hkivancoral commited on
Commit
9208016
1 Parent(s): 612a96e

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_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: 0.8166666666666667
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_fold5
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: 1.6588
36
+ - Accuracy: 0.8167
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
+ | 0.972 | 1.0 | 225 | 1.0247 | 0.3783 |
69
+ | 0.8568 | 2.0 | 450 | 0.8274 | 0.5533 |
70
+ | 0.8081 | 3.0 | 675 | 0.8040 | 0.5483 |
71
+ | 0.7625 | 4.0 | 900 | 0.7546 | 0.5933 |
72
+ | 0.7576 | 5.0 | 1125 | 0.7605 | 0.64 |
73
+ | 0.6884 | 6.0 | 1350 | 0.7873 | 0.5983 |
74
+ | 0.766 | 7.0 | 1575 | 0.7270 | 0.6583 |
75
+ | 0.6978 | 8.0 | 1800 | 0.7176 | 0.64 |
76
+ | 0.6732 | 9.0 | 2025 | 0.7347 | 0.645 |
77
+ | 0.6839 | 10.0 | 2250 | 0.7289 | 0.6267 |
78
+ | 0.6569 | 11.0 | 2475 | 0.6542 | 0.7183 |
79
+ | 0.6318 | 12.0 | 2700 | 0.6186 | 0.7283 |
80
+ | 0.6796 | 13.0 | 2925 | 0.6663 | 0.71 |
81
+ | 0.6092 | 14.0 | 3150 | 0.6155 | 0.7117 |
82
+ | 0.6242 | 15.0 | 3375 | 0.6625 | 0.6967 |
83
+ | 0.5314 | 16.0 | 3600 | 0.5775 | 0.7533 |
84
+ | 0.5564 | 17.0 | 3825 | 0.5848 | 0.7533 |
85
+ | 0.5755 | 18.0 | 4050 | 0.5751 | 0.7583 |
86
+ | 0.5677 | 19.0 | 4275 | 0.5731 | 0.7617 |
87
+ | 0.5761 | 20.0 | 4500 | 0.5204 | 0.785 |
88
+ | 0.4524 | 21.0 | 4725 | 0.5722 | 0.75 |
89
+ | 0.4782 | 22.0 | 4950 | 0.5385 | 0.7733 |
90
+ | 0.4908 | 23.0 | 5175 | 0.5176 | 0.7933 |
91
+ | 0.5195 | 24.0 | 5400 | 0.5242 | 0.7917 |
92
+ | 0.4871 | 25.0 | 5625 | 0.5298 | 0.7983 |
93
+ | 0.5293 | 26.0 | 5850 | 0.5066 | 0.8 |
94
+ | 0.504 | 27.0 | 6075 | 0.4969 | 0.81 |
95
+ | 0.4467 | 28.0 | 6300 | 0.5630 | 0.79 |
96
+ | 0.4177 | 29.0 | 6525 | 0.5247 | 0.8067 |
97
+ | 0.3722 | 30.0 | 6750 | 0.5359 | 0.8117 |
98
+ | 0.3286 | 31.0 | 6975 | 0.5623 | 0.795 |
99
+ | 0.3205 | 32.0 | 7200 | 0.5594 | 0.8017 |
100
+ | 0.3627 | 33.0 | 7425 | 0.5968 | 0.815 |
101
+ | 0.2799 | 34.0 | 7650 | 0.5562 | 0.825 |
102
+ | 0.2664 | 35.0 | 7875 | 0.6268 | 0.81 |
103
+ | 0.2603 | 36.0 | 8100 | 0.6102 | 0.82 |
104
+ | 0.2382 | 37.0 | 8325 | 0.6448 | 0.8083 |
105
+ | 0.1999 | 38.0 | 8550 | 0.7396 | 0.825 |
106
+ | 0.1413 | 39.0 | 8775 | 0.7329 | 0.8167 |
107
+ | 0.1906 | 40.0 | 9000 | 0.8804 | 0.81 |
108
+ | 0.1179 | 41.0 | 9225 | 0.7998 | 0.84 |
109
+ | 0.0965 | 42.0 | 9450 | 0.9317 | 0.8217 |
110
+ | 0.0987 | 43.0 | 9675 | 0.9015 | 0.825 |
111
+ | 0.1035 | 44.0 | 9900 | 1.1023 | 0.8083 |
112
+ | 0.0347 | 45.0 | 10125 | 1.2315 | 0.82 |
113
+ | 0.054 | 46.0 | 10350 | 1.2317 | 0.8083 |
114
+ | 0.014 | 47.0 | 10575 | 1.4229 | 0.82 |
115
+ | 0.0044 | 48.0 | 10800 | 1.5732 | 0.8217 |
116
+ | 0.0012 | 49.0 | 11025 | 1.6140 | 0.8183 |
117
+ | 0.0003 | 50.0 | 11250 | 1.6588 | 0.8167 |
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 sha256:7e3a1a22f99cef1a8cf592a238195c1787e5e1ddec316e302c4f5e2aa287ecfe
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d767c39cd40265078d4ce97084b7fd9c816eb3fc1c4b23b374dd445b15437ebb
3
  size 22167850