matthieulel
commited on
Commit
•
dc02205
1
Parent(s):
d34c883
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-finetuned-galaxy10-decals
|
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-finetuned-galaxy10-decals
|
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: 0.4357
|
21 |
+
- Accuracy: 0.8585
|
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: 20
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
55 |
+
| 1.318 | 0.9940 | 124 | 1.0409 | 0.6359 |
|
56 |
+
| 0.9268 | 1.9960 | 249 | 0.7164 | 0.7497 |
|
57 |
+
| 0.8221 | 2.9980 | 374 | 0.6210 | 0.7875 |
|
58 |
+
| 0.7276 | 4.0 | 499 | 0.5564 | 0.8162 |
|
59 |
+
| 0.6425 | 4.9940 | 623 | 0.5226 | 0.8162 |
|
60 |
+
| 0.6518 | 5.9960 | 748 | 0.5377 | 0.8185 |
|
61 |
+
| 0.6096 | 6.9980 | 873 | 0.5341 | 0.8219 |
|
62 |
+
| 0.6282 | 8.0 | 998 | 0.4718 | 0.8399 |
|
63 |
+
| 0.5394 | 8.9940 | 1122 | 0.5113 | 0.8281 |
|
64 |
+
| 0.5718 | 9.9960 | 1247 | 0.5019 | 0.8292 |
|
65 |
+
| 0.5507 | 10.9980 | 1372 | 0.4545 | 0.8461 |
|
66 |
+
| 0.4921 | 12.0 | 1497 | 0.4613 | 0.8416 |
|
67 |
+
| 0.5571 | 12.9940 | 1621 | 0.4587 | 0.8416 |
|
68 |
+
| 0.512 | 13.9960 | 1746 | 0.4673 | 0.8512 |
|
69 |
+
| 0.4855 | 14.9980 | 1871 | 0.4641 | 0.8489 |
|
70 |
+
| 0.4895 | 16.0 | 1996 | 0.4556 | 0.8450 |
|
71 |
+
| 0.4809 | 16.9940 | 2120 | 0.4317 | 0.8523 |
|
72 |
+
| 0.4785 | 17.9960 | 2245 | 0.4338 | 0.8534 |
|
73 |
+
| 0.444 | 18.9980 | 2370 | 0.4357 | 0.8579 |
|
74 |
+
| 0.4255 | 19.8798 | 2480 | 0.4357 | 0.8585 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.40.1
|
80 |
+
- Pytorch 1.12.1+cu116
|
81 |
+
- Datasets 2.19.0
|
82 |
+
- Tokenizers 0.19.1
|