Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_adamax_lr001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
6d4b0d8
•
1 Parent(s): 15d16b2

End of training

Browse files
Files changed (3) hide show
  1. README.md +111 -0
  2. model.safetensors +1 -1
  3. runs/Nov10_11-47-58_95f6e207dd34/events.out.tfevents.1699616879.95f6e207dd34.1398.2 +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_lr001_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: 0.5813953488372093
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_lr001_fold3
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: 1.6696
36
+ - Accuracy: 0.5814
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
+ - 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 | 4.2125 | 0.2558 |
71
+ | No log | 2.0 | 3 | 1.4682 | 0.2558 |
72
+ | No log | 2.67 | 4 | 1.6910 | 0.2558 |
73
+ | No log | 4.0 | 6 | 1.4476 | 0.2558 |
74
+ | No log | 4.67 | 7 | 1.3895 | 0.2558 |
75
+ | No log | 6.0 | 9 | 1.3751 | 0.2558 |
76
+ | 1.9073 | 6.67 | 10 | 1.3741 | 0.3953 |
77
+ | 1.9073 | 8.0 | 12 | 1.3957 | 0.3488 |
78
+ | 1.9073 | 8.67 | 13 | 1.3369 | 0.4419 |
79
+ | 1.9073 | 10.0 | 15 | 1.2847 | 0.4186 |
80
+ | 1.9073 | 10.67 | 16 | 1.3400 | 0.3953 |
81
+ | 1.9073 | 12.0 | 18 | 1.2676 | 0.3953 |
82
+ | 1.9073 | 12.67 | 19 | 1.2806 | 0.3721 |
83
+ | 1.1656 | 14.0 | 21 | 1.3652 | 0.3023 |
84
+ | 1.1656 | 14.67 | 22 | 1.3370 | 0.4419 |
85
+ | 1.1656 | 16.0 | 24 | 1.5165 | 0.3721 |
86
+ | 1.1656 | 16.67 | 25 | 1.5828 | 0.3953 |
87
+ | 1.1656 | 18.0 | 27 | 1.3210 | 0.3953 |
88
+ | 1.1656 | 18.67 | 28 | 1.3473 | 0.4419 |
89
+ | 0.9249 | 20.0 | 30 | 1.4346 | 0.4651 |
90
+ | 0.9249 | 20.67 | 31 | 1.3840 | 0.3953 |
91
+ | 0.9249 | 22.0 | 33 | 1.3578 | 0.4884 |
92
+ | 0.9249 | 22.67 | 34 | 1.3339 | 0.4884 |
93
+ | 0.9249 | 24.0 | 36 | 1.3509 | 0.4884 |
94
+ | 0.9249 | 24.67 | 37 | 1.3931 | 0.4884 |
95
+ | 0.9249 | 26.0 | 39 | 1.5691 | 0.5116 |
96
+ | 0.5495 | 26.67 | 40 | 1.5953 | 0.5349 |
97
+ | 0.5495 | 28.0 | 42 | 1.6688 | 0.5814 |
98
+ | 0.5495 | 28.67 | 43 | 1.6795 | 0.5581 |
99
+ | 0.5495 | 30.0 | 45 | 1.6839 | 0.5814 |
100
+ | 0.5495 | 30.67 | 46 | 1.6666 | 0.5814 |
101
+ | 0.5495 | 32.0 | 48 | 1.6555 | 0.5814 |
102
+ | 0.5495 | 32.67 | 49 | 1.6646 | 0.5814 |
103
+ | 0.2333 | 33.33 | 50 | 1.6696 | 0.5814 |
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:a396f08ce680a2d67f8447b1ab355c0a098a905c8710e53af2063f48c712ac29
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c54638df17b16beb00c2b4ab3dd5ebf07e5e72e12588b840bdc6647e4d328d8
3
  size 22123464
runs/Nov10_11-47-58_95f6e207dd34/events.out.tfevents.1699616879.95f6e207dd34.1398.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa99ace2d6eac858de37436b6f1c167b228ad5056472b846fecde9055c24c8d3
3
- size 14842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b60dcddd3734b336f7d2370b216bc6b6a784da581d9a533ffe9a9efdc14c34c
3
+ size 16295