Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-hasta-55-fold3

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
509f661
•
1 Parent(s): d6aa599

Model save

Browse files
Files changed (3) hide show
  1. README.md +135 -0
  2. model.safetensors +1 -1
  3. runs/May22_13-53-18_927069b479b5/events.out.tfevents.1716385999.927069b479b5.252.10 +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-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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.6388888888888888
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-fold3
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: 0.9385
36
+ - Accuracy: 0.6389
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 | 1.3455 | 0.3611 |
71
+ | No log | 1.7143 | 3 | 1.1600 | 0.3889 |
72
+ | No log | 2.8571 | 5 | 1.1451 | 0.3889 |
73
+ | No log | 4.0 | 7 | 1.1113 | 0.4167 |
74
+ | No log | 4.5714 | 8 | 1.1294 | 0.3611 |
75
+ | 1.114 | 5.7143 | 10 | 1.1000 | 0.4722 |
76
+ | 1.114 | 6.8571 | 12 | 1.0526 | 0.5 |
77
+ | 1.114 | 8.0 | 14 | 1.0222 | 0.5 |
78
+ | 1.114 | 8.5714 | 15 | 1.0203 | 0.4444 |
79
+ | 1.114 | 9.7143 | 17 | 0.9883 | 0.5556 |
80
+ | 1.114 | 10.8571 | 19 | 0.9686 | 0.5 |
81
+ | 0.928 | 12.0 | 21 | 0.9622 | 0.5556 |
82
+ | 0.928 | 12.5714 | 22 | 0.9396 | 0.5556 |
83
+ | 0.928 | 13.7143 | 24 | 0.9678 | 0.5556 |
84
+ | 0.928 | 14.8571 | 26 | 0.9045 | 0.6389 |
85
+ | 0.928 | 16.0 | 28 | 0.8842 | 0.6667 |
86
+ | 0.928 | 16.5714 | 29 | 0.8690 | 0.6389 |
87
+ | 0.7807 | 17.7143 | 31 | 0.8539 | 0.6389 |
88
+ | 0.7807 | 18.8571 | 33 | 0.9446 | 0.6389 |
89
+ | 0.7807 | 20.0 | 35 | 0.8785 | 0.6667 |
90
+ | 0.7807 | 20.5714 | 36 | 0.8500 | 0.6389 |
91
+ | 0.7807 | 21.7143 | 38 | 0.9317 | 0.6389 |
92
+ | 0.6419 | 22.8571 | 40 | 0.9105 | 0.6111 |
93
+ | 0.6419 | 24.0 | 42 | 0.9513 | 0.6111 |
94
+ | 0.6419 | 24.5714 | 43 | 0.9155 | 0.6111 |
95
+ | 0.6419 | 25.7143 | 45 | 0.8752 | 0.6389 |
96
+ | 0.6419 | 26.8571 | 47 | 0.8911 | 0.6111 |
97
+ | 0.6419 | 28.0 | 49 | 0.8772 | 0.5833 |
98
+ | 0.5401 | 28.5714 | 50 | 0.8496 | 0.5833 |
99
+ | 0.5401 | 29.7143 | 52 | 0.8562 | 0.6667 |
100
+ | 0.5401 | 30.8571 | 54 | 0.8377 | 0.6111 |
101
+ | 0.5401 | 32.0 | 56 | 0.9969 | 0.6111 |
102
+ | 0.5401 | 32.5714 | 57 | 1.0985 | 0.5833 |
103
+ | 0.5401 | 33.7143 | 59 | 0.9632 | 0.5833 |
104
+ | 0.4658 | 34.8571 | 61 | 0.8651 | 0.6389 |
105
+ | 0.4658 | 36.0 | 63 | 0.8731 | 0.6111 |
106
+ | 0.4658 | 36.5714 | 64 | 0.9148 | 0.5556 |
107
+ | 0.4658 | 37.7143 | 66 | 1.0383 | 0.6111 |
108
+ | 0.4658 | 38.8571 | 68 | 0.9203 | 0.6111 |
109
+ | 0.3816 | 40.0 | 70 | 0.8720 | 0.6389 |
110
+ | 0.3816 | 40.5714 | 71 | 0.8789 | 0.6389 |
111
+ | 0.3816 | 41.7143 | 73 | 0.8742 | 0.6667 |
112
+ | 0.3816 | 42.8571 | 75 | 0.8865 | 0.6944 |
113
+ | 0.3816 | 44.0 | 77 | 0.8931 | 0.6667 |
114
+ | 0.3816 | 44.5714 | 78 | 0.9036 | 0.6667 |
115
+ | 0.337 | 45.7143 | 80 | 0.9182 | 0.6389 |
116
+ | 0.337 | 46.8571 | 82 | 0.9406 | 0.6389 |
117
+ | 0.337 | 48.0 | 84 | 0.9587 | 0.6667 |
118
+ | 0.337 | 48.5714 | 85 | 0.9697 | 0.6389 |
119
+ | 0.337 | 49.7143 | 87 | 0.9818 | 0.6667 |
120
+ | 0.337 | 50.8571 | 89 | 0.9692 | 0.6389 |
121
+ | 0.2958 | 52.0 | 91 | 0.9426 | 0.6389 |
122
+ | 0.2958 | 52.5714 | 92 | 0.9374 | 0.6667 |
123
+ | 0.2958 | 53.7143 | 94 | 0.9338 | 0.6389 |
124
+ | 0.2958 | 54.8571 | 96 | 0.9337 | 0.6389 |
125
+ | 0.2958 | 56.0 | 98 | 0.9361 | 0.6389 |
126
+ | 0.2958 | 56.5714 | 99 | 0.9377 | 0.6389 |
127
+ | 0.2914 | 57.1429 | 100 | 0.9385 | 0.6389 |
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 sha256:9ff9077562632d37373f3a734b867ce451f55249b4cf3230757e2f2c9760e6d3
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a96fd63c079599244b6bd5143ce7c763460b29d6b8b47510b9a74b75035b70a
3
  size 343233492
runs/May22_13-53-18_927069b479b5/events.out.tfevents.1716385999.927069b479b5.252.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b2b7636aa3ce8a395c07552d20510f52fb34c0239098ea50ead7f872ee0d0d
3
- size 23994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e208af97e6a907e710a3587d8e3b55149ea2d334f857801dd82888e717224795
3
+ size 25817