Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-hasta-65-fold1

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
9be271b
•
1 Parent(s): 1fa1b01

Model save

Browse files
Files changed (3) hide show
  1. README.md +135 -0
  2. model.safetensors +1 -1
  3. runs/May22_14-23-48_927069b479b5/events.out.tfevents.1716387829.927069b479b5.252.16 +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-65-fold1
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: 0.5833333333333334
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-65-fold1
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: 0.9713
36
+ - Accuracy: 0.5833
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 | 1.3178 | 0.2222 |
71
+ | No log | 1.7143 | 3 | 1.4014 | 0.2778 |
72
+ | No log | 2.8571 | 5 | 1.3535 | 0.2778 |
73
+ | No log | 4.0 | 7 | 1.1299 | 0.3056 |
74
+ | No log | 4.5714 | 8 | 1.0860 | 0.4722 |
75
+ | 1.0868 | 5.7143 | 10 | 1.1121 | 0.3333 |
76
+ | 1.0868 | 6.8571 | 12 | 1.0691 | 0.3611 |
77
+ | 1.0868 | 8.0 | 14 | 1.0270 | 0.5 |
78
+ | 1.0868 | 8.5714 | 15 | 1.0360 | 0.5 |
79
+ | 1.0868 | 9.7143 | 17 | 1.0385 | 0.3889 |
80
+ | 1.0868 | 10.8571 | 19 | 0.9951 | 0.4167 |
81
+ | 0.9487 | 12.0 | 21 | 1.0029 | 0.4444 |
82
+ | 0.9487 | 12.5714 | 22 | 1.0134 | 0.4722 |
83
+ | 0.9487 | 13.7143 | 24 | 0.9599 | 0.4444 |
84
+ | 0.9487 | 14.8571 | 26 | 0.9117 | 0.5278 |
85
+ | 0.9487 | 16.0 | 28 | 0.8856 | 0.5278 |
86
+ | 0.9487 | 16.5714 | 29 | 0.9275 | 0.4722 |
87
+ | 0.7942 | 17.7143 | 31 | 0.9041 | 0.5278 |
88
+ | 0.7942 | 18.8571 | 33 | 0.8999 | 0.4722 |
89
+ | 0.7942 | 20.0 | 35 | 0.8832 | 0.5833 |
90
+ | 0.7942 | 20.5714 | 36 | 0.8864 | 0.5556 |
91
+ | 0.7942 | 21.7143 | 38 | 0.8551 | 0.5 |
92
+ | 0.5911 | 22.8571 | 40 | 0.8242 | 0.6111 |
93
+ | 0.5911 | 24.0 | 42 | 0.9265 | 0.6389 |
94
+ | 0.5911 | 24.5714 | 43 | 0.8674 | 0.5833 |
95
+ | 0.5911 | 25.7143 | 45 | 0.7892 | 0.5556 |
96
+ | 0.5911 | 26.8571 | 47 | 0.8005 | 0.5833 |
97
+ | 0.5911 | 28.0 | 49 | 0.8302 | 0.5833 |
98
+ | 0.4865 | 28.5714 | 50 | 0.8893 | 0.6111 |
99
+ | 0.4865 | 29.7143 | 52 | 0.9043 | 0.6111 |
100
+ | 0.4865 | 30.8571 | 54 | 0.8433 | 0.5833 |
101
+ | 0.4865 | 32.0 | 56 | 0.8677 | 0.5833 |
102
+ | 0.4865 | 32.5714 | 57 | 0.9008 | 0.5833 |
103
+ | 0.4865 | 33.7143 | 59 | 0.9533 | 0.6111 |
104
+ | 0.4007 | 34.8571 | 61 | 0.9175 | 0.6111 |
105
+ | 0.4007 | 36.0 | 63 | 0.9090 | 0.5833 |
106
+ | 0.4007 | 36.5714 | 64 | 1.0004 | 0.5 |
107
+ | 0.4007 | 37.7143 | 66 | 1.0393 | 0.5 |
108
+ | 0.4007 | 38.8571 | 68 | 0.9196 | 0.5833 |
109
+ | 0.3691 | 40.0 | 70 | 0.9505 | 0.6389 |
110
+ | 0.3691 | 40.5714 | 71 | 0.9634 | 0.6389 |
111
+ | 0.3691 | 41.7143 | 73 | 0.9718 | 0.5278 |
112
+ | 0.3691 | 42.8571 | 75 | 0.9257 | 0.5278 |
113
+ | 0.3691 | 44.0 | 77 | 0.9020 | 0.5 |
114
+ | 0.3691 | 44.5714 | 78 | 0.9132 | 0.5556 |
115
+ | 0.3278 | 45.7143 | 80 | 1.0340 | 0.5556 |
116
+ | 0.3278 | 46.8571 | 82 | 1.0933 | 0.5833 |
117
+ | 0.3278 | 48.0 | 84 | 1.0231 | 0.5 |
118
+ | 0.3278 | 48.5714 | 85 | 0.9826 | 0.5278 |
119
+ | 0.3278 | 49.7143 | 87 | 0.9329 | 0.5278 |
120
+ | 0.3278 | 50.8571 | 89 | 0.9280 | 0.5278 |
121
+ | 0.2909 | 52.0 | 91 | 0.9312 | 0.5556 |
122
+ | 0.2909 | 52.5714 | 92 | 0.9359 | 0.5556 |
123
+ | 0.2909 | 53.7143 | 94 | 0.9495 | 0.5833 |
124
+ | 0.2909 | 54.8571 | 96 | 0.9607 | 0.5833 |
125
+ | 0.2909 | 56.0 | 98 | 0.9685 | 0.5833 |
126
+ | 0.2909 | 56.5714 | 99 | 0.9703 | 0.5833 |
127
+ | 0.2697 | 57.1429 | 100 | 0.9713 | 0.5833 |
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 sha256:18c46960e278c53e2ea9a6102b3afa7af525b4575cc7d6b72a5a51223951c358
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed3fb9be8187f9d54be7dc275a2da49dde9ca9893e50d4769adf9366914aed1
3
  size 343233492
runs/May22_14-23-48_927069b479b5/events.out.tfevents.1716387829.927069b479b5.252.16 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd3fa3a846e0aa1bddf0f550d6826dc9684d052623796f10c6c52077e1950c34
3
- size 24628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6932d0640ac0979b6ad42601325996bbb3f06463c9e8f680b1a70c828fb13215
3
+ size 25817