Commit
•
c0ff4a8
1
Parent(s):
13f41f4
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-patch16-224-55-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: 0.759493670886076
|
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-patch16-224-55-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: 0.7541
|
36 |
+
- Accuracy: 0.7595
|
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 | 0.8571 | 3 | 0.7319 | 0.5190 |
|
71 |
+
| No log | 2.0 | 7 | 0.6756 | 0.5696 |
|
72 |
+
| 0.6544 | 2.8571 | 10 | 0.6199 | 0.6456 |
|
73 |
+
| 0.6544 | 4.0 | 14 | 0.5987 | 0.6203 |
|
74 |
+
| 0.6544 | 4.8571 | 17 | 0.5676 | 0.6709 |
|
75 |
+
| 0.6173 | 6.0 | 21 | 0.6543 | 0.5823 |
|
76 |
+
| 0.6173 | 6.8571 | 24 | 0.5310 | 0.7342 |
|
77 |
+
| 0.6173 | 8.0 | 28 | 0.6724 | 0.6076 |
|
78 |
+
| 0.5245 | 8.8571 | 31 | 0.6444 | 0.6582 |
|
79 |
+
| 0.5245 | 10.0 | 35 | 0.5027 | 0.7342 |
|
80 |
+
| 0.5245 | 10.8571 | 38 | 0.6328 | 0.6582 |
|
81 |
+
| 0.4554 | 12.0 | 42 | 0.4883 | 0.7595 |
|
82 |
+
| 0.4554 | 12.8571 | 45 | 0.6736 | 0.6582 |
|
83 |
+
| 0.4554 | 14.0 | 49 | 0.4584 | 0.7342 |
|
84 |
+
| 0.4575 | 14.8571 | 52 | 0.8099 | 0.6456 |
|
85 |
+
| 0.4575 | 16.0 | 56 | 0.4767 | 0.7468 |
|
86 |
+
| 0.4575 | 16.8571 | 59 | 0.6059 | 0.6835 |
|
87 |
+
| 0.3798 | 18.0 | 63 | 0.4863 | 0.7595 |
|
88 |
+
| 0.3798 | 18.8571 | 66 | 0.5636 | 0.7468 |
|
89 |
+
| 0.3419 | 20.0 | 70 | 0.4677 | 0.7342 |
|
90 |
+
| 0.3419 | 20.8571 | 73 | 0.4883 | 0.7089 |
|
91 |
+
| 0.3419 | 22.0 | 77 | 0.5549 | 0.7215 |
|
92 |
+
| 0.3079 | 22.8571 | 80 | 0.4324 | 0.7848 |
|
93 |
+
| 0.3079 | 24.0 | 84 | 0.6184 | 0.6709 |
|
94 |
+
| 0.3079 | 24.8571 | 87 | 0.6149 | 0.7089 |
|
95 |
+
| 0.2616 | 26.0 | 91 | 0.4488 | 0.7848 |
|
96 |
+
| 0.2616 | 26.8571 | 94 | 0.4368 | 0.7722 |
|
97 |
+
| 0.2616 | 28.0 | 98 | 0.4566 | 0.7722 |
|
98 |
+
| 0.2157 | 28.8571 | 101 | 0.4657 | 0.7848 |
|
99 |
+
| 0.2157 | 30.0 | 105 | 0.4514 | 0.7722 |
|
100 |
+
| 0.2157 | 30.8571 | 108 | 0.5083 | 0.7848 |
|
101 |
+
| 0.2258 | 32.0 | 112 | 0.5261 | 0.7848 |
|
102 |
+
| 0.2258 | 32.8571 | 115 | 0.5567 | 0.7595 |
|
103 |
+
| 0.2258 | 34.0 | 119 | 0.5566 | 0.8101 |
|
104 |
+
| 0.1972 | 34.8571 | 122 | 0.5495 | 0.8101 |
|
105 |
+
| 0.1972 | 36.0 | 126 | 0.4992 | 0.7975 |
|
106 |
+
| 0.1972 | 36.8571 | 129 | 0.5661 | 0.7595 |
|
107 |
+
| 0.1709 | 38.0 | 133 | 0.7326 | 0.7342 |
|
108 |
+
| 0.1709 | 38.8571 | 136 | 0.5635 | 0.8101 |
|
109 |
+
| 0.1537 | 40.0 | 140 | 0.8130 | 0.7468 |
|
110 |
+
| 0.1537 | 40.8571 | 143 | 0.6984 | 0.7848 |
|
111 |
+
| 0.1537 | 42.0 | 147 | 0.7777 | 0.7595 |
|
112 |
+
| 0.1687 | 42.8571 | 150 | 0.6452 | 0.8228 |
|
113 |
+
| 0.1687 | 44.0 | 154 | 0.8527 | 0.7215 |
|
114 |
+
| 0.1687 | 44.8571 | 157 | 0.6483 | 0.7975 |
|
