BilalMuftuoglu commited on
Commit
688f49a
1 Parent(s): 6394d94

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-75-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: 0.9166666666666666
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-75-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: 0.4170
36
+ - Accuracy: 0.9167
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 | 1.0629 | 0.1667 |
71
+ | No log | 2.0 | 2 | 0.8596 | 0.5833 |
72
+ | No log | 3.0 | 3 | 0.5699 | 0.9167 |
73
+ | No log | 4.0 | 4 | 0.3576 | 0.9167 |
74
+ | No log | 5.0 | 5 | 0.2875 | 0.9167 |
75
+ | No log | 6.0 | 6 | 0.2993 | 0.9167 |
76
+ | No log | 7.0 | 7 | 0.3152 | 0.9167 |
77
+ | No log | 8.0 | 8 | 0.3399 | 0.9167 |
78
+ | No log | 9.0 | 9 | 0.4232 | 0.9167 |
79
+ | 0.3622 | 10.0 | 10 | 0.5129 | 0.9167 |
80
+ | 0.3622 | 11.0 | 11 | 0.4640 | 0.9167 |
81
+ | 0.3622 | 12.0 | 12 | 0.3709 | 0.9167 |
82
+ | 0.3622 | 13.0 | 13 | 0.3229 | 0.9167 |
83
+ | 0.3622 | 14.0 | 14 | 0.3183 | 0.9167 |
84
+ | 0.3622 | 15.0 | 15 | 0.3590 | 0.9167 |
85
+ | 0.3622 | 16.0 | 16 | 0.4468 | 0.9167 |
86
+ | 0.3622 | 17.0 | 17 | 0.5249 | 0.75 |
87
+ | 0.3622 | 18.0 | 18 | 0.4227 | 0.9167 |
88
+ | 0.3622 | 19.0 | 19 | 0.3300 | 0.9167 |
89
+ | 0.1749 | 20.0 | 20 | 0.3031 | 0.9167 |
90
+ | 0.1749 | 21.0 | 21 | 0.2836 | 0.9167 |
91
+ | 0.1749 | 22.0 | 22 | 0.2596 | 0.9167 |
92
+ | 0.1749 | 23.0 | 23 | 0.2215 | 0.9167 |
93
+ | 0.1749 | 24.0 | 24 | 0.1797 | 0.9167 |
94
+ | 0.1749 | 25.0 | 25 | 0.1658 | 0.9167 |
95
+ | 0.1749 | 26.0 | 26 | 0.1600 | 0.9167 |
96
+ | 0.1749 | 27.0 | 27 | 0.1567 | 0.9167 |
97
+ | 0.1749 | 28.0 | 28 | 0.1680 | 0.9167 |
98
+ | 0.1749 | 29.0 | 29 | 0.2079 | 0.9167 |
99
+ | 0.1002 | 30.0 | 30 | 0.2458 | 0.9167 |
100
+ | 0.1002 | 31.0 | 31 | 0.2637 | 0.9167 |
101
+ | 0.1002 | 32.0 | 32 | 0.2795 | 0.9167 |
102
+ | 0.1002 | 33.0 | 33 | 0.3174 | 0.9167 |
103
+ | 0.1002 | 34.0 | 34 | 0.3426 | 0.9167 |
104
+ | 0.1002 | 35.0 | 35 | 0.3858 | 0.9167 |
105
+ | 0.1002 | 36.0 | 36 | 0.4281 | 0.9167 |
106
+ | 0.1002 | 37.0 | 37 | 0.4447 | 0.9167 |
107
+ | 0.1002 | 38.0 | 38 | 0.4355 | 0.9167 |
108
+ | 0.1002 | 39.0 | 39 | 0.4306 | 0.9167 |
109
+ | 0.0662 | 40.0 | 40 | 0.4398 | 0.9167 |
110
+ | 0.0662 | 41.0 | 41 | 0.4657 | 0.9167 |
111
+ | 0.0662 | 42.0 | 42 | 0.4941 | 0.9167 |
112
+ | 0.0662 | 43.0 | 43 | 0.5061 | 0.9167 |
113
+ | 0.0662 | 44.0 | 44 | 0.5010 | 0.9167 |
114
+ | 0.0662 | 45.0 | 45 | 0.4816 | 0.9167 |
115
+ | 0.0662 | 46.0 | 46 | 0.4398 | 0.9167 |
116
+ | 0.0662 | 47.0 | 47 | 0.3948 | 0.9167 |
117
+ | 0.0662 | 48.0 | 48 | 0.3486 | 0.9167 |
118
+ | 0.0662 | 49.0 | 49 | 0.3180 | 0.9167 |
119
+ | 0.0543 | 50.0 | 50 | 0.3029 | 0.9167 |
120
+ | 0.0543 | 51.0 | 51 | 0.3053 | 0.9167 |
121
+ | 0.0543 | 52.0 | 52 | 0.3160 | 0.9167 |
122
+ | 0.0543 | 53.0 | 53 | 0.3449 | 0.9167 |
123
