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-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: 0.8837209302325582
|
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-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: 0.5202
|
36 |
+
- Accuracy: 0.8837
|
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 | 0.8041 | 0.3488 |
|
71 |
+
| No log | 2.0 | 4 | 0.6042 | 0.7209 |
|
72 |
+
| No log | 3.0 | 6 | 0.6582 | 0.6977 |
|
73 |
+
| No log | 4.0 | 8 | 0.7007 | 0.6977 |
|
74 |
+
| 0.6827 | 5.0 | 10 | 0.5653 | 0.6977 |
|
75 |
+
| 0.6827 | 6.0 | 12 | 0.4345 | 0.8140 |
|
76 |
+
| 0.6827 | 7.0 | 14 | 0.4493 | 0.8140 |
|
77 |
+
| 0.6827 | 8.0 | 16 | 0.4764 | 0.8140 |
|
78 |
+
| 0.6827 | 9.0 | 18 | 0.3636 | 0.8372 |
|
79 |
+
| 0.4147 | 10.0 | 20 | 0.2769 | 0.8605 |
|
80 |
+
| 0.4147 | 11.0 | 22 | 0.3538 | 0.8372 |
|
81 |
+
| 0.4147 | 12.0 | 24 | 0.3320 | 0.8605 |
|
82 |
+
| 0.4147 | 13.0 | 26 | 0.2668 | 0.8372 |
|
83 |
+
| 0.4147 | 14.0 | 28 | 0.2823 | 0.8140 |
|
84 |
+
| 0.3405 | 15.0 | 30 | 0.4864 | 0.8372 |
|
85 |
+
| 0.3405 | 16.0 | 32 | 0.4416 | 0.8372 |
|
86 |
+
| 0.3405 | 17.0 | 34 | 0.3585 | 0.8140 |
|
87 |
+
| 0.3405 | 18.0 | 36 | 0.4769 | 0.8372 |
|
88 |
+
| 0.3405 | 19.0 | 38 | 0.5918 | 0.8372 |
|
89 |
+
| 0.3074 | 20.0 | 40 | 0.4116 | 0.8605 |
|
90 |
+
| 0.3074 | 21.0 | 42 | 0.4578 | 0.8372 |
|
91 |
+
| 0.3074 | 22.0 | 44 | 0.4294 | 0.8605 |
|
92 |
+
| 0.3074 | 23.0 | 46 | 0.5401 | 0.8372 |
|
93 |
+
| 0.3074 | 24.0 | 48 | 0.2069 | 0.8837 |
|
94 |
+
| 0.2155 | 25.0 | 50 | 0.2216 | 0.8837 |
|
95 |
+
| 0.2155 | 26.0 | 52 | 0.3837 | 0.8837 |
|
96 |
+
| 0.2155 | 27.0 | 54 | 0.2473 | 0.9070 |
|
97 |
+
| 0.2155 | 28.0 | 56 | 0.2233 | 0.9070 |
|
98 |
+
| 0.2155 | 29.0 | 58 | 0.3489 | 0.8837 |
|
99 |
+
| 0.1874 | 30.0 | 60 | 0.4635 | 0.8605 |
|
100 |
+
| 0.1874 | 31.0 | 62 | 0.2491 | 0.8837 |
|
101 |
+
| 0.1874 | 32.0 | 64 | 0.2564 | 0.8837 |
|
102 |
+
| 0.1874 | 33.0 | 66 | 0.3655 | 0.8837 |
|
103 |
+
| 0.1874 | 34.0 | 68 | 0.2498 | 0.9302 |
|
104 |
+
| 0.1324 | 35.0 | 70 | 0.2922 | 0.8837 |
|
105 |
+
| 0.1324 | 36.0 | 72 | 0.5368 | 0.8837 |
|
106 |
+
| 0.1324 | 37.0 | 74 | 0.5739 | 0.8837 |
|
107 |
+
| 0.1324 | 38.0 | 76 | 0.5049 | 0.8837 |
|
108 |
+
| 0.1324 | 39.0 | 78 | 0.5903 | 0.8837 |
|
109 |
+
| 0.1222 | 40.0 | 80 | 0.4886 | 0.8837 |
|
110 |
+
| 0.1222 | 41.0 | 82 | 0.4174 | 0.8837 |
|
111 |
+
| 0.1222 | 42.0 | 84 | 0.5429 | 0.8605 |
|
112 |
+
| 0.1222 | 43.0 | 86 | 0.6897 | 0.8605 |
|
113 |
+
| 0.1222 | 44.0 | 88 | 0.6805 | 0.8605 |
|
114 |
+
| 0.1008 | 45.0 | 90 | 0.4073 | 0.8837 |
|
115 |
+
| 0.1008 | 46.0 | 92 | 0.4161 | 0.8837 |
|
116 |
+
| 0.1008 | 47.0 | 94 | 0.6485 | 0.8837 |
|
117 |
+
| 0.1008 | 48.0 | 96 | 0.6746 | 0.8837 |
|
118 |
+
| 0.1008 | 49.0 | 98 | 0.4433 | 0.8837 |
|
119 |
+
| 0.117 | 50.0 | 100 | 0.2788 | 0.9535 |
|
120 |
+
| 0.117 | 51.0 | 102 | 0.3441 | 0.8837 |
|
121 |
+
