hkivancoral commited on
Commit
50eb49d
1 Parent(s): c38a259

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: facebook/deit-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_tiny_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: 0.7016666666666667
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_deit_tiny_rms_001_fold3
32
+
33
+ This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.7451
36
+ - Accuracy: 0.7017
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
+ | 1.0251 | 1.0 | 225 | 0.9264 | 0.5433 |
69
+ | 0.8762 | 2.0 | 450 | 0.9033 | 0.5383 |
70
+ | 0.9046 | 3.0 | 675 | 0.8597 | 0.52 |
71
+ | 0.8168 | 4.0 | 900 | 0.8502 | 0.5867 |
72
+ | 0.8182 | 5.0 | 1125 | 0.8396 | 0.5417 |
73
+ | 0.8366 | 6.0 | 1350 | 0.8032 | 0.64 |
74
+ | 0.7873 | 7.0 | 1575 | 0.7872 | 0.6367 |
75
+ | 0.8222 | 8.0 | 1800 | 0.7892 | 0.605 |
76
+ | 0.8096 | 9.0 | 2025 | 0.8074 | 0.63 |
77
+ | 0.7866 | 10.0 | 2250 | 0.8155 | 0.5667 |
78
+ | 0.7895 | 11.0 | 2475 | 0.7692 | 0.6433 |
79
+ | 0.7721 | 12.0 | 2700 | 0.8106 | 0.6017 |
80
+ | 0.781 | 13.0 | 2925 | 0.7742 | 0.6533 |
81
+ | 0.7888 | 14.0 | 3150 | 0.7929 | 0.6117 |
82
+ | 0.7617 | 15.0 | 3375 | 0.7600 | 0.6683 |
83
+ | 0.8324 | 16.0 | 3600 | 0.7701 | 0.6433 |
84
+ | 0.7598 | 17.0 | 3825 | 0.8095 | 0.6333 |
85
+ | 0.7476 | 18.0 | 4050 | 0.7803 | 0.6033 |
86
+ | 0.7071 | 19.0 | 4275 | 0.7505 | 0.6683 |
87
+ | 0.7193 | 20.0 | 4500 | 0.7784 | 0.6183 |
88
+ | 0.6927 | 21.0 | 4725 | 0.7879 | 0.6467 |
89
+ | 0.666 | 22.0 | 4950 | 0.7212 | 0.6967 |
90
+ | 0.6763 | 23.0 | 5175 | 0.7194 | 0.6833 |
91
+ | 0.6715 | 24.0 | 5400 | 0.7919 | 0.6367 |
92
+ | 0.7294 | 25.0 | 5625 | 0.7785 | 0.6733 |
93
+ | 0.6936 | 26.0 | 5850 | 0.7216 | 0.6983 |
94
+ | 0.6322 | 27.0 | 6075 | 0.8000 | 0.6833 |
95
+ | 0.6761 | 28.0 | 6300 | 0.7942 | 0.6183 |
96
+ | 0.688 | 29.0 | 6525 | 0.7281 | 0.6567 |
97
+ | 0.6228 | 30.0 | 6750 | 0.7332 | 0.6567 |
98
+ | 0.6366 | 31.0 | 6975 | 0.7601 | 0.6717 |
99
+ | 0.6176 | 32.0 | 7200 | 0.7157 | 0.6883 |
100
+ | 0.6636 | 33.0 | 7425 | 0.7555 | 0.6567 |
101
+ | 0.6315 | 34.0 | 7650 | 0.7242 | 0.665 |
102
+ | 0.5915 | 35.0 | 7875 | 0.6940 | 0.6783 |
103
+ | 0.6259 | 36.0 | 8100 | 0.6760 | 0.6917 |
104
+ | 0.6325 | 37.0 | 8325 | 0.6834 | 0.6967 |
105
+ | 0.5846 | 38.0 | 8550 | 0.7137 | 0.6733 |
106
+ | 0.6018 | 39.0 | 8775 | 0.6801 | 0.6933 |
107
+ | 0.5692 | 40.0 | 9000 | 0.6837 | 0.6883 |
108
+ | 0.5234 | 41.0 | 9225 | 0.6917 | 0.6833 |
109
+ | 0.5543 | 42.0 | 9450 | 0.6614 | 0.7017 |
110
+ | 0.5363 | 43.0 | 9675 | 0.6720 | 0.7017 |
111
+ | 0.5474 | 44.0 | 9900 | 0.6703 | 0.7067 |
112
+ | 0.5234 | 45.0 | 10125 | 0.7035 | 0.6983 |
113
+ | 0.4923 | 46.0 | 10350 | 0.7111 | 0.7017 |
114
+ | 0.5435 | 47.0 | 10575 | 0.6985 | 0.7133 |
115
+ | 0.4932 | 48.0 | 10800 | 0.7085 | 0.7133 |
116
+ | 0.486 | 49.0 | 11025 | 0.7485 | 0.7033 |
117
+ | 0.4701 | 50.0 | 11250 | 0.7451 | 0.7017 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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:fa079ba235741ae77148a7561bd79355a05b93c19d4cdd3d67946e5e6164c658
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22733aa94c46aa82acd9c8d9b7395d29bab2b378f02483eae5b3fd2f67f306a8
3
  size 22167850