Hugging Face's logo

hkivancoral
/
hushem_5x_beit_base_adamax_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
beit
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
4457a8b
•
1 Parent(s): 1bff122

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov27_06-27-35_4550fdbe7878/events.out.tfevents.1701066456.4550fdbe7878.67538.4 +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_adamax_001_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: 0.7804878048780488
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_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: 2.4090
36
+ - Accuracy: 0.7805
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
+ | 1.4173 | 1.0 | 28 | 1.3891 | 0.2683 |
69
+ | 1.3694 | 2.0 | 56 | 1.3106 | 0.2927 |
70
+ | 1.1585 | 3.0 | 84 | 1.3727 | 0.5610 |
71
+ | 1.1633 | 4.0 | 112 | 0.9530 | 0.6341 |
72
+ | 1.0808 | 5.0 | 140 | 0.8248 | 0.7073 |
73
+ | 1.0058 | 6.0 | 168 | 0.6596 | 0.7073 |
74
+ | 0.8888 | 7.0 | 196 | 0.8270 | 0.6829 |
75
+ | 0.8643 | 8.0 | 224 | 1.1710 | 0.5122 |
76
+ | 0.8719 | 9.0 | 252 | 0.8636 | 0.6098 |
77
+ | 0.9495 | 10.0 | 280 | 0.6951 | 0.7073 |
78
+ | 0.7539 | 11.0 | 308 | 0.7129 | 0.8049 |
79
+ | 0.7103 | 12.0 | 336 | 1.1463 | 0.5366 |
80
+ | 0.8944 | 13.0 | 364 | 0.9066 | 0.6829 |
81
+ | 0.8497 | 14.0 | 392 | 0.8746 | 0.7073 |
82
+ | 0.79 | 15.0 | 420 | 1.0867 | 0.6341 |
83
+ | 0.7113 | 16.0 | 448 | 0.8154 | 0.7073 |
84
+ | 0.7564 | 17.0 | 476 | 0.7453 | 0.7561 |
85
+ | 0.6147 | 18.0 | 504 | 1.0583 | 0.6098 |
86
+ | 0.7024 | 19.0 | 532 | 0.9615 | 0.6829 |
87
+ | 0.7327 | 20.0 | 560 | 1.0915 | 0.6098 |
88
+ | 0.5576 | 21.0 | 588 | 0.9041 | 0.7561 |
89
+ | 0.4937 | 22.0 | 616 | 1.0076 | 0.8049 |
90
+ | 0.5781 | 23.0 | 644 | 1.0524 | 0.6829 |
91
+ | 0.478 | 24.0 | 672 | 1.0298 | 0.7561 |
92
+ | 0.5392 | 25.0 | 700 | 1.0140 | 0.6585 |
93
+ | 0.3827 | 26.0 | 728 | 1.6432 | 0.7317 |
94
+ | 0.3978 | 27.0 | 756 | 1.4850 | 0.7561 |
95
+ | 0.3605 | 28.0 | 784 | 1.3340 | 0.7805 |
96
+ | 0.2382 | 29.0 | 812 | 1.4757 | 0.7805 |
97
+ | 0.2077 | 30.0 | 840 | 2.1685 | 0.7317 |
98
+ | 0.2429 | 31.0 | 868 | 1.3423 | 0.7805 |
99
+ | 0.2302 | 32.0 | 896 | 1.8898 | 0.7561 |
100
+ | 0.1961 | 33.0 | 924 | 1.4382 | 0.7805 |
101
+ | 0.1775 | 34.0 | 952 | 1.8008 | 0.7561 |
102
+ | 0.1314 | 35.0 | 980 | 1.9048 | 0.7317 |
103
+ | 0.0435 | 36.0 | 1008 | 2.0856 | 0.7317 |
104
+ | 0.1658 | 37.0 | 1036 | 2.4005 | 0.7561 |
105
+ | 0.0258 | 38.0 | 1064 | 2.3634 | 0.7805 |
106
+ | 0.0985 | 39.0 | 1092 | 2.3142 | 0.7561 |
107
+ | 0.0844 | 40.0 | 1120 | 2.5789 | 0.7073 |
108
+ | 0.0832 | 41.0 | 1148 | 2.3270 | 0.7805 |
109
+ | 0.0163 | 42.0 | 1176 | 2.1273 | 0.8293 |
110
+ | 0.0187 | 43.0 | 1204 | 2.3057 | 0.7805 |
111
+ | 0.0207 | 44.0 | 1232 | 2.3431 | 0.7561 |
112
+ | 0.0233 | 45.0 | 1260 | 2.3612 | 0.7317 |
113
+ | 0.0252 | 46.0 | 1288 | 2.4095 | 0.7317 |
114
+ | 0.0208 | 47.0 | 1316 | 2.3721 | 0.7805 |
115
+ | 0.0009 | 48.0 | 1344 | 2.4085 | 0.7805 |
116
+ | 0.0012 | 49.0 | 1372 | 2.4090 | 0.7805 |
117
+ | 0.0004 | 50.0 | 1400 | 2.4090 | 0.7805 |
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 sha256:19e5a37cc2161d62a478f3ebe2069eca88dc332c48dd0509168a113a44865640
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1249f65a6ca7efe3326b8c0b6f17ed261e60eaca1459fcc817c6c5f93072ff
3
  size 343086480
runs/Nov27_06-27-35_4550fdbe7878/events.out.tfevents.1701066456.4550fdbe7878.67538.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f0767cfeba56310c91cb902d1d741b610ba05d92c0f6ae18889045878c1e6f4
3
- size 43007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9165ac40c6152233946e7055f89ecde648e5991788454fa5e801a7261d76684f
3
+ size 43361