Model save
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swin-base-patch4-window7-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: swin-base-patch4-window7-224-finetuned-lora-scenes
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# swin-base-patch4-window7-224-finetuned-lora-scenes
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0407
|
23 |
+
- Accuracy: 0.9853
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.005
|
43 |
+
- train_batch_size: 32
|
44 |
+
- eval_batch_size: 32
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 128
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 6
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
57 |
+
| 0.2038 | 0.97 | 27 | 0.0655 | 0.9763 |
|
58 |
+
| 0.1143 | 1.98 | 55 | 0.0557 | 0.9820 |
|
59 |
+
| 0.1224 | 2.99 | 83 | 0.0517 | 0.9763 |
|
60 |
+
| 0.0891 | 4.0 | 111 | 0.0439 | 0.9831 |
|
61 |
+
| 0.0696 | 4.97 | 138 | 0.0407 | 0.9853 |
|
62 |
+
| 0.0716 | 5.84 | 162 | 0.0436 | 0.9853 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.35.2
|
68 |
+
- Pytorch 2.1.0+cu118
|
69 |
+
- Datasets 2.15.0
|
70 |
+
- Tokenizers 0.15.0
|
runs/Dec06_20-19-14_03002615e15d/events.out.tfevents.1701893966.03002615e15d.5252.0
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 sha256:516a711b9049f1a9c62ef774b1054601900eea9a91d3760752feaf1394f79f55
|
3 |
+
size 9816
|
runs/Dec06_20-19-14_03002615e15d/events.out.tfevents.1701894862.03002615e15d.5252.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45008f7371776dfc83aa0deb5ce89ae65074aec07d37765d0d92adf48d23d275
|
3 |
+
size 411
|