Hugging Face's logo

hkivancoral
/
smids_1x_beit_base_adamax_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
7713515
•
1 Parent(s): 425f366

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov30_00-16-26_f888a2bfcfb9/events.out.tfevents.1701303394.f888a2bfcfb9.842.0 +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: smids_1x_beit_base_adamax_001_fold2
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: 0.7903494176372712
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
+ # smids_1x_beit_base_adamax_001_fold2
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: 1.4865
36
+ - Accuracy: 0.7903
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
+ | 0.9007 | 1.0 | 75 | 0.8802 | 0.5191 |
69
+ | 0.7789 | 2.0 | 150 | 0.8973 | 0.5424 |
70
+ | 0.8219 | 3.0 | 225 | 0.7607 | 0.6406 |
71
+ | 0.7838 | 4.0 | 300 | 0.7358 | 0.6522 |
72
+ | 0.6602 | 5.0 | 375 | 0.6978 | 0.6672 |
73
+ | 0.7026 | 6.0 | 450 | 0.6685 | 0.6955 |
74
+ | 0.6394 | 7.0 | 525 | 0.7731 | 0.6589 |
75
+ | 0.6471 | 8.0 | 600 | 0.6234 | 0.7138 |
76
+ | 0.5881 | 9.0 | 675 | 0.6358 | 0.7205 |
77
+ | 0.5254 | 10.0 | 750 | 0.5746 | 0.7671 |
78
+ | 0.5153 | 11.0 | 825 | 0.5501 | 0.7704 |
79
+ | 0.5459 | 12.0 | 900 | 0.5543 | 0.7687 |
80
+ | 0.5526 | 13.0 | 975 | 0.5321 | 0.7737 |
81
+ | 0.5236 | 14.0 | 1050 | 0.5404 | 0.7937 |
82
+ | 0.4317 | 15.0 | 1125 | 0.6220 | 0.7604 |
83
+ | 0.4195 | 16.0 | 1200 | 0.5679 | 0.7854 |
84
+ | 0.3753 | 17.0 | 1275 | 0.6021 | 0.7687 |
85
+ | 0.3821 | 18.0 | 1350 | 0.5958 | 0.7854 |
86
+ | 0.3599 | 19.0 | 1425 | 0.6478 | 0.7837 |
87
+ | 0.2813 | 20.0 | 1500 | 0.6634 | 0.7671 |
88
+ | 0.224 | 21.0 | 1575 | 0.6766 | 0.7820 |
89
+ | 0.2635 | 22.0 | 1650 | 0.6781 | 0.7870 |
90
+ | 0.1832 | 23.0 | 1725 | 0.8041 | 0.7604 |
91
+ | 0.1751 | 24.0 | 1800 | 0.8069 | 0.7671 |
92
+ | 0.2421 | 25.0 | 1875 | 0.8820 | 0.7737 |
93
+ | 0.2115 | 26.0 | 1950 | 0.8838 | 0.7970 |
94
+ | 0.1798 | 27.0 | 2025 | 0.8954 | 0.7787 |
95
+ | 0.1341 | 28.0 | 2100 | 1.0505 | 0.7987 |
96
+ | 0.0669 | 29.0 | 2175 | 1.2992 | 0.7770 |
97
+ | 0.0892 | 30.0 | 2250 | 1.1168 | 0.7987 |
98
+ | 0.1159 | 31.0 | 2325 | 1.2066 | 0.7870 |
99
+ | 0.1289 | 32.0 | 2400 | 1.5859 | 0.7687 |
100
+ | 0.0687 | 33.0 | 2475 | 1.1777 | 0.7887 |
101
+ | 0.0226 | 34.0 | 2550 | 1.4423 | 0.7854 |
102
+ | 0.04 | 35.0 | 2625 | 1.4594 | 0.7870 |
103
+ | 0.0552 | 36.0 | 2700 | 1.3867 | 0.7820 |
104
+ | 0.0439 | 37.0 | 2775 | 1.4599 | 0.7720 |
105
+ | 0.0308 | 38.0 | 2850 | 1.4968 | 0.7903 |
106
+ | 0.0564 | 39.0 | 2925 | 1.5256 | 0.7953 |
107
+ | 0.0227 | 40.0 | 3000 | 1.4454 | 0.7953 |
108
+ | 0.0214 | 41.0 | 3075 | 1.3100 | 0.8087 |
109
+ | 0.0167 | 42.0 | 3150 | 1.4699 | 0.7987 |
110
+ | 0.0299 | 43.0 | 3225 | 1.4525 | 0.7903 |
111
+ | 0.0171 | 44.0 | 3300 | 1.3889 | 0.8053 |
112
+ | 0.011 | 45.0 | 3375 | 1.3819 | 0.7920 |
113
+ | 0.014 | 46.0 | 3450 | 1.5122 | 0.7903 |
114
+ | 0.0198 | 47.0 | 3525 | 1.4328 | 0.7920 |
115
+ | 0.0085 | 48.0 | 3600 | 1.5057 | 0.7920 |
116
+ | 0.0028 | 49.0 | 3675 | 1.4856 | 0.7903 |
117
+ | 0.0049 | 50.0 | 3750 | 1.4865 | 0.7903 |
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:aef2858f5f246929b64ff3b5e70431d2b2b3adc62f1e1c409ef51bab006376be
3
  size 343083404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bca16d86cc045cff43a33a1a5c6d6208cf8ded46192996ebb96f2b075dbfa0f
3
  size 343083404
runs/Nov30_00-16-26_f888a2bfcfb9/events.out.tfevents.1701303394.f888a2bfcfb9.842.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:755b42c8bdc435b1ec9dedb47d9b92737f0c809b774c0f2471651f0de3767e62
3
- size 79877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b08ab8cc1d0ee6901467ec653ea6b00010afaf3d1fb04b54bf7704519c2dc56
3
+ size 80231