hkivancoral commited on
Commit
0725285
·
1 Parent(s): 18a193d

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_rms_001_fold1
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: 0.7662771285475793
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_rms_001_fold1
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: 1.0295
36
+ - Accuracy: 0.7663
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
+ | 0.9037 | 1.0 | 226 | 1.1611 | 0.4224 |
69
+ | 0.8436 | 2.0 | 452 | 0.8419 | 0.5442 |
70
+ | 0.8202 | 3.0 | 678 | 0.8414 | 0.5359 |
71
+ | 0.8734 | 4.0 | 904 | 0.8332 | 0.5326 |
72
+ | 0.8282 | 5.0 | 1130 | 0.7907 | 0.6127 |
73
+ | 0.8721 | 6.0 | 1356 | 0.8061 | 0.5559 |
74
+ | 0.7744 | 7.0 | 1582 | 0.7612 | 0.6260 |
75
+ | 0.7444 | 8.0 | 1808 | 0.8606 | 0.5492 |
76
+ | 0.7266 | 9.0 | 2034 | 0.7492 | 0.6427 |
77
+ | 0.7385 | 10.0 | 2260 | 0.7643 | 0.6344 |
78
+ | 0.6851 | 11.0 | 2486 | 0.7983 | 0.5843 |
79
+ | 0.6844 | 12.0 | 2712 | 0.7946 | 0.6561 |
80
+ | 0.6727 | 13.0 | 2938 | 0.8087 | 0.6244 |
81
+ | 0.6244 | 14.0 | 3164 | 0.6709 | 0.6912 |
82
+ | 0.6712 | 15.0 | 3390 | 0.6742 | 0.7095 |
83
+ | 0.6346 | 16.0 | 3616 | 0.6684 | 0.7162 |
84
+ | 0.5408 | 17.0 | 3842 | 0.6615 | 0.7028 |
85
+ | 0.63 | 18.0 | 4068 | 0.6480 | 0.7295 |
86
+ | 0.6263 | 19.0 | 4294 | 0.7205 | 0.6611 |
87
+ | 0.5327 | 20.0 | 4520 | 0.6519 | 0.7078 |
88
+ | 0.6622 | 21.0 | 4746 | 0.6350 | 0.7179 |
89
+ | 0.6299 | 22.0 | 4972 | 0.8817 | 0.6210 |
90
+ | 0.6304 | 23.0 | 5198 | 0.6476 | 0.7362 |
91
+ | 0.5526 | 24.0 | 5424 | 0.6677 | 0.7145 |
92
+ | 0.6295 | 25.0 | 5650 | 0.6118 | 0.7546 |
93
+ | 0.6308 | 26.0 | 5876 | 0.6212 | 0.7362 |
94
+ | 0.5383 | 27.0 | 6102 | 0.7015 | 0.7179 |
95
+ | 0.5618 | 28.0 | 6328 | 0.8218 | 0.6711 |
96
+ | 0.4879 | 29.0 | 6554 | 0.7043 | 0.6928 |
97
+ | 0.5827 | 30.0 | 6780 | 0.6552 | 0.7229 |
98
+ | 0.5364 | 31.0 | 7006 | 0.6340 | 0.7379 |
99
+ | 0.4905 | 32.0 | 7232 | 0.6047 | 0.7529 |
100
+ | 0.4492 | 33.0 | 7458 | 0.7039 | 0.7028 |
101
+ | 0.4914 | 34.0 | 7684 | 0.6660 | 0.7379 |
102
+ | 0.3519 | 35.0 | 7910 | 0.6494 | 0.7479 |
103
+ | 0.3791 | 36.0 | 8136 | 0.6497 | 0.7513 |
104
+ | 0.4111 | 37.0 | 8362 | 0.6075 | 0.7646 |
105
+ | 0.4433 | 38.0 | 8588 | 0.6728 | 0.7679 |
106
+ | 0.3357 | 39.0 | 8814 | 0.6576 | 0.7529 |
107
+ | 0.3901 | 40.0 | 9040 | 0.6972 | 0.7596 |
108
+ | 0.4094 | 41.0 | 9266 | 0.6481 | 0.7696 |
109
+ | 0.3576 | 42.0 | 9492 | 0.6871 | 0.7746 |
110
+ | 0.335 | 43.0 | 9718 | 0.7307 | 0.7846 |
111
+ | 0.2737 | 44.0 | 9944 | 0.7687 | 0.7746 |
112
+ | 0.3485 | 45.0 | 10170 | 0.7785 | 0.7780 |
113
+ | 0.278 | 46.0 | 10396 | 0.8580 | 0.7730 |
114
+ | 0.2622 | 47.0 | 10622 | 0.8921 | 0.7713 |
115
+ | 0.2496 | 48.0 | 10848 | 0.9544 | 0.7730 |
116
+ | 0.1441 | 49.0 | 11074 | 0.9744 | 0.7730 |
117
+ | 0.1894 | 50.0 | 11300 | 1.0295 | 0.7663 |
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:bb8b97e1d32037b8735ef5d54dd41bb2f9728426545c843b9467c6bc2f8334a5
3
  size 86735658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60218e6f2ba54a70441d8706c0e7e9998bde038df94874126116212bd929c7c
3
  size 86735658