Hugging Face's logo

hkivancoral
/
hushem_1x_deit_base_adamax_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
11c30f0
•
1 Parent(s): 73c2829

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov15_13-43-24_2fc4888c5945/events.out.tfevents.1700055805.2fc4888c5945.935.2 +2 -2
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_1x_deit_base_adamax_001_fold3
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: 0.627906976744186
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_base_adamax_001_fold3
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.8177
36
+ - Accuracy: 0.6279
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 | 1.4213 | 0.2558 |
69
+ | 1.6944 | 2.0 | 12 | 1.4223 | 0.2558 |
70
+ | 1.6944 | 3.0 | 18 | 1.4356 | 0.2558 |
71
+ | 1.4104 | 4.0 | 24 | 1.3899 | 0.2558 |
72
+ | 1.4138 | 5.0 | 30 | 1.3790 | 0.2558 |
73
+ | 1.4138 | 6.0 | 36 | 1.3481 | 0.2558 |
74
+ | 1.38 | 7.0 | 42 | 1.3370 | 0.4419 |
75
+ | 1.38 | 8.0 | 48 | 1.1768 | 0.4884 |
76
+ | 1.2875 | 9.0 | 54 | 1.4426 | 0.2558 |
77
+ | 1.3451 | 10.0 | 60 | 1.3489 | 0.3721 |
78
+ | 1.3451 | 11.0 | 66 | 1.4974 | 0.0930 |
79
+ | 1.358 | 12.0 | 72 | 1.1260 | 0.4884 |
80
+ | 1.358 | 13.0 | 78 | 1.2091 | 0.2558 |
81
+ | 1.2345 | 14.0 | 84 | 1.4654 | 0.3023 |
82
+ | 1.2591 | 15.0 | 90 | 1.2058 | 0.4419 |
83
+ | 1.2591 | 16.0 | 96 | 1.2441 | 0.4419 |
84
+ | 1.1691 | 17.0 | 102 | 1.5475 | 0.3721 |
85
+ | 1.1691 | 18.0 | 108 | 1.1410 | 0.4186 |
86
+ | 1.106 | 19.0 | 114 | 1.3744 | 0.4651 |
87
+ | 1.0155 | 20.0 | 120 | 1.0730 | 0.5349 |
88
+ | 1.0155 | 21.0 | 126 | 1.1330 | 0.4884 |
89
+ | 0.8578 | 22.0 | 132 | 0.8490 | 0.6512 |
90
+ | 0.8578 | 23.0 | 138 | 1.2329 | 0.5581 |
91
+ | 0.8221 | 24.0 | 144 | 0.8247 | 0.6047 |
92
+ | 0.8029 | 25.0 | 150 | 0.8615 | 0.7209 |
93
+ | 0.8029 | 26.0 | 156 | 1.4388 | 0.4651 |
94
+ | 0.8866 | 27.0 | 162 | 0.9162 | 0.5814 |
95
+ | 0.8866 | 28.0 | 168 | 0.9617 | 0.6512 |
96
+ | 0.7595 | 29.0 | 174 | 0.8582 | 0.6279 |
97
+ | 0.6117 | 30.0 | 180 | 1.0142 | 0.6512 |
98
+ | 0.6117 | 31.0 | 186 | 1.2731 | 0.6512 |
99
+ | 0.6007 | 32.0 | 192 | 1.1454 | 0.6279 |
100
+ | 0.6007 | 33.0 | 198 | 0.9205 | 0.6744 |
101
+ | 0.5463 | 34.0 | 204 | 1.2293 | 0.6744 |
102
+ | 0.4378 | 35.0 | 210 | 1.3367 | 0.6512 |
103
+ | 0.4378 | 36.0 | 216 | 1.0885 | 0.6512 |
104
+ | 0.4154 | 37.0 | 222 | 1.7651 | 0.6744 |
105
+ | 0.4154 | 38.0 | 228 | 1.3160 | 0.5814 |
106
+ | 0.3817 | 39.0 | 234 | 2.0046 | 0.6279 |
107
+ | 0.3462 | 40.0 | 240 | 1.4912 | 0.6279 |
108
+ | 0.3462 | 41.0 | 246 | 1.7923 | 0.6047 |
109
+ | 0.3206 | 42.0 | 252 | 1.8177 | 0.6279 |
110
+ | 0.3206 | 43.0 | 258 | 1.8177 | 0.6279 |
111
+ | 0.3043 | 44.0 | 264 | 1.8177 | 0.6279 |
112
+ | 0.2864 | 45.0 | 270 | 1.8177 | 0.6279 |
113
+ | 0.2864 | 46.0 | 276 | 1.8177 | 0.6279 |
114
+ | 0.3222 | 47.0 | 282 | 1.8177 | 0.6279 |
115
+ | 0.3222 | 48.0 | 288 | 1.8177 | 0.6279 |
116
+ | 0.3546 | 49.0 | 294 | 1.8177 | 0.6279 |
117
+ | 0.3175 | 50.0 | 300 | 1.8177 | 0.6279 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.1
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.14.7
125
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff3e08d52c654d39efd374833783a56c0f494d28dc0d7d7c865e7a80e85a6090
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ffd10444a5be7dad6f118af06a7d2d0d5a5045b21b5a9a891a478fa825230f
3
  size 343230128
runs/Nov15_13-43-24_2fc4888c5945/events.out.tfevents.1700055805.2fc4888c5945.935.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c0f6d71175135021ebb0a9678139d167e5f3e371da263aa3fc7a82cd94f9dbd
3
- size 25090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec0959f9d11504cbef8a6db91ae94a3d9a7a300febe8747b84fea97f7968e312
3
+ size 25444