BilalMuftuoglu commited on
Commit
0e902bc
1 Parent(s): 17a483e

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-fold5
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-fold5
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: 2.1448
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 | 1.3530 | 0.2727 |
71
+ | No log | 2.0 | 2 | 1.1775 | 0.2727 |
72
+ | No log | 3.0 | 3 | 0.9128 | 0.5455 |
73
+ | No log | 4.0 | 4 | 0.7292 | 0.7273 |
74
+ | No log | 5.0 | 5 | 0.7753 | 0.7273 |
75
+ | No log | 6.0 | 6 | 0.9952 | 0.7273 |
76
+ | No log | 7.0 | 7 | 1.1799 | 0.7273 |
77
+ | No log | 8.0 | 8 | 1.2699 | 0.7273 |
78
+ | No log | 9.0 | 9 | 1.2729 | 0.7273 |
79
+ | 0.38 | 10.0 | 10 | 1.2451 | 0.7273 |
80
+ | 0.38 | 11.0 | 11 | 1.2341 | 0.7273 |
81
+ | 0.38 | 12.0 | 12 | 1.2153 | 0.7273 |
82
+ | 0.38 | 13.0 | 13 | 1.1847 | 0.7273 |
83
+ | 0.38 | 14.0 | 14 | 1.1903 | 0.7273 |
84
+ | 0.38 | 15.0 | 15 | 1.2128 | 0.7273 |
85
+ | 0.38 | 16.0 | 16 | 1.1724 | 0.7273 |
86
+ | 0.38 | 17.0 | 17 | 1.0705 | 0.7273 |
87
+ | 0.38 | 18.0 | 18 | 1.0106 | 0.7273 |
88
+ | 0.38 | 19.0 | 19 | 1.0238 | 0.7273 |
89
+ | 0.1729 | 20.0 | 20 | 1.0594 | 0.7273 |
90
+ | 0.1729 | 21.0 | 21 | 1.1695 | 0.7273 |
91
+ | 0.1729 | 22.0 | 22 | 1.2466 | 0.7273 |
92
+ | 0.1729 | 23.0 | 23 | 1.2861 | 0.7273 |
93
+ | 0.1729 | 24.0 | 24 | 1.2790 | 0.7273 |
94
+ | 0.1729 | 25.0 | 25 | 1.3177 | 0.7273 |
95
+ | 0.1729 | 26.0 | 26 | 1.4130 | 0.7273 |
96
+ | 0.1729 | 27.0 | 27 | 1.5155 | 0.7273 |
97
+ | 0.1729 | 28.0 | 28 | 1.6224 | 0.7273 |
98
+ | 0.1729 | 29.0 | 29 | 1.5918 | 0.7273 |
99
+ | 0.0904 | 30.0 | 30 | 1.4099 | 0.7273 |
100
+ | 0.0904 | 31.0 | 31 | 1.2681 | 0.7273 |
101
+ | 0.0904 | 32.0 | 32 | 1.1371 | 0.7273 |
102
+ | 0.0904 | 33.0 | 33 | 1.0387 | 0.7273 |
103
+ | 0.0904 | 34.0 | 34 | 1.0128 | 0.7273 |
104
+ | 0.0904 | 35.0 | 35 | 1.0423 | 0.7273 |
105
+ | 0.0904 | 36.0 | 36 | 1.1730 | 0.7273 |
106
+ | 0.0904 | 37.0 | 37 | 1.3305 | 0.7273 |
107
+ | 0.0904 | 38.0 | 38 | 1.3820 | 0.7273 |
108
+ | 0.0904 | 39.0 | 39 | 1.3682 | 0.7273 |
109
+ | 0.0591 | 40.0 | 40 | 1.2854 | 0.7273 |
110
+ | 0.0591 | 41.0 | 41 | 1.2000 | 0.7273 |
111
+ | 0.0591 | 42.0 | 42 | 1.2079 | 0.7273 |
112
+ | 0.0591 | 43.0 | 43 | 1.2967 | 0.7273 |
113
+ | 0.0591 | 44.0 | 44 | 1.3672 | 0.7273 |
114
+ | 0.0591 | 45.0 | 45 | 1.3709 | 0.7273 |
115
+ | 0.0591 | 46.0 | 46 | 1.4370 | 0.7273 |
116
+ | 0.0591 | 47.0 | 47 | 1.4863 | 0.7273 |
117
+ | 0.0591 | 48.0 | 48 | 1.5696 | 0.7273 |
118
+ | 0.0591 | 49.0 | 49 | 1.5678 | 0.7273 |
119
+ | 0.0289 | 50.0 | 50 | 1.5444 | 0.7273 |
120
+ | 0.0289 | 51.0 | 51 | 1.5086 | 0.7273 |
121
+ | 0.0289 | 52.0 | 52 | 1.4333 | 0.7273 |
122
+ | 0.0289 | 53.0 | 53 | 1.3644 | 0.7273 |
123
+ | 0.0289 | 54.0 | 54 | 1.3099 | 0.7273 |
124
