BilalMuftuoglu
commited on
Commit
•
75c5fdb
1
Parent(s):
22cd396
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-patch16-224-75-fold2
|
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: 0.9302325581395349
|
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-patch16-224-75-fold2
|
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: 0.2482
|
36 |
+
- Accuracy: 0.9302
|
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 | 2 | 0.8815 | 0.4419 |
|
71 |
+
| No log | 2.0 | 4 | 0.6436 | 0.6977 |
|
72 |
+
| No log | 3.0 | 6 | 0.8488 | 0.6977 |
|
73 |
+
| No log | 4.0 | 8 | 0.8219 | 0.6977 |
|
74 |
+
| 0.6918 | 5.0 | 10 | 0.5491 | 0.6977 |
|
75 |
+
| 0.6918 | 6.0 | 12 | 0.4603 | 0.7209 |
|
76 |
+
| 0.6918 | 7.0 | 14 | 0.5602 | 0.7442 |
|
77 |
+
| 0.6918 | 8.0 | 16 | 0.5694 | 0.7442 |
|
78 |
+
| 0.6918 | 9.0 | 18 | 0.4430 | 0.8140 |
|
79 |
+
| 0.3867 | 10.0 | 20 | 0.3880 | 0.8605 |
|
80 |
+
| 0.3867 | 11.0 | 22 | 0.5069 | 0.8140 |
|
81 |
+
| 0.3867 | 12.0 | 24 | 0.3739 | 0.8605 |
|
82 |
+
| 0.3867 | 13.0 | 26 | 0.2981 | 0.8837 |
|
83 |
+
| 0.3867 | 14.0 | 28 | 0.3170 | 0.8837 |
|
84 |
+
| 0.2722 | 15.0 | 30 | 0.2511 | 0.8837 |
|
85 |
+
| 0.2722 | 16.0 | 32 | 0.2408 | 0.8837 |
|
86 |
+
| 0.2722 | 17.0 | 34 | 0.3751 | 0.8605 |
|
87 |
+
| 0.2722 | 18.0 | 36 | 0.3081 | 0.8605 |
|
88 |
+
| 0.2722 | 19.0 | 38 | 0.2489 | 0.8837 |
|
89 |
+
| 0.209 | 20.0 | 40 | 0.2802 | 0.8837 |
|
90 |
+
| 0.209 | 21.0 | 42 | 0.2625 | 0.9302 |
|
91 |
+
| 0.209 | 22.0 | 44 | 0.2595 | 0.9302 |
|
92 |
+
| 0.209 | 23.0 | 46 | 0.5048 | 0.8372 |
|
93 |
+
| 0.209 | 24.0 | 48 | 0.2880 | 0.8605 |
|
94 |
+
| 0.2027 | 25.0 | 50 | 0.2860 | 0.8372 |
|
95 |
+
| 0.2027 | 26.0 | 52 | 0.4067 | 0.8372 |
|
96 |
+
| 0.2027 | 27.0 | 54 | 0.2462 | 0.9070 |
|
97 |
+
| 0.2027 | 28.0 | 56 | 0.2753 | 0.9070 |
|
98 |
+
| 0.2027 | 29.0 | 58 | 0.3699 | 0.8140 |
|
99 |
+
| 0.1426 | 30.0 | 60 | 0.4983 | 0.8372 |
|
100 |
+
| 0.1426 | 31.0 | 62 | 0.3140 | 0.8605 |
|
101 |
+
| 0.1426 | 32.0 | 64 | 0.3470 | 0.8372 |
|
102 |
+
| 0.1426 | 33.0 | 66 | 0.4443 | 0.8372 |
|
103 |
+
| 0.1426 | 34.0 | 68 | 0.2583 | 0.8837 |
|
104 |
+
| 0.1385 | 35.0 | 70 | 0.2239 | 0.9302 |
|
105 |
+
| 0.1385 | 36.0 | 72 | 0.2708 | 0.9070 |
|
106 |
+
| 0.1385 | 37.0 | 74 | 0.2660 | 0.9070 |
|
107 |
+
| 0.1385 | 38.0 | 76 | 0.2754 | 0.9070 |
|
108 |
+
| 0.1385 | 39.0 | 78 | 0.4246 | 0.8605 |
|
109 |
+
| 0.1202 | 40.0 | 80 | 0.2779 | 0.9070 |
|
110 |
+
| 0.1202 | 41.0 | 82 | 0.2726 | 0.8837 |
|
111 |
+
| 0.1202 | 42.0 | 84 | 0.2536 | 0.9070 |
|
112 |
+
| 0.1202 | 43.0 | 86 | 0.2667 | 0.9302 |
|
113 |
+
| 0.1202 | 44.0 | 88 | 0.4191 | 0.8837 |
|
114 |
+
| 0.1211 | 45.0 | 90 | 0.3213 | 0.9302 |
|
115 |
+
| 0.1211 | 46.0 | 92 | 0.2290 | 0.9070 |
|
116 |
+
| 0.1211 | 47.0 | 94 | 0.3043 | 0.8837 |
|
117 |
+
| 0.1211 | 48.0 | 96 | 0.1906 | 0.9302 |
|
118 |
+
| 0.1211 | 49.0 | 98 | 0.3201 | 0.8605 |
|
119 |
+
| 0.1067 | 50.0 | 100 | 0.3062 | 0.8837 |
|
120 |
+
| 0.1067 | 51.0 | 102 | 0.2047 | 0.9302 |
|
121 |
