Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_rms_lr001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
1624b31
•
1 Parent(s): 8fdd625

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_1x_deit_tiny_rms_lr001_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: 0.37777777777777777
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_1x_deit_tiny_rms_lr001_fold1
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: 1.6888
36
+ - Accuracy: 0.3778
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
+ | No log | 1.0 | 6 | 5.6136 | 0.2667 |
69
+ | 3.3911 | 2.0 | 12 | 1.9975 | 0.2444 |
70
+ | 3.3911 | 3.0 | 18 | 1.6108 | 0.2444 |
71
+ | 1.8768 | 4.0 | 24 | 1.5122 | 0.2667 |
72
+ | 1.5956 | 5.0 | 30 | 1.5150 | 0.2444 |
73
+ | 1.5956 | 6.0 | 36 | 1.8016 | 0.2444 |
74
+ | 1.4916 | 7.0 | 42 | 1.5690 | 0.4444 |
75
+ | 1.4916 | 8.0 | 48 | 1.4991 | 0.2667 |
76
+ | 1.4756 | 9.0 | 54 | 1.4574 | 0.2444 |
77
+ | 1.4478 | 10.0 | 60 | 1.4022 | 0.2444 |
78
+ | 1.4478 | 11.0 | 66 | 1.4406 | 0.2667 |
79
+ | 1.421 | 12.0 | 72 | 1.3666 | 0.2444 |
80
+ | 1.421 | 13.0 | 78 | 1.3200 | 0.2667 |
81
+ | 1.4101 | 14.0 | 84 | 1.4311 | 0.2444 |
82
+ | 1.366 | 15.0 | 90 | 1.5240 | 0.4 |
83
+ | 1.366 | 16.0 | 96 | 1.1533 | 0.5333 |
84
+ | 1.3311 | 17.0 | 102 | 1.1480 | 0.4667 |
85
+ | 1.3311 | 18.0 | 108 | 1.5207 | 0.2444 |
86
+ | 1.1912 | 19.0 | 114 | 1.6588 | 0.2889 |
87
+ | 1.1923 | 20.0 | 120 | 1.4947 | 0.4667 |
88
+ | 1.1923 | 21.0 | 126 | 1.3281 | 0.2444 |
89
+ | 1.1796 | 22.0 | 132 | 1.3569 | 0.3333 |
90
+ | 1.1796 | 23.0 | 138 | 1.7298 | 0.2444 |
91
+ | 1.1031 | 24.0 | 144 | 1.6401 | 0.3556 |
92
+ | 1.2056 | 25.0 | 150 | 1.3732 | 0.2889 |
93
+ | 1.2056 | 26.0 | 156 | 1.8651 | 0.3333 |
94
+ | 1.1039 | 27.0 | 162 | 1.2494 | 0.4667 |
95
+ | 1.1039 | 28.0 | 168 | 1.4459 | 0.2889 |
96
+ | 1.0659 | 29.0 | 174 | 1.4875 | 0.3333 |
97
+ | 1.0534 | 30.0 | 180 | 1.4599 | 0.3556 |
98
+ | 1.0534 | 31.0 | 186 | 1.3781 | 0.3556 |
99
+ | 1.0466 | 32.0 | 192 | 1.7266 | 0.4 |
100
+ | 1.0466 | 33.0 | 198 | 1.5340 | 0.4222 |
101
+ | 0.973 | 34.0 | 204 | 1.5429 | 0.3111 |
102
+ | 1.0226 | 35.0 | 210 | 1.6233 | 0.3111 |
103
+ | 1.0226 | 36.0 | 216 | 1.7204 | 0.3111 |
104
+ | 0.9676 | 37.0 | 222 | 1.7918 | 0.4 |
105
+ | 0.9676 | 38.0 | 228 | 1.6933 | 0.3333 |
106
+ | 0.8379 | 39.0 | 234 | 1.6708 | 0.4222 |
107
+ | 0.8938 | 40.0 | 240 | 1.6748 | 0.4 |
108
+ | 0.8938 | 41.0 | 246 | 1.6963 | 0.3778 |
109
+ | 0.8462 | 42.0 | 252 | 1.6888 | 0.3778 |
110
+ | 0.8462 | 43.0 | 258 | 1.6888 | 0.3778 |
111
+ | 0.8764 | 44.0 | 264 | 1.6888 | 0.3778 |
112
+ | 0.8676 | 45.0 | 270 | 1.6888 | 0.3778 |
113
+ | 0.8676 | 46.0 | 276 | 1.6888 | 0.3778 |
114
+ | 0.8418 | 47.0 | 282 | 1.6888 | 0.3778 |
115
+ | 0.8418 | 48.0 | 288 | 1.6888 | 0.3778 |
116
+ | 0.8647 | 49.0 | 294 | 1.6888 | 0.3778 |
117
+ | 0.872 | 50.0 | 300 | 1.6888 | 0.3778 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.0
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.14.6
125
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48f5e3927549f5f52ea53e97acb05589d76e6891490315655a9c784d2028388d
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f577590457b99532e5f722478c35d3153072dc818bce9fde73d91d6f1c47738
3
  size 22123464