Hugging Face's logo

hkivancoral
/
hushem_5x_deit_small_rms_001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
d10f3e2
•
1 Parent(s): d3a1557

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +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: hushem_5x_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: 0.4444444444444444
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_5x_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: 4.9688
36
+ - Accuracy: 0.4444
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
+ | 1.7253 | 1.0 | 27 | 1.4539 | 0.2444 |
69
+ | 1.4329 | 2.0 | 54 | 1.3827 | 0.3556 |
70
+ | 1.413 | 3.0 | 81 | 1.4287 | 0.2667 |
71
+ | 1.2575 | 4.0 | 108 | 1.2729 | 0.4222 |
72
+ | 1.2908 | 5.0 | 135 | 1.8913 | 0.3333 |
73
+ | 1.1882 | 6.0 | 162 | 1.1330 | 0.5111 |
74
+ | 1.0961 | 7.0 | 189 | 1.6635 | 0.3778 |
75
+ | 1.0705 | 8.0 | 216 | 1.0816 | 0.5556 |
76
+ | 0.8596 | 9.0 | 243 | 2.1258 | 0.4 |
77
+ | 0.8047 | 10.0 | 270 | 1.2784 | 0.4444 |
78
+ | 0.7923 | 11.0 | 297 | 2.1314 | 0.3778 |
79
+ | 0.7354 | 12.0 | 324 | 1.5632 | 0.3778 |
80
+ | 0.7076 | 13.0 | 351 | 1.6923 | 0.4 |
81
+ | 0.7272 | 14.0 | 378 | 1.4002 | 0.4222 |
82
+ | 0.6359 | 15.0 | 405 | 1.6646 | 0.4 |
83
+ | 0.5977 | 16.0 | 432 | 1.6603 | 0.4444 |
84
+ | 0.6463 | 17.0 | 459 | 1.5891 | 0.4444 |
85
+ | 0.6624 | 18.0 | 486 | 1.8543 | 0.4 |
86
+ | 0.5726 | 19.0 | 513 | 1.5545 | 0.5111 |
87
+ | 0.5713 | 20.0 | 540 | 1.7099 | 0.4 |
88
+ | 0.5626 | 21.0 | 567 | 1.6364 | 0.4 |
89
+ | 0.5358 | 22.0 | 594 | 1.8888 | 0.4667 |
90
+ | 0.5334 | 23.0 | 621 | 1.9170 | 0.4667 |
91
+ | 0.4645 | 24.0 | 648 | 2.0287 | 0.4222 |
92
+ | 0.5514 | 25.0 | 675 | 1.5224 | 0.4889 |
93
+ | 0.5254 | 26.0 | 702 | 2.4633 | 0.3556 |
94
+ | 0.441 | 27.0 | 729 | 1.7933 | 0.4222 |
95
+ | 0.3855 | 28.0 | 756 | 2.4673 | 0.4222 |
96
+ | 0.4099 | 29.0 | 783 | 2.6353 | 0.4222 |
97
+ | 0.4294 | 30.0 | 810 | 2.2588 | 0.4444 |
98
+ | 0.3329 | 31.0 | 837 | 2.3858 | 0.4 |
99
+ | 0.3787 | 32.0 | 864 | 2.2861 | 0.3333 |
100
+ | 0.3457 | 33.0 | 891 | 2.1705 | 0.4222 |
101
+ | 0.2509 | 34.0 | 918 | 2.4731 | 0.4222 |
102
+ | 0.1898 | 35.0 | 945 | 2.9376 | 0.3111 |
103
+ | 0.197 | 36.0 | 972 | 3.2201 | 0.4222 |
104
+ | 0.1255 | 37.0 | 999 | 2.5816 | 0.5333 |
105
+ | 0.1258 | 38.0 | 1026 | 3.6398 | 0.4 |
106
+ | 0.1837 | 39.0 | 1053 | 3.2179 | 0.4222 |
107
+ | 0.0881 | 40.0 | 1080 | 3.5990 | 0.4444 |
108
+ | 0.0547 | 41.0 | 1107 | 4.2943 | 0.4222 |
109
+ | 0.0315 | 42.0 | 1134 | 4.0730 | 0.4222 |
110
+ | 0.0187 | 43.0 | 1161 | 4.2944 | 0.4667 |
111
+ | 0.0043 | 44.0 | 1188 | 4.5081 | 0.4667 |
112
+ | 0.0016 | 45.0 | 1215 | 4.8996 | 0.4444 |
113
+ | 0.0009 | 46.0 | 1242 | 4.8993 | 0.4444 |
114
+ | 0.0009 | 47.0 | 1269 | 4.9469 | 0.4444 |
115
+ | 0.0007 | 48.0 | 1296 | 4.9681 | 0.4444 |
116
+ | 0.0006 | 49.0 | 1323 | 4.9688 | 0.4444 |
117
+ | 0.0006 | 50.0 | 1350 | 4.9688 | 0.4444 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7872b0b54cd91fc96921030cb5b6f6c23feade79e9378e78549232a59ca695c
3
  size 86691704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c35595e2503fca458bee0725fa7428c645d068dc9c9bd61d41cda6cba811b1
3
  size 86691704