hkivancoral commited on
Commit
bb6835b
1 Parent(s): 516db82

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_3x_deit_small_sgd_00001_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: 0.4875207986688852
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_small_sgd_00001_fold2
32
+
33
+ This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.0145
36
+ - Accuracy: 0.4875
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: 1e-05
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
+ | 1.0768 | 1.0 | 225 | 1.0706 | 0.4276 |
69
+ | 1.0941 | 2.0 | 450 | 1.0680 | 0.4293 |
70
+ | 1.0918 | 3.0 | 675 | 1.0655 | 0.4309 |
71
+ | 1.0511 | 4.0 | 900 | 1.0630 | 0.4376 |
72
+ | 1.0876 | 5.0 | 1125 | 1.0606 | 0.4393 |
73
+ | 1.0339 | 6.0 | 1350 | 1.0583 | 0.4393 |
74
+ | 1.0616 | 7.0 | 1575 | 1.0561 | 0.4459 |
75
+ | 1.0897 | 8.0 | 1800 | 1.0540 | 0.4459 |
76
+ | 1.053 | 9.0 | 2025 | 1.0518 | 0.4493 |
77
+ | 1.0515 | 10.0 | 2250 | 1.0498 | 0.4509 |
78
+ | 1.0879 | 11.0 | 2475 | 1.0479 | 0.4542 |
79
+ | 1.0316 | 12.0 | 2700 | 1.0459 | 0.4542 |
80
+ | 1.0424 | 13.0 | 2925 | 1.0441 | 0.4576 |
81
+ | 1.0786 | 14.0 | 3150 | 1.0424 | 0.4609 |
82
+ | 1.061 | 15.0 | 3375 | 1.0407 | 0.4626 |
83
+ | 1.064 | 16.0 | 3600 | 1.0390 | 0.4642 |
84
+ | 1.0184 | 17.0 | 3825 | 1.0374 | 0.4626 |
85
+ | 1.0313 | 18.0 | 4050 | 1.0359 | 0.4626 |
86
+ | 1.0429 | 19.0 | 4275 | 1.0344 | 0.4642 |
87
+ | 1.0308 | 20.0 | 4500 | 1.0330 | 0.4642 |
88
+ | 1.049 | 21.0 | 4725 | 1.0317 | 0.4659 |
89
+ | 1.0164 | 22.0 | 4950 | 1.0304 | 0.4642 |
90
+ | 1.0457 | 23.0 | 5175 | 1.0292 | 0.4642 |
91
+ | 1.0471 | 24.0 | 5400 | 1.0280 | 0.4626 |
92
+ | 1.0294 | 25.0 | 5625 | 1.0269 | 0.4642 |
93
+ | 1.0309 | 26.0 | 5850 | 1.0258 | 0.4659 |
94
+ | 1.0318 | 27.0 | 6075 | 1.0248 | 0.4659 |
95
+ | 1.0436 | 28.0 | 6300 | 1.0238 | 0.4676 |
96
+ | 1.0288 | 29.0 | 6525 | 1.0229 | 0.4725 |
97
+ | 1.0425 | 30.0 | 6750 | 1.0220 | 0.4742 |
98
+ | 1.0267 | 31.0 | 6975 | 1.0212 | 0.4792 |
99
+ | 1.0174 | 32.0 | 7200 | 1.0204 | 0.4809 |
100
+ | 1.0197 | 33.0 | 7425 | 1.0197 | 0.4809 |
101
+ | 1.0313 | 34.0 | 7650 | 1.0190 | 0.4809 |
102
+ | 1.0296 | 35.0 | 7875 | 1.0184 | 0.4809 |
103
+ | 1.0429 | 36.0 | 8100 | 1.0179 | 0.4842 |
104
+ | 1.0312 | 37.0 | 8325 | 1.0173 | 0.4859 |
105
+ | 1.0214 | 38.0 | 8550 | 1.0169 | 0.4842 |
106
+ | 1.0321 | 39.0 | 8775 | 1.0164 | 0.4859 |
107
+ | 1.0329 | 40.0 | 9000 | 1.0161 | 0.4859 |
108
+ | 1.0094 | 41.0 | 9225 | 1.0157 | 0.4875 |
109
+ | 0.9973 | 42.0 | 9450 | 1.0154 | 0.4875 |
110
+ | 1.0326 | 43.0 | 9675 | 1.0152 | 0.4875 |
111
+ | 1.0086 | 44.0 | 9900 | 1.0150 | 0.4875 |
112
+ | 1.0104 | 45.0 | 10125 | 1.0148 | 0.4875 |
113
+ | 1.0211 | 46.0 | 10350 | 1.0147 | 0.4875 |
114
+ | 0.9952 | 47.0 | 10575 | 1.0146 | 0.4875 |
115
+ | 0.9977 | 48.0 | 10800 | 1.0146 | 0.4875 |
116
+ | 1.0187 | 49.0 | 11025 | 1.0146 | 0.4875 |
117
+ | 1.0188 | 50.0 | 11250 | 1.0145 | 0.4875 |
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 sha256:0fc25ed2fad04abddc98cfd567a3a6df426d250fa05b46199048329a1abf65ac
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802507f64f188c3dcbc8919ecc519492040767cfd319176cef2de654fbf6e7fb
3
  size 86735658