Augusto777
commited on
Commit
•
29c7cf0
1
Parent(s):
bd77a0e
Model save
Browse files- README.md +99 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: swinv2-tiny-patch4-window8-256-dmae-va-U-40
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# swinv2-tiny-patch4-window8-256-dmae-va-U-40
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1077
|
21 |
+
- Accuracy: 0.9817
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 40
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| No log | 0.9 | 7 | 1.3839 | 0.3028 |
|
56 |
+
| 1.4343 | 1.94 | 15 | 1.3643 | 0.2844 |
|
57 |
+
| 1.3413 | 2.97 | 23 | 1.3310 | 0.3578 |
|
58 |
+
| 1.2473 | 4.0 | 31 | 1.1081 | 0.5138 |
|
59 |
+
| 1.2473 | 4.9 | 38 | 0.8292 | 0.7064 |
|
60 |
+
| 1.0532 | 5.94 | 46 | 0.7420 | 0.6239 |
|
61 |
+
| 0.917 | 6.97 | 54 | 0.6345 | 0.6972 |
|
62 |
+
| 0.7939 | 8.0 | 62 | 0.4898 | 0.8532 |
|
63 |
+
| 0.7939 | 8.9 | 69 | 0.5918 | 0.7523 |
|
64 |
+
| 0.7457 | 9.94 | 77 | 0.5271 | 0.7615 |
|
65 |
+
| 0.6834 | 10.97 | 85 | 0.3296 | 0.9450 |
|
66 |
+
| 0.5847 | 12.0 | 93 | 0.2883 | 0.9174 |
|
67 |
+
| 0.5199 | 12.9 | 100 | 0.2896 | 0.9266 |
|
68 |
+
| 0.5199 | 13.94 | 108 | 0.2859 | 0.8991 |
|
69 |
+
| 0.4657 | 14.97 | 116 | 0.2515 | 0.9083 |
|
70 |
+
| 0.4585 | 16.0 | 124 | 0.2261 | 0.9083 |
|
71 |
+
| 0.3892 | 16.9 | 131 | 0.2142 | 0.9266 |
|
72 |
+
| 0.3892 | 17.94 | 139 | 0.1788 | 0.9450 |
|
73 |
+
| 0.3939 | 18.97 | 147 | 0.1948 | 0.9266 |
|
74 |
+
| 0.3429 | 20.0 | 155 | 0.1685 | 0.9450 |
|
75 |
+
| 0.3493 | 20.9 | 162 | 0.1986 | 0.9083 |
|
76 |
+
| 0.3462 | 21.94 | 170 | 0.1540 | 0.9358 |
|
77 |
+
| 0.3462 | 22.97 | 178 | 0.1449 | 0.9450 |
|
78 |
+
| 0.3117 | 24.0 | 186 | 0.1379 | 0.9541 |
|
79 |
+
| 0.3109 | 24.9 | 193 | 0.1423 | 0.9450 |
|
80 |
+
| 0.2867 | 25.94 | 201 | 0.1451 | 0.9450 |
|
81 |
+
| 0.2867 | 26.97 | 209 | 0.1154 | 0.9725 |
|
82 |
+
| 0.293 | 28.0 | 217 | 0.1152 | 0.9541 |
|
83 |
+
| 0.2782 | 28.9 | 224 | 0.1261 | 0.9633 |
|
84 |
+
| 0.2744 | 29.94 | 232 | 0.1175 | 0.9817 |
|
85 |
+
| 0.2711 | 30.97 | 240 | 0.1292 | 0.9633 |
|
86 |
+
| 0.2711 | 32.0 | 248 | 0.1101 | 0.9817 |
|
87 |
+
| 0.2652 | 32.9 | 255 | 0.1202 | 0.9633 |
|
88 |
+
| 0.2218 | 33.94 | 263 | 0.1119 | 0.9817 |
|
89 |
+
| 0.2899 | 34.97 | 271 | 0.1071 | 0.9817 |
|
90 |
+
| 0.2899 | 36.0 | 279 | 0.1077 | 0.9817 |
|
91 |
+
| 0.2143 | 36.13 | 280 | 0.1077 | 0.9817 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.35.2
|
97 |
+
- Pytorch 2.1.0+cu121
|
98 |
+
- Datasets 2.16.1
|
99 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110356296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:980e224b008d0d8bffa7bbf2f157b355831f5ffa947c5e650db13dc4b163dff0
|
3 |
size 110356296
|