Hugging Face's logo

hkivancoral
/
smids_3x_beit_base_sgd_0001_fold2

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
63349be
•
1 Parent(s): 23ae4a4

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_3x_beit_base_sgd_0001_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: 0.7886855241264559
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_3x_beit_base_sgd_0001_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: 0.5470
36
+ - Accuracy: 0.7887
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: 0.0001
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
+ | 1.1643 | 1.0 | 225 | 1.2557 | 0.3494 |
69
+ | 1.1336 | 2.0 | 450 | 1.1964 | 0.3727 |
70
+ | 1.0702 | 3.0 | 675 | 1.1415 | 0.3960 |
71
+ | 1.0744 | 4.0 | 900 | 1.0897 | 0.4226 |
72
+ | 0.9272 | 5.0 | 1125 | 1.0392 | 0.4526 |
73
+ | 0.9348 | 6.0 | 1350 | 0.9924 | 0.4908 |
74
+ | 0.9221 | 7.0 | 1575 | 0.9474 | 0.5374 |
75
+ | 0.8806 | 8.0 | 1800 | 0.9069 | 0.5890 |
76
+ | 0.8541 | 9.0 | 2025 | 0.8693 | 0.6206 |
77
+ | 0.8102 | 10.0 | 2250 | 0.8367 | 0.6439 |
78
+ | 0.7893 | 11.0 | 2475 | 0.8072 | 0.6672 |
79
+ | 0.7786 | 12.0 | 2700 | 0.7812 | 0.6872 |
80
+ | 0.7601 | 13.0 | 2925 | 0.7581 | 0.7038 |
81
+ | 0.7654 | 14.0 | 3150 | 0.7376 | 0.7105 |
82
+ | 0.7556 | 15.0 | 3375 | 0.7195 | 0.7171 |
83
+ | 0.7319 | 16.0 | 3600 | 0.7031 | 0.7321 |
84
+ | 0.6868 | 17.0 | 3825 | 0.6881 | 0.7354 |
85
+ | 0.7278 | 18.0 | 4050 | 0.6745 | 0.7421 |
86
+ | 0.6222 | 19.0 | 4275 | 0.6623 | 0.7454 |
87
+ | 0.6905 | 20.0 | 4500 | 0.6515 | 0.7471 |
88
+ | 0.6715 | 21.0 | 4725 | 0.6419 | 0.7554 |
89
+ | 0.7342 | 22.0 | 4950 | 0.6326 | 0.7554 |
90
+ | 0.6844 | 23.0 | 5175 | 0.6245 | 0.7621 |
91
+ | 0.6577 | 24.0 | 5400 | 0.6173 | 0.7654 |
92
+ | 0.6177 | 25.0 | 5625 | 0.6101 | 0.7687 |
93
+ | 0.647 | 26.0 | 5850 | 0.6037 | 0.7671 |
94
+ | 0.6355 | 27.0 | 6075 | 0.5976 | 0.7704 |
95
+ | 0.6059 | 28.0 | 6300 | 0.5926 | 0.7704 |
96
+ | 0.5954 | 29.0 | 6525 | 0.5873 | 0.7770 |
97
+ | 0.6256 | 30.0 | 6750 | 0.5829 | 0.7787 |
98
+ | 0.6261 | 31.0 | 6975 | 0.5789 | 0.7820 |
99
+ | 0.5804 | 32.0 | 7200 | 0.5748 | 0.7820 |
100
+ | 0.5936 | 33.0 | 7425 | 0.5711 | 0.7854 |
101
+ | 0.5647 | 34.0 | 7650 | 0.5682 | 0.7854 |
102
+ | 0.6238 | 35.0 | 7875 | 0.5657 | 0.7854 |
103
+ | 0.5976 | 36.0 | 8100 | 0.5630 | 0.7854 |
104
+ | 0.5852 | 37.0 | 8325 | 0.5605 | 0.7870 |
105
+ | 0.5826 | 38.0 | 8550 | 0.5584 | 0.7854 |
106
+ | 0.5619 | 39.0 | 8775 | 0.5564 | 0.7854 |
107
+ | 0.5946 | 40.0 | 9000 | 0.5547 | 0.7870 |
108
+ | 0.5381 | 41.0 | 9225 | 0.5529 | 0.7870 |
109
+ | 0.5966 | 42.0 | 9450 | 0.5514 | 0.7870 |
110
+ | 0.588 | 43.0 | 9675 | 0.5504 | 0.7870 |
111
+ | 0.5705 | 44.0 | 9900 | 0.5494 | 0.7854 |
112
+ | 0.6073 | 45.0 | 10125 | 0.5486 | 0.7870 |
113
+ | 0.5915 | 46.0 | 10350 | 0.5480 | 0.7887 |
114
+ | 0.5988 | 47.0 | 10575 | 0.5476 | 0.7887 |
115
+ | 0.542 | 48.0 | 10800 | 0.5472 | 0.7887 |
116
+ | 0.5885 | 49.0 | 11025 | 0.5471 | 0.7887 |
117
+ | 0.5585 | 50.0 | 11250 | 0.5470 | 0.7887 |
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 sha256:2f82d8dde40d00f987d3954aff8823290dc96a233599c27e9ea0f0d6f116ee07
3
  size 343133766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88b491afa82d4fe6a52c14fb0ddaf05ad7f34610f70edd9d1a409be2a5ff984
3
  size 343133766