| 0.117 | 52.0 | 104 | 0.4663 | 0.8605 |
|
122 |
+
| 0.117 | 53.0 | 106 | 0.3300 | 0.9070 |
|
123 |
+
| 0.117 | 54.0 | 108 | 0.2531 | 0.9535 |
|
124 |
+
| 0.0879 | 55.0 | 110 | 0.2261 | 0.9535 |
|
125 |
+
| 0.0879 | 56.0 | 112 | 0.3490 | 0.9070 |
|
126 |
+
| 0.0879 | 57.0 | 114 | 0.5060 | 0.8837 |
|
127 |
+
| 0.0879 | 58.0 | 116 | 0.4847 | 0.8837 |
|
128 |
+
| 0.0879 | 59.0 | 118 | 0.3604 | 0.8837 |
|
129 |
+
| 0.0898 | 60.0 | 120 | 0.3626 | 0.8837 |
|
130 |
+
| 0.0898 | 61.0 | 122 | 0.4641 | 0.8837 |
|
131 |
+
| 0.0898 | 62.0 | 124 | 0.4606 | 0.8837 |
|
132 |
+
| 0.0898 | 63.0 | 126 | 0.3419 | 0.8837 |
|
133 |
+
| 0.0898 | 64.0 | 128 | 0.3331 | 0.9070 |
|
134 |
+
| 0.095 | 65.0 | 130 | 0.3804 | 0.8837 |
|
135 |
+
| 0.095 | 66.0 | 132 | 0.3783 | 0.8837 |
|
136 |
+
| 0.095 | 67.0 | 134 | 0.3524 | 0.8837 |
|
137 |
+
| 0.095 | 68.0 | 136 | 0.4232 | 0.8605 |
|
138 |
+
| 0.095 | 69.0 | 138 | 0.4157 | 0.8605 |
|
139 |
+
| 0.0735 | 70.0 | 140 | 0.4937 | 0.8605 |
|
140 |
+
| 0.0735 | 71.0 | 142 | 0.4616 | 0.8605 |
|
141 |
+
| 0.0735 | 72.0 | 144 | 0.4388 | 0.8837 |
|
142 |
+
| 0.0735 | 73.0 | 146 | 0.3811 | 0.8837 |
|
143 |
+
| 0.0735 | 74.0 | 148 | 0.2522 | 0.9302 |
|
144 |
+
| 0.0855 | 75.0 | 150 | 0.1677 | 0.9535 |
|
145 |
+
| 0.0855 | 76.0 | 152 | 0.1653 | 0.9535 |
|
146 |
+
| 0.0855 | 77.0 | 154 | 0.2173 | 0.9535 |
|
147 |
+
| 0.0855 | 78.0 | 156 | 0.3596 | 0.8837 |
|
148 |
+
| 0.0855 | 79.0 | 158 | 0.4653 | 0.8605 |
|
149 |
+
| 0.077 | 80.0 | 160 | 0.4739 | 0.8837 |
|
150 |
+
| 0.077 | 81.0 | 162 | 0.3609 | 0.8837 |
|
151 |
+
| 0.077 | 82.0 | 164 | 0.2334 | 0.9535 |
|
152 |
+
| 0.077 | 83.0 | 166 | 0.2125 | 0.9535 |
|
153 |
+
| 0.077 | 84.0 | 168 | 0.2595 | 0.9535 |
|
154 |
+
| 0.0731 | 85.0 | 170 | 0.3702 | 0.8837 |
|
155 |
+
| 0.0731 | 86.0 | 172 | 0.4634 | 0.8837 |
|
156 |
+
| 0.0731 | 87.0 | 174 | 0.5254 | 0.8837 |
|
157 |
+
| 0.0731 | 88.0 | 176 | 0.5813 | 0.8837 |
|
158 |
+
| 0.0731 | 89.0 | 178 | 0.5628 | 0.8837 |
|
159 |
+
| 0.078 | 90.0 | 180 | 0.5479 | 0.8837 |
|
160 |
+
| 0.078 | 91.0 | 182 | 0.5216 | 0.8837 |
|
161 |
+
| 0.078 | 92.0 | 184 | 0.5098 | 0.8837 |
|
162 |
+
| 0.078 | 93.0 | 186 | 0.5244 | 0.8837 |
|
163 |
+
| 0.078 | 94.0 | 188 | 0.5472 | 0.8837 |
|
164 |
+
| 0.079 | 95.0 | 190 | 0.5590 | 0.8837 |
|
165 |
+
| 0.079 | 96.0 | 192 | 0.5589 | 0.8837 |
|
166 |
+
| 0.079 | 97.0 | 194 | 0.5455 | 0.8837 |
|
167 |
+
| 0.079 | 98.0 | 196 | 0.5322 | 0.8837 |
|
168 |
+
| 0.079 | 99.0 | 198 | 0.5215 | 0.8837 |
|
169 |
+
| 0.0477 | 100.0 | 200 | 0.5202 | 0.8837 |
|
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:a9f7d9632aed180a071e42dd470baa77e61838d083adb771d1f37c418eb30471
|
3 |
size 343230408
|
runs/May22_01-39-51_804716d6a90a/events.out.tfevents.1716341992.804716d6a90a.958.28
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 sha256:24efbccf3654c320a64e885466084137d94fd634443974cf085034621ae8980f
|
3 |
+
size 41359
|