Hugging Face's logo

hkivancoral
/
hushem_40x_deit_tiny_rms_001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
6dde77b
•
1 Parent(s): f37939b

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: hushem_40x_deit_tiny_rms_001_fold4
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: 0.6904761904761905
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
+ # hushem_40x_deit_tiny_rms_001_fold4
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: 3.6233
36
+ - Accuracy: 0.6905
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
+ | 1.1473 | 1.0 | 219 | 0.8756 | 0.6190 |
69
+ | 0.9719 | 2.0 | 438 | 0.9893 | 0.5714 |
70
+ | 0.7611 | 3.0 | 657 | 0.7217 | 0.7619 |
71
+ | 0.6995 | 4.0 | 876 | 0.7516 | 0.6429 |
72
+ | 0.6928 | 5.0 | 1095 | 1.0447 | 0.5952 |
73
+ | 0.6114 | 6.0 | 1314 | 0.9410 | 0.6667 |
74
+ | 0.4906 | 7.0 | 1533 | 1.4457 | 0.5238 |
75
+ | 0.4956 | 8.0 | 1752 | 1.1229 | 0.6429 |
76
+ | 0.3708 | 9.0 | 1971 | 0.5610 | 0.7381 |
77
+ | 0.3213 | 10.0 | 2190 | 1.1632 | 0.6667 |
78
+ | 0.279 | 11.0 | 2409 | 0.8853 | 0.7381 |
79
+ | 0.26 | 12.0 | 2628 | 1.0316 | 0.6905 |
80
+ | 0.2004 | 13.0 | 2847 | 0.8001 | 0.7619 |
81
+ | 0.2396 | 14.0 | 3066 | 1.0495 | 0.7381 |
82
+ | 0.1937 | 15.0 | 3285 | 1.2736 | 0.7381 |
83
+ | 0.1386 | 16.0 | 3504 | 0.9949 | 0.7381 |
84
+ | 0.1459 | 17.0 | 3723 | 1.2302 | 0.6905 |
85
+ | 0.0754 | 18.0 | 3942 | 1.9238 | 0.6667 |
86
+ | 0.0996 | 19.0 | 4161 | 1.4396 | 0.6905 |
87
+ | 0.0438 | 20.0 | 4380 | 1.1891 | 0.7143 |
88
+ | 0.1349 | 21.0 | 4599 | 1.4228 | 0.7381 |
89
+ | 0.0058 | 22.0 | 4818 | 1.2340 | 0.7619 |
90
+ | 0.0345 | 23.0 | 5037 | 1.1630 | 0.6667 |
91
+ | 0.0461 | 24.0 | 5256 | 2.1318 | 0.6429 |
92
+ | 0.0595 | 25.0 | 5475 | 1.7499 | 0.6905 |
93
+ | 0.004 | 26.0 | 5694 | 1.6488 | 0.6905 |
94
+ | 0.0014 | 27.0 | 5913 | 1.8134 | 0.6905 |
95
+ | 0.0335 | 28.0 | 6132 | 2.3351 | 0.6905 |
96
+ | 0.0071 | 29.0 | 6351 | 2.4170 | 0.5714 |
97
+ | 0.0006 | 30.0 | 6570 | 1.5965 | 0.7381 |
98
+ | 0.0014 | 31.0 | 6789 | 2.0937 | 0.7381 |
99
+ | 0.0419 | 32.0 | 7008 | 1.8845 | 0.6905 |
100
+ | 0.042 | 33.0 | 7227 | 3.6234 | 0.6190 |
101
+ | 0.0018 | 34.0 | 7446 | 1.5177 | 0.6905 |
102
+ | 0.027 | 35.0 | 7665 | 1.3824 | 0.7857 |
103
+ | 0.0005 | 36.0 | 7884 | 2.3915 | 0.7619 |
104
+ | 0.0226 | 37.0 | 8103 | 1.6001 | 0.7381 |
105
+ | 0.001 | 38.0 | 8322 | 2.3141 | 0.6905 |
106
+ | 0.0 | 39.0 | 8541 | 2.5460 | 0.7143 |
107
+ | 0.0 | 40.0 | 8760 | 2.6724 | 0.6905 |
108
+ | 0.0 | 41.0 | 8979 | 2.7005 | 0.6905 |
109
+ | 0.0 | 42.0 | 9198 | 2.8171 | 0.7143 |
110
+ | 0.0 | 43.0 | 9417 | 2.9876 | 0.7143 |
111
+ | 0.0 | 44.0 | 9636 | 3.1125 | 0.7143 |
112
+ | 0.0 | 45.0 | 9855 | 3.2479 | 0.7143 |
113
+ | 0.0 | 46.0 | 10074 | 3.4344 | 0.7143 |
114
+ | 0.0 | 47.0 | 10293 | 3.4573 | 0.7143 |
115
+ | 0.0 | 48.0 | 10512 | 3.5752 | 0.6905 |
116
+ | 0.0 | 49.0 | 10731 | 3.5910 | 0.6905 |
117
+ | 0.0 | 50.0 | 10950 | 3.6233 | 0.6905 |
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 sha256:1099437d207fe66bf294a447bd5a8d141bc68fc5bba7f4f1243520bd943b10ee
3
  size 22168618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c940d9d5f41e3d87013f62b40bc9884e78aa3f02fb585f64935e48a86b30cc3
3
  size 22168618