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 +61,22 @@ 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 |
-
|
|
71 |
-
| 1.
|
72 |
-
|
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.6852 | 5.97 | 109 | 0.5354 | 0.8456 |
|
76 |
-
| 0.5344 | 6.96 | 127 | 0.4872 | 0.8456 |
|
77 |
-
| 0.5354 | 8.0 | 146 | 0.3524 | 0.8958 |
|
78 |
-
| 0.4576 | 8.99 | 164 | 0.3925 | 0.8687 |
|
79 |
-
| 0.426 | 9.97 | 182 | 0.3159 | 0.9112 |
|
80 |
-
| 0.4059 | 10.96 | 200 | 0.4182 | 0.8610 |
|
81 |
-
| 0.3733 | 12.0 | 219 | 0.3867 | 0.8803 |
|
82 |
-
| 0.4006 | 12.99 | 237 | 0.3451 | 0.9035 |
|
83 |
-
| 0.3237 | 13.97 | 255 | 0.3464 | 0.9112 |
|
84 |
-
| 0.338 | 14.96 | 273 | 0.3715 | 0.8958 |
|
85 |
-
| 0.3055 | 16.0 | 292 | 0.3270 | 0.9073 |
|
86 |
-
| 0.3029 | 16.99 | 310 | 0.3527 | 0.9112 |
|
87 |
-
| 0.3032 | 17.97 | 328 | 0.3871 | 0.8842 |
|
88 |
-
| 0.2734 | 18.96 | 346 | 0.3783 | 0.9035 |
|
89 |
-
| 0.2641 | 20.0 | 365 | 0.3802 | 0.9073 |
|
90 |
-
| 0.2433 | 20.99 | 383 | 0.3474 | 0.8958 |
|
91 |
-
| 0.2338 | 21.97 | 401 | 0.3848 | 0.9035 |
|
92 |
-
| 0.2078 | 22.96 | 419 | 0.3941 | 0.8958 |
|
93 |
-
| 0.2299 | 24.0 | 438 | 0.3334 | 0.9189 |
|
94 |
-
| 0.2119 | 24.99 | 456 | 0.3391 | 0.9228 |
|
95 |
-
| 0.2125 | 25.97 | 474 | 0.3499 | 0.9228 |
|
96 |
-
| 0.2249 | 26.96 | 492 | 0.3287 | 0.9151 |
|
97 |
-
| 0.2011 | 28.0 | 511 | 0.3669 | 0.9035 |
|
98 |
-
| 0.1524 | 28.99 | 529 | 0.3521 | 0.9035 |
|
99 |
-
| 0.1624 | 29.97 | 547 | 0.3955 | 0.8958 |
|
100 |
-
| 0.1536 | 30.96 | 565 | 0.3757 | 0.9073 |
|
101 |
-
| 0.1526 | 32.0 | 584 | 0.3765 | 0.8996 |
|
102 |
-
| 0.1692 | 32.99 | 602 | 0.3417 | 0.9112 |
|
103 |
-
| 0.1561 | 33.97 | 620 | 0.3430 | 0.9228 |
|
104 |
-
| 0.1314 | 34.96 | 638 | 0.3381 | 0.9266 |
|
105 |
-
| 0.1613 | 36.0 | 657 | 0.3425 | 0.9151 |
|
106 |
-
| 0.1268 | 36.99 | 675 | 0.3434 | 0.9228 |
|
107 |
-
| 0.1263 | 37.97 | 693 | 0.3665 | 0.9035 |
|
108 |
-
| 0.096 | 38.96 | 711 | 0.3864 | 0.9189 |
|
109 |
-
| 0.1375 | 40.0 | 730 | 0.3802 | 0.9266 |
|
110 |
-
| 0.1279 | 40.99 | 748 | 0.3584 | 0.9266 |
|
111 |
-
| 0.1153 | 41.97 | 766 | 0.3745 | 0.9189 |
|
112 |
-
| 0.1343 | 42.96 | 784 | 0.3877 | 0.9189 |
|
113 |
-
| 0.1272 | 44.0 | 803 | 0.3729 | 0.9228 |
|
114 |
-
| 0.1238 | 44.99 | 821 | 0.3904 | 0.9228 |
|
115 |
-
| 0.1184 | 45.97 | 839 | 0.3819 | 0.9151 |
|
116 |
-
| 0.0927 | 46.96 | 857 | 0.3756 | 0.9228 |
|
117 |
-
| 0.1221 | 48.0 | 876 | 0.3798 | 0.9228 |
|
118 |
-
| 0.1116 | 48.99 | 894 | 0.3790 | 0.9228 |
|
119 |
-
| 0.0939 | 49.32 | 900 | 0.3788 | 0.9228 |
|
120 |
|
121 |
|
122 |
### Framework versions
|
123 |
|
124 |
- Transformers 4.38.1
|
125 |
- Pytorch 2.1.0+cu121
|
126 |
-
- Datasets 2.
|
127 |
- Tokenizers 0.15.2
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8108108108108109
|
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: 0.6244
|
36 |
+
- Accuracy: 0.8108
|
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: 5
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.8838 | 0.99 | 18 | 1.2972 | 0.6371 |
|
71 |
+
| 1.0537 | 1.97 | 36 | 0.8605 | 0.7336 |
|
72 |
+
| 0.7996 | 2.96 | 54 | 0.7460 | 0.7645 |
|
73 |
+
| 0.7009 | 4.0 | 73 | 0.6442 | 0.7992 |
|
74 |
+
| 0.6115 | 4.93 | 90 | 0.6244 | 0.8108 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
|
77 |
### Framework versions
|
78 |
|
79 |
- Transformers 4.38.1
|
80 |
- Pytorch 2.1.0+cu121
|
81 |
+
- Datasets 2.18.0
|
82 |
- 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 sha256:70bdce06d68ecc62487ed76abeb00d8f820c449f8913306e1180571b4fd77ca2
|
3 |
size 110367448
|
runs/Mar02_06-42-13_601745c6f59f/events.out.tfevents.1709361746.601745c6f59f.171.0
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 sha256:21cce2453838ea20d5c6f11840dff9bbf2d409becbeab769fc8512f22d0424cf
|
3 |
+
size 9218
|