Model save
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,67 +61,27 @@ The following hyperparameters were used during training:
|
|
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:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
| 2.
|
71 |
-
| 1.
|
72 |
-
|
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.3479 | 10.96 | 200 | 0.5310 | 0.8263 |
|
81 |
-
| 0.329 | 12.0 | 219 | 0.5439 | 0.8494 |
|
82 |
-
| 0.3376 | 12.99 | 237 | 0.5050 | 0.8494 |
|
83 |
-
| 0.2804 | 13.97 | 255 | 0.5709 | 0.8263 |
|
84 |
-
| 0.2941 | 14.96 | 273 | 0.6376 | 0.8147 |
|
85 |
-
| 0.3026 | 16.0 | 292 | 0.5447 | 0.8494 |
|
86 |
-
| 0.2578 | 16.99 | 310 | 0.5056 | 0.8803 |
|
87 |
-
| 0.219 | 17.97 | 328 | 0.5620 | 0.8610 |
|
88 |
-
| 0.2403 | 18.96 | 346 | 0.5582 | 0.8456 |
|
89 |
-
| 0.2258 | 20.0 | 365 | 0.5458 | 0.8494 |
|
90 |
-
| 0.2265 | 20.99 | 383 | 0.5411 | 0.8533 |
|
91 |
-
| 0.1893 | 21.97 | 401 | 0.5477 | 0.8494 |
|
92 |
-
| 0.1896 | 22.96 | 419 | 0.5125 | 0.8494 |
|
93 |
-
| 0.1976 | 24.0 | 438 | 0.5672 | 0.8340 |
|
94 |
-
| 0.1725 | 24.99 | 456 | 0.5581 | 0.8456 |
|
95 |
-
| 0.168 | 25.97 | 474 | 0.5965 | 0.8456 |
|
96 |
-
| 0.1821 | 26.96 | 492 | 0.5567 | 0.8610 |
|
97 |
-
| 0.1805 | 28.0 | 511 | 0.5998 | 0.8533 |
|
98 |
-
| 0.1616 | 28.99 | 529 | 0.5451 | 0.8533 |
|
99 |
-
| 0.1467 | 29.97 | 547 | 0.5574 | 0.8494 |
|
100 |
-
| 0.1439 | 30.96 | 565 | 0.5707 | 0.8571 |
|
101 |
-
| 0.13 | 32.0 | 584 | 0.6019 | 0.8378 |
|
102 |
-
| 0.1353 | 32.99 | 602 | 0.5952 | 0.8610 |
|
103 |
-
| 0.1329 | 33.97 | 620 | 0.6262 | 0.8378 |
|
104 |
-
| 0.1258 | 34.96 | 638 | 0.6314 | 0.8456 |
|
105 |
-
| 0.1408 | 36.0 | 657 | 0.5761 | 0.8494 |
|
106 |
-
| 0.1197 | 36.99 | 675 | 0.5703 | 0.8610 |
|
107 |
-
| 0.1208 | 37.97 | 693 | 0.6247 | 0.8456 |
|
108 |
-
| 0.1197 | 38.96 | 711 | 0.6026 | 0.8533 |
|
109 |
-
| 0.1271 | 40.0 | 730 | 0.5953 | 0.8533 |
|
110 |
-
| 0.1053 | 40.99 | 748 | 0.6070 | 0.8533 |
|
111 |
-
| 0.0846 | 41.97 | 766 | 0.6094 | 0.8610 |
|
112 |
-
| 0.1206 | 42.96 | 784 | 0.5912 | 0.8494 |
|
113 |
-
| 0.1225 | 44.0 | 803 | 0.6074 | 0.8494 |
|
114 |
-
| 0.1184 | 44.99 | 821 | 0.5943 | 0.8494 |
|
115 |
-
| 0.1027 | 45.97 | 839 | 0.6084 | 0.8494 |
|
116 |
-
| 0.1113 | 46.96 | 857 | 0.6034 | 0.8533 |
|
117 |
-
| 0.0945 | 48.0 | 876 | 0.6106 | 0.8494 |
|
118 |
-
| 0.1159 | 48.99 | 894 | 0.6143 | 0.8533 |
|
119 |
-
| 0.0963 | 49.32 | 900 | 0.6144 | 0.8533 |
|
120 |
|
121 |
|
122 |
### Framework versions
|
123 |
|
124 |
-
- Transformers 4.
|
125 |
- Pytorch 2.1.0+cu121
|
126 |
- Datasets 2.17.1
|
127 |
- Tokenizers 0.15.2
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8571428571428571
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4634
|
36 |
+
- Accuracy: 0.8571
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
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: 10
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 2.0639 | 0.99 | 18 | 1.1575 | 0.6873 |
|
71 |
+
| 1.0962 | 1.97 | 36 | 0.8400 | 0.7336 |
|
72 |
+
| 0.8715 | 2.96 | 54 | 0.7163 | 0.7915 |
|
73 |
+
| 0.7241 | 4.0 | 73 | 0.6331 | 0.7992 |
|
74 |
+
| 0.6171 | 4.99 | 91 | 0.5140 | 0.8340 |
|
75 |
+
| 0.5467 | 5.97 | 109 | 0.4848 | 0.8610 |
|
76 |
+
| 0.518 | 6.96 | 127 | 0.4585 | 0.8456 |
|
77 |
+
| 0.4543 | 8.0 | 146 | 0.4549 | 0.8726 |
|
78 |
+
| 0.4378 | 8.99 | 164 | 0.4448 | 0.8571 |
|
79 |
+
| 0.431 | 9.86 | 180 | 0.4634 | 0.8571 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
83 |
|
84 |
+
- Transformers 4.38.1
|
85 |
- Pytorch 2.1.0+cu121
|
86 |
- Datasets 2.17.1
|
87 |
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110367448
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52712d8005b1ec7e23bbe740f3cb25d826aff2e1debf56131c7ce28832e28b9a
|
3 |
size 110367448
|
runs/Mar01_04-04-16_a2ca3ccf826b/events.out.tfevents.1709266087.a2ca3ccf826b.460.0
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 sha256:7dc98c54360879ce216176228e76e09ce1f8e40862362ad51b9b426358f0c9c4
|
3 |
+
size 12715
|