+
| 0.1067 | 52.0 | 104 | 0.2116 | 0.9070 |
|
122 |
+
| 0.1067 | 53.0 | 106 | 0.2113 | 0.9302 |
|
123 |
+
| 0.1067 | 54.0 | 108 | 0.2340 | 0.9302 |
|
124 |
+
| 0.0826 | 55.0 | 110 | 0.2328 | 0.9302 |
|
125 |
+
| 0.0826 | 56.0 | 112 | 0.2824 | 0.8837 |
|
126 |
+
| 0.0826 | 57.0 | 114 | 0.2921 | 0.8837 |
|
127 |
+
| 0.0826 | 58.0 | 116 | 0.2608 | 0.9302 |
|
128 |
+
| 0.0826 | 59.0 | 118 | 0.2650 | 0.9302 |
|
129 |
+
| 0.0894 | 60.0 | 120 | 0.2878 | 0.9070 |
|
130 |
+
| 0.0894 | 61.0 | 122 | 0.2935 | 0.9070 |
|
131 |
+
| 0.0894 | 62.0 | 124 | 0.2656 | 0.9302 |
|
132 |
+
| 0.0894 | 63.0 | 126 | 0.3438 | 0.9070 |
|
133 |
+
| 0.0894 | 64.0 | 128 | 0.2840 | 0.9302 |
|
134 |
+
| 0.0964 | 65.0 | 130 | 0.2711 | 0.9070 |
|
135 |
+
| 0.0964 | 66.0 | 132 | 0.2888 | 0.9070 |
|
136 |
+
| 0.0964 | 67.0 | 134 | 0.2723 | 0.9070 |
|
137 |
+
| 0.0964 | 68.0 | 136 | 0.2563 | 0.8837 |
|
138 |
+
| 0.0964 | 69.0 | 138 | 0.2336 | 0.9302 |
|
139 |
+
| 0.0711 | 70.0 | 140 | 0.2386 | 0.9302 |
|
140 |
+
| 0.0711 | 71.0 | 142 | 0.2482 | 0.9070 |
|
141 |
+
| 0.0711 | 72.0 | 144 | 0.2821 | 0.9070 |
|
142 |
+
| 0.0711 | 73.0 | 146 | 0.2941 | 0.8837 |
|
143 |
+
| 0.0711 | 74.0 | 148 | 0.2564 | 0.9070 |
|
144 |
+
| 0.0824 | 75.0 | 150 | 0.2509 | 0.9302 |
|
145 |
+
| 0.0824 | 76.0 | 152 | 0.2544 | 0.9302 |
|
146 |
+
| 0.0824 | 77.0 | 154 | 0.2474 | 0.9302 |
|
147 |
+
| 0.0824 | 78.0 | 156 | 0.2375 | 0.9302 |
|
148 |
+
| 0.0824 | 79.0 | 158 | 0.2389 | 0.9302 |
|
149 |
+
| 0.0691 | 80.0 | 160 | 0.2371 | 0.9302 |
|
150 |
+
| 0.0691 | 81.0 | 162 | 0.2393 | 0.9302 |
|
151 |
+
| 0.0691 | 82.0 | 164 | 0.2523 | 0.9070 |
|
152 |
+
| 0.0691 | 83.0 | 166 | 0.2677 | 0.8837 |
|
153 |
+
| 0.0691 | 84.0 | 168 | 0.2945 | 0.8837 |
|
154 |
+
| 0.0638 | 85.0 | 170 | 0.3245 | 0.8605 |
|
155 |
+
| 0.0638 | 86.0 | 172 | 0.2960 | 0.8837 |
|
156 |
+
| 0.0638 | 87.0 | 174 | 0.2658 | 0.9302 |
|
157 |
+
| 0.0638 | 88.0 | 176 | 0.2614 | 0.9302 |
|
158 |
+
| 0.0638 | 89.0 | 178 | 0.2613 | 0.9302 |
|
159 |
+
| 0.0705 | 90.0 | 180 | 0.2549 | 0.9302 |
|
160 |
+
| 0.0705 | 91.0 | 182 | 0.2510 | 0.9302 |
|
161 |
+
| 0.0705 | 92.0 | 184 | 0.2514 | 0.9302 |
|
162 |
+
| 0.0705 | 93.0 | 186 | 0.2522 | 0.9302 |
|
163 |
+
| 0.0705 | 94.0 | 188 | 0.2504 | 0.9070 |
|
164 |
+
| 0.0666 | 95.0 | 190 | 0.2459 | 0.9302 |
|
165 |
+
| 0.0666 | 96.0 | 192 | 0.2424 | 0.9302 |
|
166 |
+
| 0.0666 | 97.0 | 194 | 0.2428 | 0.9302 |
|
167 |
+
| 0.0666 | 98.0 | 196 | 0.2451 | 0.9302 |
|
168 |
+
| 0.0666 | 99.0 | 198 | 0.2471 | 0.9302 |
|
169 |
+
| 0.0566 | 100.0 | 200 | 0.2482 | 0.9302 |
|
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:
|
3 |
size 343230408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c5c43e7635db7180115ff4472a8a23eccc5ff804c356fac25d2b8147f2cc56
|
3 |
size 343230408
|
runs/May22_00-42-41_804716d6a90a/events.out.tfevents.1716338562.804716d6a90a.958.22
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9092515c800c6a933d64475a1574130fabaf1fd393a846af0f498f9dc17705fa
|
3 |
+
size 41359
|