86
+ | 1.5441 | 19.0 | 532 | 1.6210 | 0.2439 |
87
+ | 1.547 | 20.0 | 560 | 1.6205 | 0.2439 |
88
+ | 1.5712 | 21.0 | 588 | 1.6200 | 0.2439 |
89
+ | 1.595 | 22.0 | 616 | 1.6195 | 0.2439 |
90
+ | 1.6001 | 23.0 | 644 | 1.6190 | 0.2439 |
91
+ | 1.6008 | 24.0 | 672 | 1.6185 | 0.2439 |
92
+ | 1.5469 | 25.0 | 700 | 1.6181 | 0.2439 |
93
+ | 1.567 | 26.0 | 728 | 1.6177 | 0.2439 |
94
+ | 1.618 | 27.0 | 756 | 1.6173 | 0.2439 |
95
+ | 1.4849 | 28.0 | 784 | 1.6170 | 0.2439 |
96
+ | 1.5706 | 29.0 | 812 | 1.6166 | 0.2439 |
97
+ | 1.5269 | 30.0 | 840 | 1.6163 | 0.2439 |
98
+ | 1.588 | 31.0 | 868 | 1.6160 | 0.2439 |
99
+ | 1.5207 | 32.0 | 896 | 1.6157 | 0.2439 |
100
+ | 1.5395 | 33.0 | 924 | 1.6155 | 0.2439 |
101
+ | 1.5482 | 34.0 | 952 | 1.6152 | 0.2439 |
102
+ | 1.6004 | 35.0 | 980 | 1.6150 | 0.2439 |
103
+ | 1.5389 | 36.0 | 1008 | 1.6148 | 0.2439 |
104
+ | 1.5566 | 37.0 | 1036 | 1.6146 | 0.2439 |
105
+ | 1.54 | 38.0 | 1064 | 1.6145 | 0.2439 |
106
+ | 1.5715 | 39.0 | 1092 | 1.6143 | 0.2439 |
107
+ | 1.5148 | 40.0 | 1120 | 1.6142 | 0.2439 |
108
+ | 1.5688 | 41.0 | 1148 | 1.6141 | 0.2439 |
109
+ | 1.5803 | 42.0 | 1176 | 1.6140 | 0.2439 |
110
+ | 1.5477 | 43.0 | 1204 | 1.6139 | 0.2439 |
111
+ | 1.5623 | 44.0 | 1232 | 1.6138 | 0.2439 |
112
+ | 1.5648 | 45.0 | 1260 | 1.6137 | 0.2439 |
113
+ | 1.5331 | 46.0 | 1288 | 1.6137 | 0.2439 |
114
+ | 1.5791 | 47.0 | 1316 | 1.6137 | 0.2439 |
115
+ | 1.5282 | 48.0 | 1344 | 1.6137 | 0.2439 |
116
+ | 1.5715 | 49.0 | 1372 | 1.6137 | 0.2439 |
117
+ | 1.5955 | 50.0 | 1400 | 1.6137 | 0.2439 |
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 sha256:5b8f5cac907bdbd545e0efe7a7cc6171b57bf345f7abcc778fbf40544cc62212
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c1b89cfdec08b36a8b43a9b1689b28d1d4787359e1aba9270bba5f1c30aae0
3
  size 343086480
runs/Nov29_02-29-23_ac8792add2e0/events.out.tfevents.1701224963.ac8792add2e0.2336.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d99e4b43a4ee70adc346729b00233619c81a3bf4ab84eccc208c8bf1c7fb2782
3
- size 43004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845ae4504e8f6961de4a697e6647599cbb29ec30ecb80689e1c6252d89365149
3
+ size 43358