BilalMuftuoglu commited on
Commit
b421947
1 Parent(s): 8b03d2f

Model save

Browse files
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-85-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: 0.7272727272727273
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-85-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: 2.1933
36
+ - Accuracy: 0.7273
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 | 1.0 | 1 | 1.2772 | 0.0909 |
71
+ | No log | 2.0 | 2 | 1.1448 | 0.1818 |
72
+ | No log | 3.0 | 3 | 0.9744 | 0.7273 |
73
+ | No log | 4.0 | 4 | 0.9234 | 0.7273 |
74
+ | No log | 5.0 | 5 | 1.0760 | 0.7273 |
75
+ | No log | 6.0 | 6 | 1.3222 | 0.7273 |
76
+ | No log | 7.0 | 7 | 1.5248 | 0.7273 |
77
+ | No log | 8.0 | 8 | 1.6139 | 0.7273 |
78
+ | No log | 9.0 | 9 | 1.6711 | 0.7273 |
79
+ | 0.3554 | 10.0 | 10 | 1.7354 | 0.7273 |
80
+ | 0.3554 | 11.0 | 11 | 1.6721 | 0.7273 |
81
+ | 0.3554 | 12.0 | 12 | 1.5988 | 0.7273 |
82
+ | 0.3554 | 13.0 | 13 | 1.5960 | 0.7273 |
83
+ | 0.3554 | 14.0 | 14 | 1.5832 | 0.7273 |
84
+ | 0.3554 | 15.0 | 15 | 1.5683 | 0.7273 |
85
+ | 0.3554 | 16.0 | 16 | 1.5774 | 0.7273 |
86
+ | 0.3554 | 17.0 | 17 | 1.6468 | 0.7273 |
87
+ | 0.3554 | 18.0 | 18 | 1.7091 | 0.7273 |
88
+ | 0.3554 | 19.0 | 19 | 1.7276 | 0.7273 |
89
+ | 0.1335 | 20.0 | 20 | 1.7052 | 0.7273 |
90
+ | 0.1335 | 21.0 | 21 | 1.6426 | 0.7273 |
91
+ | 0.1335 | 22.0 | 22 | 1.5316 | 0.7273 |
92
+ | 0.1335 | 23.0 | 23 | 1.4017 | 0.7273 |
93
+ | 0.1335 | 24.0 | 24 | 1.3009 | 0.7273 |
94
+ | 0.1335 | 25.0 | 25 | 1.2864 | 0.7273 |
95
+ | 0.1335 | 26.0 | 26 | 1.3934 | 0.7273 |
96
+ | 0.1335 | 27.0 | 27 | 1.4436 | 0.7273 |
97
+ | 0.1335 | 28.0 | 28 | 1.5752 | 0.7273 |
98
+ | 0.1335 | 29.0 | 29 | 1.6211 | 0.7273 |
99
+ | 0.0769 | 30.0 | 30 | 1.5944 | 0.7273 |
100
+ | 0.0769 | 31.0 | 31 | 1.5283 | 0.7273 |
101
+ | 0.0769 | 32.0 | 32 | 1.4341 | 0.7273 |
102
+ | 0.0769 | 33.0 | 33 | 1.4512 | 0.7273 |
103
+ | 0.0769 | 34.0 | 34 | 1.4980 | 0.7273 |
104
+ | 0.0769 | 35.0 | 35 | 1.5803 | 0.7273 |
105
+ | 0.0769 | 36.0 | 36 | 1.7676 | 0.7273 |
106
+ | 0.0769 | 37.0 | 37 | 1.8581 | 0.7273 |
107
+ | 0.0769 | 38.0 | 38 | 1.8816 | 0.7273 |
108
+ | 0.0769 | 39.0 | 39 | 1.8317 | 0.7273 |
109
+ | 0.0505 | 40.0 | 40 | 1.7445 | 0.7273 |
110
+ | 0.0505 | 41.0 | 41 | 1.6965 | 0.7273 |
111
+ | 0.0505 | 42.0 | 42 | 1.7210 | 0.7273 |
112
+ | 0.0505 | 43.0 | 43 | 1.6903 | 0.7273 |
113
+ | 0.0505 | 44.0 | 44 | 1.6944 | 0.7273 |
114
+ | 0.0505 | 45.0 | 45 | 1.6923 | 0.7273 |
115
+ | 0.0505 | 46.0 | 46 | 1.7470 | 0.7273 |
116
+ | 0.0505 | 47.0 | 47 | 1.7502 | 0.7273 |
117
+ | 0.0505 | 48.0 | 48 | 1.7739 | 0.7273 |
118
+ | 0.0505 | 49.0 | 49 | 1.7819 | 0.7273 |
119
+ | 0.0255 | 50.0 | 50 | 1.8200 | 0.7273 |
120
+ | 0.0255 | 51.0 | 51 | 1.8122 | 0.7273 |
121
+ | 0.0255 | 52.0 | 52 | 1.7939 | 0.7273 |
122
+ | 0.0255 | 53.0 | 53 | 1.7736 | 0.7273 |
123
+ | 0.0255 | 54.0 | 54 | 1.7411 | 0.7273 |
