Model save
Browse files
README.md
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-patch16-224-65-fold4
|
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: 0.7746478873239436
|
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-patch16-224-65-fold4
|
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: 0.6081
|
36 |
+
- Accuracy: 0.7746
|
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 | 0.9231 | 3 | 0.7219 | 0.5493 |
|
71 |
+
| No log | 1.8462 | 6 | 0.6863 | 0.5493 |
|
72 |
+
| No log | 2.7692 | 9 | 0.6578 | 0.5493 |
|
73 |
+
| 0.6825 | 4.0 | 13 | 0.6293 | 0.6338 |
|
74 |
+
| 0.6825 | 4.9231 | 16 | 0.6186 | 0.6761 |
|
75 |
+
| 0.6825 | 5.8462 | 19 | 0.6135 | 0.7042 |
|
76 |
+
| 0.6206 | 6.7692 | 22 | 0.6163 | 0.6479 |
|
77 |
+
| 0.6206 | 8.0 | 26 | 0.6350 | 0.6479 |
|
78 |
+
| 0.6206 | 8.9231 | 29 | 0.6078 | 0.6901 |
|
79 |
+
| 0.5728 | 9.8462 | 32 | 0.6873 | 0.6761 |
|
80 |
+
| 0.5728 | 10.7692 | 35 | 0.6771 | 0.6761 |
|
81 |
+
| 0.5728 | 12.0 | 39 | 0.5912 | 0.6620 |
|
82 |
+
| 0.5329 | 12.9231 | 42 | 0.5524 | 0.7465 |
|
83 |
+
| 0.5329 | 13.8462 | 45 | 0.5923 | 0.7183 |
|
84 |
+
| 0.5329 | 14.7692 | 48 | 0.6650 | 0.6761 |
|
85 |
+
| 0.4279 | 16.0 | 52 | 0.5183 | 0.7746 |
|
86 |
+
| 0.4279 | 16.9231 | 55 | 0.4761 | 0.7887 |
|
87 |
+
| 0.4279 | 17.8462 | 58 | 0.5590 | 0.7183 |
|
88 |
+
| 0.4055 | 18.7692 | 61 | 0.5320 | 0.7465 |
|
89 |
+
| 0.4055 | 20.0 | 65 | 0.6605 | 0.7183 |
|
90 |
+
| 0.4055 | 20.9231 | 68 | 0.5821 | 0.7465 |
|
91 |
+
| 0.3478 | 21.8462 | 71 | 0.5589 | 0.7465 |
|
92 |
+
| 0.3478 | 22.7692 | 74 | 0.6247 | 0.7465 |
|
93 |
+
| 0.3478 | 24.0 | 78 | 0.7006 | 0.6620 |
|
94 |
+
| 0.3769 | 24.9231 | 81 | 0.7575 | 0.7183 |
|
95 |
+
| 0.3769 | 25.8462 | 84 | 0.5367 | 0.7746 |
|
96 |
+
| 0.3769 | 26.7692 | 87 | 0.5335 | 0.7746 |
|
97 |
+
| 0.2957 | 28.0 | 91 | 0.5914 | 0.7606 |
|
98 |
+
| 0.2957 | 28.9231 | 94 | 0.6780 | 0.7465 |
|
99 |
+
| 0.2957 | 29.8462 | 97 | 0.5345 | 0.7746 |
|
100 |
+
| 0.2463 | 30.7692 | 100 | 0.6132 | 0.7606 |
|
101 |
+
| 0.2463 | 32.0 | 104 | 0.5758 | 0.7887 |
|
102 |
+
| 0.2463 | 32.9231 | 107 | 0.7236 | 0.7324 |
|
103 |
+
| 0.2323 | 33.8462 | 110 | 0.5247 | 0.8169 |
|
104 |
+
| 0.2323 | 34.7692 | 113 | 0.6018 | 0.7183 |
|
105 |
+
| 0.2323 | 36.0 | 117 | 0.5366 | 0.8028 |
|
106 |
+
| 0.1921 | 36.9231 | 120 | 0.6314 | 0.7465 |
|
107 |
+
| 0.1921 | 37.8462 | 123 | 0.5763 | 0.7746 |
|
108 |
+
| 0.1921 | 38.7692 | 126 | 0.5574 | 0.8028 |
|
109 |
+
| 0.1686 | 40.0 | 130 | 0.6261 | 0.7887 |
|
110 |
+
| 0.1686 | 40.9231 | 133 | 0.6525 | 0.7887 |
|
111 |
+
| 0.1686 | 41.8462 | 136 | 0.5726 | 0.8169 |
|
112 |
+
| 0.1686 | 42.7692 | 139 | 0.8200 | 0.7042 |
|
113 |
+
| 0.2073 | 44.0 | 143 | 0.4798 | 0.7887 |
|
114 |
+
| 0.2073 | 44.9231 | 146 | 0.5342 | 0.7887 |
|
115 |
+
| 0.2073 | 45.8462 | 149 | 0.4834 | 0.7887 |
|
116 |
+
| 0.1702 | 46.7692 | 152 | 0.6101 | 0.7465 |
|
117 |
+
| 0.1702 | 48.0 | 156 | 0.4779 | 0.8169 |
|
118 |
+