+ | 0.0543 | 54.0 | 54 | 0.3712 | 0.9167 |
124
+ | 0.0543 | 55.0 | 55 | 0.3785 | 0.9167 |
125
+ | 0.0543 | 56.0 | 56 | 0.4049 | 0.9167 |
126
+ | 0.0543 | 57.0 | 57 | 0.4094 | 0.9167 |
127
+ | 0.0543 | 58.0 | 58 | 0.4179 | 0.9167 |
128
+ | 0.0543 | 59.0 | 59 | 0.4083 | 0.9167 |
129
+ | 0.0473 | 60.0 | 60 | 0.3855 | 0.9167 |
130
+ | 0.0473 | 61.0 | 61 | 0.3758 | 0.9167 |
131
+ | 0.0473 | 62.0 | 62 | 0.3675 | 0.9167 |
132
+ | 0.0473 | 63.0 | 63 | 0.3660 | 0.9167 |
133
+ | 0.0473 | 64.0 | 64 | 0.3843 | 0.9167 |
134
+ | 0.0473 | 65.0 | 65 | 0.4092 | 0.9167 |
135
+ | 0.0473 | 66.0 | 66 | 0.4374 | 0.9167 |
136
+ | 0.0473 | 67.0 | 67 | 0.4666 | 0.9167 |
137
+ | 0.0473 | 68.0 | 68 | 0.4798 | 0.9167 |
138
+ | 0.0473 | 69.0 | 69 | 0.4869 | 0.9167 |
139
+ | 0.018 | 70.0 | 70 | 0.4853 | 0.9167 |
140
+ | 0.018 | 71.0 | 71 | 0.4783 | 0.9167 |
141
+ | 0.018 | 72.0 | 72 | 0.4649 | 0.9167 |
142
+ | 0.018 | 73.0 | 73 | 0.4525 | 0.9167 |
143
+ | 0.018 | 74.0 | 74 | 0.4411 | 0.9167 |
144
+ | 0.018 | 75.0 | 75 | 0.4355 | 0.9167 |
145
+ | 0.018 | 76.0 | 76 | 0.4310 | 0.9167 |
146
+ | 0.018 | 77.0 | 77 | 0.4330 | 0.9167 |
147
+ | 0.018 | 78.0 | 78 | 0.4296 | 0.9167 |
148
+ | 0.018 | 79.0 | 79 | 0.4264 | 0.9167 |
149
+ | 0.0195 | 80.0 | 80 | 0.4204 | 0.9167 |
150
+ | 0.0195 | 81.0 | 81 | 0.4182 | 0.9167 |
151
+ | 0.0195 | 82.0 | 82 | 0.4193 | 0.9167 |
152
+ | 0.0195 | 83.0 | 83 | 0.4225 | 0.9167 |
153
+ | 0.0195 | 84.0 | 84 | 0.4208 | 0.9167 |
154
+ | 0.0195 | 85.0 | 85 | 0.4193 | 0.9167 |
155
+ | 0.0195 | 86.0 | 86 | 0.4185 | 0.9167 |
156
+ | 0.0195 | 87.0 | 87 | 0.4186 | 0.9167 |
157
+ | 0.0195 | 88.0 | 88 | 0.4163 | 0.9167 |
158
+ | 0.0195 | 89.0 | 89 | 0.4076 | 0.9167 |
159
+ | 0.0203 | 90.0 | 90 | 0.4032 | 0.9167 |
160
+ | 0.0203 | 91.0 | 91 | 0.4000 | 0.9167 |
161
+ | 0.0203 | 92.0 | 92 | 0.4003 | 0.9167 |
162
+ | 0.0203 | 93.0 | 93 | 0.4033 | 0.9167 |
163
+ | 0.0203 | 94.0 | 94 | 0.4079 | 0.9167 |
164
+ | 0.0203 | 95.0 | 95 | 0.4112 | 0.9167 |
165
+ | 0.0203 | 96.0 | 96 | 0.4138 | 0.9167 |
166
+ | 0.0203 | 97.0 | 97 | 0.4155 | 0.9167 |
167
+ | 0.0203 | 98.0 | 98 | 0.4167 | 0.9167 |
168
+ | 0.0203 | 99.0 | 99 | 0.4169 | 0.9167 |
169
+ | 0.0252 | 100.0 | 100 | 0.4170 | 0.9167 |
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:a1faa9d16d64d5c3338182b5f56c2dfd2e8193e53cfe7b43ad7d805f8c40c6e4
3
  size 343233492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fea114e3041020103ae81336ef00fbbb31c474a993e0c8923dab1a1c57f8b4
3
  size 343233492
runs/May22_15-30-32_927069b479b5/events.out.tfevents.1716391833.927069b479b5.252.30 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b59483f2a696e5ea5a5dc6172b5e9615cb2155a03f29194e358ce71559f80d2
3
- size 37942
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6922b2522c6f51f4bc4595007b5e1208d3ed58f06008d9b51c9bbb8012d0f861
3
+ size 39131