115 |
+
| 0.1588 | 46.0 | 161 | 0.8185 | 0.7342 |
|
116 |
+
| 0.1588 | 46.8571 | 164 | 0.6821 | 0.7722 |
|
117 |
+
| 0.1588 | 48.0 | 168 | 0.7594 | 0.7342 |
|
118 |
+
| 0.144 | 48.8571 | 171 | 1.0232 | 0.7595 |
|
119 |
+
| 0.144 | 50.0 | 175 | 0.6178 | 0.7848 |
|
120 |
+
| 0.144 | 50.8571 | 178 | 0.6243 | 0.7595 |
|
121 |
+
| 0.1449 | 52.0 | 182 | 0.8159 | 0.7342 |
|
122 |
+
| 0.1449 | 52.8571 | 185 | 0.6664 | 0.7722 |
|
123 |
+
| 0.1449 | 54.0 | 189 | 0.7070 | 0.7342 |
|
124 |
+
| 0.144 | 54.8571 | 192 | 0.7361 | 0.7468 |
|
125 |
+
| 0.144 | 56.0 | 196 | 0.6656 | 0.7595 |
|
126 |
+
| 0.144 | 56.8571 | 199 | 0.7487 | 0.7468 |
|
127 |
+
| 0.1199 | 58.0 | 203 | 0.7993 | 0.7342 |
|
128 |
+
| 0.1199 | 58.8571 | 206 | 0.7426 | 0.7722 |
|
129 |
+
| 0.1258 | 60.0 | 210 | 0.7531 | 0.7975 |
|
130 |
+
| 0.1258 | 60.8571 | 213 | 0.7388 | 0.7848 |
|
131 |
+
| 0.1258 | 62.0 | 217 | 0.7395 | 0.7975 |
|
132 |
+
| 0.1392 | 62.8571 | 220 | 0.8238 | 0.7468 |
|
133 |
+
| 0.1392 | 64.0 | 224 | 0.9302 | 0.7215 |
|
134 |
+
| 0.1392 | 64.8571 | 227 | 0.7539 | 0.7722 |
|
135 |
+
| 0.1303 | 66.0 | 231 | 0.6739 | 0.8101 |
|
136 |
+
| 0.1303 | 66.8571 | 234 | 0.6627 | 0.7848 |
|
137 |
+
| 0.1303 | 68.0 | 238 | 0.6403 | 0.7848 |
|
138 |
+
| 0.1423 | 68.8571 | 241 | 0.6379 | 0.7975 |
|
139 |
+
| 0.1423 | 70.0 | 245 | 0.7658 | 0.7595 |
|
140 |
+
| 0.1423 | 70.8571 | 248 | 0.9195 | 0.7342 |
|
141 |
+
| 0.1019 | 72.0 | 252 | 0.7287 | 0.7722 |
|
142 |
+
| 0.1019 | 72.8571 | 255 | 0.6548 | 0.7975 |
|
143 |
+
| 0.1019 | 74.0 | 259 | 0.6534 | 0.7848 |
|
144 |
+
| 0.1286 | 74.8571 | 262 | 0.7331 | 0.7848 |
|
145 |
+
| 0.1286 | 76.0 | 266 | 0.7845 | 0.7595 |
|
146 |
+
| 0.1286 | 76.8571 | 269 | 0.7188 | 0.7975 |
|
147 |
+
| 0.1054 | 78.0 | 273 | 0.6595 | 0.7722 |
|
148 |
+
| 0.1054 | 78.8571 | 276 | 0.6623 | 0.7722 |
|
149 |
+
| 0.1053 | 80.0 | 280 | 0.7337 | 0.7722 |
|
150 |
+
| 0.1053 | 80.8571 | 283 | 0.8085 | 0.7468 |
|
151 |
+
| 0.1053 | 82.0 | 287 | 0.8201 | 0.7468 |
|
152 |
+
| 0.1086 | 82.8571 | 290 | 0.7947 | 0.7468 |
|
153 |
+
| 0.1086 | 84.0 | 294 | 0.7669 | 0.7722 |
|
154 |
+
| 0.1086 | 84.8571 | 297 | 0.7582 | 0.7595 |
|
155 |
+
| 0.1186 | 85.7143 | 300 | 0.7541 | 0.7595 |
|
156 |
+
|
157 |
+
|
158 |
+
### Framework versions
|
159 |
+
|
160 |
+
- Transformers 4.41.0
|
161 |
+
- Pytorch 2.3.0+cu121
|
162 |
+
- Datasets 2.19.1
|
163 |
+
- 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 sha256:9687a8d66e6870faef6692a228507eab199154ee89e8b0d798f69d8dd8e75526
|
3 |
size 343230408
|
runs/May21_21-38-00_804716d6a90a/events.out.tfevents.1716327481.804716d6a90a.958.8
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:e41fa4714060f16a4f894abea8dfa8a719517fdd6576f53d44560a07820d47c7
|
3 |
+
size 39109
|