124
+ | 0.0255 | 55.0 | 55 | 1.6773 | 0.7273 |
125
+ | 0.0255 | 56.0 | 56 | 1.6556 | 0.7273 |
126
+ | 0.0255 | 57.0 | 57 | 1.6767 | 0.7273 |
127
+ | 0.0255 | 58.0 | 58 | 1.6623 | 0.7273 |
128
+ | 0.0255 | 59.0 | 59 | 1.6553 | 0.7273 |
129
+ | 0.0227 | 60.0 | 60 | 1.6682 | 0.7273 |
130
+ | 0.0227 | 61.0 | 61 | 1.6209 | 0.7273 |
131
+ | 0.0227 | 62.0 | 62 | 1.6188 | 0.7273 |
132
+ | 0.0227 | 63.0 | 63 | 1.6919 | 0.7273 |
133
+ | 0.0227 | 64.0 | 64 | 1.7957 | 0.7273 |
134
+ | 0.0227 | 65.0 | 65 | 1.8750 | 0.7273 |
135
+ | 0.0227 | 66.0 | 66 | 1.9156 | 0.7273 |
136
+ | 0.0227 | 67.0 | 67 | 1.9163 | 0.7273 |
137
+ | 0.0227 | 68.0 | 68 | 1.8969 | 0.7273 |
138
+ | 0.0227 | 69.0 | 69 | 1.8814 | 0.7273 |
139
+ | 0.0185 | 70.0 | 70 | 1.8715 | 0.7273 |
140
+ | 0.0185 | 71.0 | 71 | 1.8892 | 0.7273 |
141
+ | 0.0185 | 72.0 | 72 | 1.9383 | 0.7273 |
142
+ | 0.0185 | 73.0 | 73 | 1.9627 | 0.7273 |
143
+ | 0.0185 | 74.0 | 74 | 2.0154 | 0.7273 |
144
+ | 0.0185 | 75.0 | 75 | 2.0326 | 0.7273 |
145
+ | 0.0185 | 76.0 | 76 | 2.0425 | 0.7273 |
146
+ | 0.0185 | 77.0 | 77 | 2.0586 | 0.7273 |
147
+ | 0.0185 | 78.0 | 78 | 2.0582 | 0.7273 |
148
+ | 0.0185 | 79.0 | 79 | 2.0863 | 0.7273 |
149
+ | 0.0246 | 80.0 | 80 | 2.1233 | 0.7273 |
150
+ | 0.0246 | 81.0 | 81 | 2.1527 | 0.7273 |
151
+ | 0.0246 | 82.0 | 82 | 2.1760 | 0.7273 |
152
+ | 0.0246 | 83.0 | 83 | 2.1907 | 0.7273 |
153
+ | 0.0246 | 84.0 | 84 | 2.1859 | 0.7273 |
154
+ | 0.0246 | 85.0 | 85 | 2.1654 | 0.7273 |
155
+ | 0.0246 | 86.0 | 86 | 2.1479 | 0.7273 |
156
+ | 0.0246 | 87.0 | 87 | 2.1194 | 0.7273 |
157
+ | 0.0246 | 88.0 | 88 | 2.1059 | 0.7273 |
158
+ | 0.0246 | 89.0 | 89 | 2.1032 | 0.7273 |
159
+ | 0.0228 | 90.0 | 90 | 2.0999 | 0.7273 |
160
+ | 0.0228 | 91.0 | 91 | 2.1037 | 0.7273 |
161
+ | 0.0228 | 92.0 | 92 | 2.1026 | 0.7273 |
162
+ | 0.0228 | 93.0 | 93 | 2.1132 | 0.7273 |
163
+ | 0.0228 | 94.0 | 94 | 2.1302 | 0.7273 |
164
+ | 0.0228 | 95.0 | 95 | 2.1453 | 0.7273 |
165
+ | 0.0228 | 96.0 | 96 | 2.1634 | 0.7273 |
166
+ | 0.0228 | 97.0 | 97 | 2.1762 | 0.7273 |
167
+ | 0.0228 | 98.0 | 98 | 2.1859 | 0.7273 |
168
+ | 0.0228 | 99.0 | 99 | 2.1916 | 0.7273 |
169
+ | 0.0142 | 100.0 | 100 | 2.1933 | 0.7273 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.41.0
175
+ - Pytorch 2.3.0+cu121
176
+ - Datasets 2.19.1
177
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b92facdebed54645e5bd7bcaaf7f2b85de69937545df73735480d9101c4b305
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162ca0aef28f5ff21e018748b9923f395a5f6a019893eade9e5b3a0855b00d3a
3
  size 343233492
runs/May22_15-53-51_927069b479b5/events.out.tfevents.1716393232.927069b479b5.252.36 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d6cc8b4cbfad6c3bc48e37af2c647e79699520b50d5268d83c2bb28990b7ab
3
- size 37625
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41422f3ba5b9149f0dd91a940687271b1c8f4184338a68d1870cb24a391e52c0
3
+ size 39131