| 0.1702 | 48.9231 | 159 | 0.5048 | 0.7887 |
|
119 |
+
| 0.153 | 49.8462 | 162 | 0.6298 | 0.7465 |
|
120 |
+
| 0.153 | 50.7692 | 165 | 0.5995 | 0.7606 |
|
121 |
+
| 0.153 | 52.0 | 169 | 0.6475 | 0.7042 |
|
122 |
+
| 0.1508 | 52.9231 | 172 | 0.4888 | 0.8028 |
|
123 |
+
| 0.1508 | 53.8462 | 175 | 0.4954 | 0.8310 |
|
124 |
+
| 0.1508 | 54.7692 | 178 | 0.4390 | 0.8028 |
|
125 |
+
| 0.1293 | 56.0 | 182 | 0.4778 | 0.8592 |
|
126 |
+
| 0.1293 | 56.9231 | 185 | 0.4888 | 0.8310 |
|
127 |
+
| 0.1293 | 57.8462 | 188 | 0.4832 | 0.8732 |
|
128 |
+
| 0.1489 | 58.7692 | 191 | 0.5277 | 0.8310 |
|
129 |
+
| 0.1489 | 60.0 | 195 | 0.6217 | 0.7324 |
|
130 |
+
| 0.1489 | 60.9231 | 198 | 0.6090 | 0.7465 |
|
131 |
+
| 0.1487 | 61.8462 | 201 | 0.5424 | 0.8451 |
|
132 |
+
| 0.1487 | 62.7692 | 204 | 0.5570 | 0.8451 |
|
133 |
+
| 0.1487 | 64.0 | 208 | 0.7248 | 0.7183 |
|
134 |
+
| 0.1456 | 64.9231 | 211 | 0.5841 | 0.7887 |
|
135 |
+
| 0.1456 | 65.8462 | 214 | 0.5905 | 0.8310 |
|
136 |
+
| 0.1456 | 66.7692 | 217 | 0.5609 | 0.8310 |
|
137 |
+
| 0.1284 | 68.0 | 221 | 0.5470 | 0.8028 |
|
138 |
+
| 0.1284 | 68.9231 | 224 | 0.5473 | 0.8310 |
|
139 |
+
| 0.1284 | 69.8462 | 227 | 0.5813 | 0.8310 |
|
140 |
+
| 0.1225 | 70.7692 | 230 | 0.5683 | 0.8451 |
|
141 |
+
| 0.1225 | 72.0 | 234 | 0.5581 | 0.8310 |
|
142 |
+
| 0.1225 | 72.9231 | 237 | 0.5717 | 0.7887 |
|
143 |
+
| 0.1233 | 73.8462 | 240 | 0.6054 | 0.7606 |
|
144 |
+
| 0.1233 | 74.7692 | 243 | 0.5910 | 0.7887 |
|
145 |
+
| 0.1233 | 76.0 | 247 | 0.5707 | 0.8169 |
|
146 |
+
| 0.1234 | 76.9231 | 250 | 0.5733 | 0.8028 |
|
147 |
+
| 0.1234 | 77.8462 | 253 | 0.5748 | 0.8028 |
|
148 |
+
| 0.1234 | 78.7692 | 256 | 0.5723 | 0.7887 |
|
149 |
+
| 0.1219 | 80.0 | 260 | 0.5503 | 0.8169 |
|
150 |
+
| 0.1219 | 80.9231 | 263 | 0.5532 | 0.8028 |
|
151 |
+
| 0.1219 | 81.8462 | 266 | 0.5828 | 0.7746 |
|
152 |
+
| 0.1219 | 82.7692 | 269 | 0.6062 | 0.7746 |
|
153 |
+
| 0.1075 | 84.0 | 273 | 0.5752 | 0.8028 |
|
154 |
+
| 0.1075 | 84.9231 | 276 | 0.5748 | 0.8028 |
|
155 |
+
| 0.1075 | 85.8462 | 279 | 0.5776 | 0.8169 |
|
156 |
+
| 0.1013 | 86.7692 | 282 | 0.5844 | 0.8028 |
|
157 |
+
| 0.1013 | 88.0 | 286 | 0.5930 | 0.8028 |
|
158 |
+
| 0.1013 | 88.9231 | 289 | 0.6020 | 0.7887 |
|
159 |
+
| 0.1092 | 89.8462 | 292 | 0.6055 | 0.7746 |
|
160 |
+
| 0.1092 | 90.7692 | 295 | 0.6075 | 0.7746 |
|
161 |
+
| 0.1092 | 92.0 | 299 | 0.6080 | 0.7746 |
|
162 |
+
| 0.1096 | 92.3077 | 300 | 0.6081 | 0.7746 |
|
163 |
+
|
164 |
+
|
165 |
+
### Framework versions
|
166 |
+
|
167 |
+
- Transformers 4.41.0
|
168 |
+
- Pytorch 2.3.0+cu121
|
169 |
+
- Datasets 2.19.1
|
170 |
+
- 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:d20bd5f5554146cebe3a82c35e72611bf35906b8da3aca31ae333e6e146de175
|
3 |
size 343230408
|
runs/May21_23-28-10_804716d6a90a/events.out.tfevents.1716334094.804716d6a90a.958.16
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 sha256:4d8775c0856733e70ebf90a2e9f85a8ab61c19ab1f97e16893ca5f3eea078ea6
|
3 |
+
size 41352
|