+ | 0.0289 | 55.0 | 55 | 1.3355 | 0.7273 |
125
+ | 0.0289 | 56.0 | 56 | 1.4286 | 0.7273 |
126
+ | 0.0289 | 57.0 | 57 | 1.6121 | 0.7273 |
127
+ | 0.0289 | 58.0 | 58 | 1.8074 | 0.7273 |
128
+ | 0.0289 | 59.0 | 59 | 1.9461 | 0.7273 |
129
+ | 0.0342 | 60.0 | 60 | 2.0314 | 0.7273 |
130
+ | 0.0342 | 61.0 | 61 | 2.0408 | 0.7273 |
131
+ | 0.0342 | 62.0 | 62 | 2.0476 | 0.7273 |
132
+ | 0.0342 | 63.0 | 63 | 2.0517 | 0.7273 |
133
+ | 0.0342 | 64.0 | 64 | 2.0217 | 0.7273 |
134
+ | 0.0342 | 65.0 | 65 | 1.9582 | 0.7273 |
135
+ | 0.0342 | 66.0 | 66 | 1.8825 | 0.7273 |
136
+ | 0.0342 | 67.0 | 67 | 1.8085 | 0.7273 |
137
+ | 0.0342 | 68.0 | 68 | 1.7880 | 0.7273 |
138
+ | 0.0342 | 69.0 | 69 | 1.7796 | 0.7273 |
139
+ | 0.0203 | 70.0 | 70 | 1.7929 | 0.7273 |
140
+ | 0.0203 | 71.0 | 71 | 1.8213 | 0.7273 |
141
+ | 0.0203 | 72.0 | 72 | 1.8388 | 0.7273 |
142
+ | 0.0203 | 73.0 | 73 | 1.8488 | 0.7273 |
143
+ | 0.0203 | 74.0 | 74 | 1.8753 | 0.7273 |
144
+ | 0.0203 | 75.0 | 75 | 1.9079 | 0.7273 |
145
+ | 0.0203 | 76.0 | 76 | 1.9396 | 0.7273 |
146
+ | 0.0203 | 77.0 | 77 | 1.9556 | 0.7273 |
147
+ | 0.0203 | 78.0 | 78 | 1.9591 | 0.7273 |
148
+ | 0.0203 | 79.0 | 79 | 1.9668 | 0.7273 |
149
+ | 0.0324 | 80.0 | 80 | 1.9865 | 0.7273 |
150
+ | 0.0324 | 81.0 | 81 | 2.0098 | 0.7273 |
151
+ | 0.0324 | 82.0 | 82 | 2.0384 | 0.7273 |
152
+ | 0.0324 | 83.0 | 83 | 2.0659 | 0.7273 |
153
+ | 0.0324 | 84.0 | 84 | 2.0952 | 0.7273 |
154
+ | 0.0324 | 85.0 | 85 | 2.1069 | 0.7273 |
155
+ | 0.0324 | 86.0 | 86 | 2.1130 | 0.7273 |
156
+ | 0.0324 | 87.0 | 87 | 2.1181 | 0.7273 |
157
+ | 0.0324 | 88.0 | 88 | 2.1180 | 0.7273 |
158
+ | 0.0324 | 89.0 | 89 | 2.1173 | 0.7273 |
159
+ | 0.0244 | 90.0 | 90 | 2.1193 | 0.7273 |
160
+ | 0.0244 | 91.0 | 91 | 2.1226 | 0.7273 |
161
+ | 0.0244 | 92.0 | 92 | 2.1256 | 0.7273 |
162
+ | 0.0244 | 93.0 | 93 | 2.1312 | 0.7273 |
163
+ | 0.0244 | 94.0 | 94 | 2.1333 | 0.7273 |
164
+ | 0.0244 | 95.0 | 95 | 2.1371 | 0.7273 |
165
+ | 0.0244 | 96.0 | 96 | 2.1413 | 0.7273 |
166
+ | 0.0244 | 97.0 | 97 | 2.1438 | 0.7273 |
167
+ | 0.0244 | 98.0 | 98 | 2.1454 | 0.7273 |
168
+ | 0.0244 | 99.0 | 99 | 2.1451 | 0.7273 |
169
+ | 0.027 | 100.0 | 100 | 2.1448 | 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 sha256:2acdfd3cd2d644496ba4e02743bf80ad17aebd1aebbba5b97257d76b1f7e5a70
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8466f547874f83a9f9d1a9842d5d6eb76188d5f0e146dcae1a9e3743f4d79a1
3
  size 343233492
runs/May22_16-23-57_927069b479b5/events.out.tfevents.1716395038.927069b479b5.252.44 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fa8bca83bde8508a5721fb38e354d7a89000831fbc7bfb281b2c66102a9265c
3
- size 37308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcaaf85203a4525f85acb83ab0dcc574be150a387a63114af7792eb491b0e159
3
+ size 39131