Hugging Face's logo

hkivancoral
/
smids_5x_beit_base_rms_001_fold3

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
b4042c6
•
1 Parent(s): c7e081d

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +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: smids_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: 0.7883333333333333
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_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: 1.2450
36
+ - Accuracy: 0.7883
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
+ | 0.8383 | 1.0 | 375 | 0.9251 | 0.4967 |
69
+ | 0.7811 | 2.0 | 750 | 0.8274 | 0.55 |
70
+ | 0.7757 | 3.0 | 1125 | 0.8322 | 0.55 |
71
+ | 0.774 | 4.0 | 1500 | 0.7903 | 0.5667 |
72
+ | 0.7988 | 5.0 | 1875 | 0.7818 | 0.59 |
73
+ | 0.7926 | 6.0 | 2250 | 0.7711 | 0.595 |
74
+ | 0.7549 | 7.0 | 2625 | 0.7682 | 0.6267 |
75
+ | 0.7997 | 8.0 | 3000 | 0.7569 | 0.61 |
76
+ | 0.6926 | 9.0 | 3375 | 0.7561 | 0.6417 |
77
+ | 0.7413 | 10.0 | 3750 | 0.7251 | 0.6567 |
78
+ | 0.6722 | 11.0 | 4125 | 0.7285 | 0.6533 |
79
+ | 0.7582 | 12.0 | 4500 | 0.7029 | 0.66 |
80
+ | 0.6728 | 13.0 | 4875 | 0.7283 | 0.6433 |
81
+ | 0.6373 | 14.0 | 5250 | 0.7252 | 0.6333 |
82
+ | 0.648 | 15.0 | 5625 | 0.7000 | 0.67 |
83
+ | 0.6675 | 16.0 | 6000 | 0.7072 | 0.6683 |
84
+ | 0.7316 | 17.0 | 6375 | 0.7063 | 0.6717 |
85
+ | 0.7151 | 18.0 | 6750 | 0.6856 | 0.6683 |
86
+ | 0.6082 | 19.0 | 7125 | 0.6800 | 0.6817 |
87
+ | 0.6879 | 20.0 | 7500 | 0.6816 | 0.6733 |
88
+ | 0.5586 | 21.0 | 7875 | 0.6735 | 0.695 |
89
+ | 0.6065 | 22.0 | 8250 | 0.6507 | 0.71 |
90
+ | 0.5783 | 23.0 | 8625 | 0.6597 | 0.69 |
91
+ | 0.6456 | 24.0 | 9000 | 0.6102 | 0.74 |
92
+ | 0.5238 | 25.0 | 9375 | 0.6683 | 0.7117 |
93
+ | 0.5326 | 26.0 | 9750 | 0.6240 | 0.7183 |
94
+ | 0.5499 | 27.0 | 10125 | 0.6403 | 0.7083 |
95
+ | 0.5607 | 28.0 | 10500 | 0.5945 | 0.7417 |
96
+ | 0.4887 | 29.0 | 10875 | 0.6536 | 0.71 |
97
+ | 0.5354 | 30.0 | 11250 | 0.5785 | 0.725 |
98
+ | 0.5136 | 31.0 | 11625 | 0.6072 | 0.7517 |
99
+ | 0.5448 | 32.0 | 12000 | 0.6265 | 0.7383 |
100
+ | 0.4542 | 33.0 | 12375 | 0.6265 | 0.7417 |
101
+ | 0.4208 | 34.0 | 12750 | 0.6113 | 0.745 |
102
+ | 0.3509 | 35.0 | 13125 | 0.6279 | 0.7467 |
103
+ | 0.4112 | 36.0 | 13500 | 0.6145 | 0.74 |
104
+ | 0.3719 | 37.0 | 13875 | 0.6674 | 0.745 |
105
+ | 0.3029 | 38.0 | 14250 | 0.6977 | 0.7583 |
106
+ | 0.3416 | 39.0 | 14625 | 0.6751 | 0.7717 |
107
+ | 0.3246 | 40.0 | 15000 | 0.6878 | 0.7633 |
108
+ | 0.2432 | 41.0 | 15375 | 0.6417 | 0.79 |
109
+ | 0.2014 | 42.0 | 15750 | 0.7882 | 0.78 |
110
+ | 0.2354 | 43.0 | 16125 | 0.8175 | 0.7817 |
111
+ | 0.1797 | 44.0 | 16500 | 0.8553 | 0.79 |
112
+ | 0.1419 | 45.0 | 16875 | 0.9481 | 0.765 |
113
+ | 0.1815 | 46.0 | 17250 | 1.0306 | 0.765 |
114
+ | 0.1604 | 47.0 | 17625 | 1.0263 | 0.765 |
115
+ | 0.103 | 48.0 | 18000 | 1.1281 | 0.7833 |
116
+ | 0.0441 | 49.0 | 18375 | 1.2055 | 0.79 |
117
+ | 0.0741 | 50.0 | 18750 | 1.2450 | 0.7883 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1b7fbc9d7075b3435bb5cfb6bafd6d2fdb3a1cb6fd77cc76a1c80ba0154bf6e
3
  size 343133766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6db8c996f995ffa57d6da66d784e34fa177721eb77f303f49c5ee3b515a5b58
3
  size 343133766