Hugging Face's logo

hkivancoral
/
hushem_5x_deit_tiny_rms_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
381dedf
•
1 Parent(s): b80af00

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-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_deit_tiny_rms_001_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: 0.4666666666666667
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_tiny_rms_001_fold2
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: 4.2103
36
+ - Accuracy: 0.4667
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
+ | 1.9281 | 1.0 | 27 | 1.5117 | 0.2444 |
69
+ | 1.5142 | 2.0 | 54 | 1.4322 | 0.2444 |
70
+ | 1.4521 | 3.0 | 81 | 1.4347 | 0.2667 |
71
+ | 1.4849 | 4.0 | 108 | 1.6669 | 0.2444 |
72
+ | 1.4295 | 5.0 | 135 | 1.4219 | 0.2444 |
73
+ | 1.5039 | 6.0 | 162 | 1.4488 | 0.2444 |
74
+ | 1.4071 | 7.0 | 189 | 1.5265 | 0.2667 |
75
+ | 1.3353 | 8.0 | 216 | 1.4657 | 0.2 |
76
+ | 1.2509 | 9.0 | 243 | 1.4974 | 0.2667 |
77
+ | 1.2656 | 10.0 | 270 | 1.3879 | 0.2667 |
78
+ | 1.1653 | 11.0 | 297 | 1.5762 | 0.3333 |
79
+ | 1.1362 | 12.0 | 324 | 1.6646 | 0.4 |
80
+ | 1.2223 | 13.0 | 351 | 1.6454 | 0.1556 |
81
+ | 1.027 | 14.0 | 378 | 1.7430 | 0.2222 |
82
+ | 1.0093 | 15.0 | 405 | 1.8846 | 0.3778 |
83
+ | 0.9584 | 16.0 | 432 | 2.4104 | 0.1333 |
84
+ | 0.9432 | 17.0 | 459 | 2.0298 | 0.2667 |
85
+ | 0.9525 | 18.0 | 486 | 2.0687 | 0.3111 |
86
+ | 0.8065 | 19.0 | 513 | 2.3917 | 0.1778 |
87
+ | 0.8858 | 20.0 | 540 | 1.9861 | 0.2222 |
88
+ | 0.761 | 21.0 | 567 | 2.1617 | 0.3111 |
89
+ | 0.7456 | 22.0 | 594 | 2.6510 | 0.2667 |
90
+ | 0.7215 | 23.0 | 621 | 2.5639 | 0.4 |
91
+ | 0.7957 | 24.0 | 648 | 2.1510 | 0.3111 |
92
+ | 0.6858 | 25.0 | 675 | 2.2884 | 0.5111 |
93
+ | 0.6662 | 26.0 | 702 | 2.5211 | 0.4667 |
94
+ | 0.6301 | 27.0 | 729 | 2.5983 | 0.4667 |
95
+ | 0.676 | 28.0 | 756 | 2.4047 | 0.3778 |
96
+ | 0.5592 | 29.0 | 783 | 2.9746 | 0.4444 |
97
+ | 0.5758 | 30.0 | 810 | 2.5122 | 0.3778 |
98
+ | 0.5241 | 31.0 | 837 | 2.9556 | 0.4222 |
99
+ | 0.5249 | 32.0 | 864 | 2.6136 | 0.4889 |
100
+ | 0.527 | 33.0 | 891 | 2.5736 | 0.4222 |
101
+ | 0.5079 | 34.0 | 918 | 2.8504 | 0.5333 |
102
+ | 0.4469 | 35.0 | 945 | 3.2380 | 0.4 |
103
+ | 0.4391 | 36.0 | 972 | 3.1267 | 0.4444 |
104
+ | 0.3925 | 37.0 | 999 | 3.3000 | 0.4667 |
105
+ | 0.3719 | 38.0 | 1026 | 3.1308 | 0.5111 |
106
+ | 0.3137 | 39.0 | 1053 | 3.2238 | 0.4889 |
107
+ | 0.2551 | 40.0 | 1080 | 3.3279 | 0.5333 |
108
+ | 0.2638 | 41.0 | 1107 | 3.4382 | 0.5111 |
109
+ | 0.2004 | 42.0 | 1134 | 3.7709 | 0.4667 |
110
+ | 0.1877 | 43.0 | 1161 | 3.7286 | 0.4222 |
111
+ | 0.1439 | 44.0 | 1188 | 3.9363 | 0.4889 |
112
+ | 0.1405 | 45.0 | 1215 | 4.0904 | 0.4667 |
113
+ | 0.1084 | 46.0 | 1242 | 4.2188 | 0.4889 |
114
+ | 0.0629 | 47.0 | 1269 | 4.1702 | 0.5111 |
115
+ | 0.0462 | 48.0 | 1296 | 4.2158 | 0.4667 |
116
+ | 0.0313 | 49.0 | 1323 | 4.2103 | 0.4667 |
117
+ | 0.0292 | 50.0 | 1350 | 4.2103 | 0.4667 |
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:d52733fdf47c20a2cc49c0374ea44b7cb4d069b5dc1a861b92a5791f8aa4ec49
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6942a4fd088d0d86c0ca9e2b67da02660976c01d7da84d0ce933a76c6077d881
3
  size 22123464