Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_adamax_lr0001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
97d6281
•
1 Parent(s): 041fc59

End of training

Browse files
Files changed (3) hide show
  1. README.md +111 -0
  2. model.safetensors +1 -1
  3. runs/Nov10_12-06-18_3e3d7f37aaee/events.out.tfevents.1699617979.3e3d7f37aaee.1331.4 +2 -2
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_adamax_lr0001_fold5
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: 0.6585365853658537
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_adamax_lr0001_fold5
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: 0.8924
36
+ - Accuracy: 0.6585
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: 0.0001
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 50
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.67 | 1 | 1.9330 | 0.2439 |
71
+ | No log | 2.0 | 3 | 1.4362 | 0.3659 |
72
+ | No log | 2.67 | 4 | 1.3806 | 0.3902 |
73
+ | No log | 4.0 | 6 | 1.3304 | 0.4634 |
74
+ | No log | 4.67 | 7 | 1.3017 | 0.4390 |
75
+ | No log | 6.0 | 9 | 1.1836 | 0.4878 |
76
+ | 1.2323 | 6.67 | 10 | 1.1688 | 0.5610 |
77
+ | 1.2323 | 8.0 | 12 | 1.1361 | 0.5366 |
78
+ | 1.2323 | 8.67 | 13 | 1.1291 | 0.5366 |
79
+ | 1.2323 | 10.0 | 15 | 1.0782 | 0.6098 |
80
+ | 1.2323 | 10.67 | 16 | 1.0358 | 0.6585 |
81
+ | 1.2323 | 12.0 | 18 | 1.0020 | 0.6098 |
82
+ | 1.2323 | 12.67 | 19 | 1.0059 | 0.6098 |
83
+ | 0.3527 | 14.0 | 21 | 0.9293 | 0.6098 |
84
+ | 0.3527 | 14.67 | 22 | 0.9162 | 0.6341 |
85
+ | 0.3527 | 16.0 | 24 | 0.9233 | 0.6098 |
86
+ | 0.3527 | 16.67 | 25 | 0.9213 | 0.6098 |
87
+ | 0.3527 | 18.0 | 27 | 0.9193 | 0.6098 |
88
+ | 0.3527 | 18.67 | 28 | 0.9345 | 0.6098 |
89
+ | 0.04 | 20.0 | 30 | 0.8872 | 0.6585 |
90
+ | 0.04 | 20.67 | 31 | 0.8549 | 0.6829 |
91
+ | 0.04 | 22.0 | 33 | 0.8221 | 0.6829 |
92
+ | 0.04 | 22.67 | 34 | 0.8117 | 0.7073 |
93
+ | 0.04 | 24.0 | 36 | 0.8041 | 0.7561 |
94
+ | 0.04 | 24.67 | 37 | 0.8128 | 0.7561 |
95
+ | 0.04 | 26.0 | 39 | 0.8413 | 0.6829 |
96
+ | 0.0062 | 26.67 | 40 | 0.8565 | 0.6585 |
97
+ | 0.0062 | 28.0 | 42 | 0.8789 | 0.6585 |
98
+ | 0.0062 | 28.67 | 43 | 0.8864 | 0.6585 |
99
+ | 0.0062 | 30.0 | 45 | 0.8920 | 0.6585 |
100
+ | 0.0062 | 30.67 | 46 | 0.8925 | 0.6585 |
101
+ | 0.0062 | 32.0 | 48 | 0.8929 | 0.6585 |
102
+ | 0.0062 | 32.67 | 49 | 0.8927 | 0.6585 |
103
+ | 0.0031 | 33.33 | 50 | 0.8924 | 0.6585 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.35.0
109
+ - Pytorch 2.1.0+cu118
110
+ - Datasets 2.14.6
111
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:599d47a1f7bbfe1880f91a7e7327019c7a80f5f837ff450350601f670d174f84
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8061267b54c4cc1b8ebb9797cd038f4948747b6e0fc5143db75270c52332294b
3
  size 22123464
runs/Nov10_12-06-18_3e3d7f37aaee/events.out.tfevents.1699617979.3e3d7f37aaee.1331.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66176de74f45eecd527b143e440006533ff5c330878af6088d3c1482fe4ae556
3
- size 15480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb3aae060d9b2522ded3fa01b45d39a67d73f4edac6f302bb9e6690c81a67d2
3
+ size 16299