Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-hasta-55-fold4

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
8881597
•
1 Parent(s): 8c36842

Model save

Browse files
Files changed (3) hide show
  1. README.md +135 -0
  2. model.safetensors +1 -1
  3. runs/May22_14-03-23_927069b479b5/events.out.tfevents.1716386605.927069b479b5.252.12 +2 -2
README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-base-distilled-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: deit-base-distilled-patch16-224-hasta-55-fold4
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.5555555555555556
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
+ # deit-base-distilled-patch16-224-hasta-55-fold4
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.3346
36
+ - Accuracy: 0.5556
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: 5e-05
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: 100
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | No log | 0.5714 | 1 | 1.1563 | 0.4167 |
71
+ | No log | 1.7143 | 3 | 1.1167 | 0.3611 |
72
+ | No log | 2.8571 | 5 | 1.3251 | 0.3611 |
73
+ | No log | 4.0 | 7 | 1.1401 | 0.3611 |
74
+ | No log | 4.5714 | 8 | 1.0346 | 0.5278 |
75
+ | 1.1327 | 5.7143 | 10 | 1.0377 | 0.4444 |
76
+ | 1.1327 | 6.8571 | 12 | 1.0117 | 0.5556 |
77
+ | 1.1327 | 8.0 | 14 | 1.0721 | 0.3889 |
78
+ | 1.1327 | 8.5714 | 15 | 1.0312 | 0.4167 |
79
+ | 1.1327 | 9.7143 | 17 | 1.0228 | 0.5 |
80
+ | 1.1327 | 10.8571 | 19 | 0.9868 | 0.5556 |
81
+ | 0.9623 | 12.0 | 21 | 1.1119 | 0.5 |
82
+ | 0.9623 | 12.5714 | 22 | 1.1094 | 0.5 |
83
+ | 0.9623 | 13.7143 | 24 | 0.9811 | 0.6389 |
84
+ | 0.9623 | 14.8571 | 26 | 1.0888 | 0.4722 |
85
+ | 0.9623 | 16.0 | 28 | 1.0576 | 0.5833 |
86
+ | 0.9623 | 16.5714 | 29 | 1.0583 | 0.6389 |
87
+ | 0.8158 | 17.7143 | 31 | 1.0731 | 0.5833 |
88
+ | 0.8158 | 18.8571 | 33 | 0.9776 | 0.5833 |
89
+ | 0.8158 | 20.0 | 35 | 1.0211 | 0.6667 |
90
+ | 0.8158 | 20.5714 | 36 | 1.0035 | 0.6111 |
91
+ | 0.8158 | 21.7143 | 38 | 0.9845 | 0.5556 |
92
+ | 0.653 | 22.8571 | 40 | 1.0856 | 0.6389 |
93
+ | 0.653 | 24.0 | 42 | 1.0787 | 0.6111 |
94
+ | 0.653 | 24.5714 | 43 | 1.0536 | 0.5833 |
95
+ | 0.653 | 25.7143 | 45 | 1.0995 | 0.5833 |
96
+ | 0.653 | 26.8571 | 47 | 1.1207 | 0.5833 |
97
+ | 0.653 | 28.0 | 49 | 1.1610 | 0.5833 |
98
+ | 0.5371 | 28.5714 | 50 | 1.1164 | 0.6111 |
99
+ | 0.5371 | 29.7143 | 52 | 1.1101 | 0.5833 |
100
+ | 0.5371 | 30.8571 | 54 | 1.1040 | 0.5556 |
101
+ | 0.5371 | 32.0 | 56 | 1.0995 | 0.5833 |
102
+ | 0.5371 | 32.5714 | 57 | 1.1076 | 0.5833 |
103
+ | 0.5371 | 33.7143 | 59 | 1.1530 | 0.5833 |
104
+ | 0.4039 | 34.8571 | 61 | 1.1780 | 0.5556 |
105
+ | 0.4039 | 36.0 | 63 | 1.1379 | 0.6111 |
106
+ | 0.4039 | 36.5714 | 64 | 1.1324 | 0.6111 |
107
+ | 0.4039 | 37.7143 | 66 | 1.1546 | 0.5556 |
108
+ | 0.4039 | 38.8571 | 68 | 1.1910 | 0.5556 |
109
+ | 0.348 | 40.0 | 70 | 1.1487 | 0.5833 |
110
+ | 0.348 | 40.5714 | 71 | 1.1367 | 0.5833 |
111
+ | 0.348 | 41.7143 | 73 | 1.1627 | 0.5833 |
112
+ | 0.348 | 42.8571 | 75 | 1.2421 | 0.5833 |
113
+ | 0.348 | 44.0 | 77 | 1.3073 | 0.5556 |
114
+ | 0.348 | 44.5714 | 78 | 1.2773 | 0.5556 |
115
+ | 0.321 | 45.7143 | 80 | 1.2160 | 0.5833 |
116
+ | 0.321 | 46.8571 | 82 | 1.2220 | 0.5833 |
117
+ | 0.321 | 48.0 | 84 | 1.2168 | 0.5833 |
118
+ | 0.321 | 48.5714 | 85 | 1.2190 | 0.5833 |
119
+ | 0.321 | 49.7143 | 87 | 1.2255 | 0.5833 |
120
+ | 0.321 | 50.8571 | 89 | 1.2174 | 0.5833 |
121
+ | 0.3168 | 52.0 | 91 | 1.2152 | 0.5833 |
122
+ | 0.3168 | 52.5714 | 92 | 1.2308 | 0.5833 |
123
+ | 0.3168 | 53.7143 | 94 | 1.2728 | 0.5556 |
124
+ | 0.3168 | 54.8571 | 96 | 1.3121 | 0.5556 |
125
+ | 0.3168 | 56.0 | 98 | 1.3350 | 0.5556 |
126
+ | 0.3168 | 56.5714 | 99 | 1.3354 | 0.5556 |
127
+ | 0.2876 | 57.1429 | 100 | 1.3346 | 0.5556 |
128
+
129
+
130
+ ### Framework versions
131
+
132
+ - Transformers 4.41.0
133
+ - Pytorch 2.3.0+cu121
134
+ - Datasets 2.19.1
135
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f2193fbc22adaa14c79f80734cf108d38008846bc6ecc629986c130d7e57391
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a855db22b6bffe3bd6c8876f1aab65bd2b8518e2e574b34b73990dfe0325466
3
  size 343233492
runs/May22_14-03-23_927069b479b5/events.out.tfevents.1716386605.927069b479b5.252.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d62102f0b00a25dc2c6485d7ffc276d95959a5d264ed4e2a40c121ea822d858
3
- size 23994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09451223da97f95268eef3df669a7219c00b538e477164a332a9609c6b8c2d44
3
+ size 25817