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:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,15 +61,37 @@ 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 |
-
| No log | 1.0 | 1 | 1.
|
71 |
-
| No log | 2.0 | 2 | 1.
|
72 |
-
| No log | 3.0 | 3 | 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8333333333333334
|
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: 0.3933
|
36 |
+
- Accuracy: 0.8333
|
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: 25
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 1.0 | 1 | 1.8803 | 0.5 |
|
71 |
+
| No log | 2.0 | 2 | 1.8439 | 0.5 |
|
72 |
+
| No log | 3.0 | 3 | 1.7572 | 0.5 |
|
73 |
+
| No log | 4.0 | 4 | 1.6256 | 0.5 |
|
74 |
+
| No log | 5.0 | 5 | 1.5082 | 0.5 |
|
75 |
+
| No log | 6.0 | 6 | 1.4301 | 0.5 |
|
76 |
+
| No log | 7.0 | 7 | 1.3379 | 0.5 |
|
77 |
+
| No log | 8.0 | 8 | 1.2260 | 0.5 |
|
78 |
+
| No log | 9.0 | 9 | 1.1071 | 0.6667 |
|
79 |
+
| 0.6539 | 10.0 | 10 | 0.9941 | 0.6667 |
|
80 |
+
| 0.6539 | 11.0 | 11 | 0.8836 | 0.6667 |
|
81 |
+
| 0.6539 | 12.0 | 12 | 0.7859 | 0.6667 |
|
82 |
+
| 0.6539 | 13.0 | 13 | 0.7059 | 0.8333 |
|
83 |
+
| 0.6539 | 14.0 | 14 | 0.6358 | 0.8333 |
|
84 |
+
| 0.6539 | 15.0 | 15 | 0.5752 | 0.8333 |
|
85 |
+
| 0.6539 | 16.0 | 16 | 0.5343 | 0.8333 |
|
86 |
+
| 0.6539 | 17.0 | 17 | 0.4994 | 0.8333 |
|
87 |
+
| 0.6539 | 18.0 | 18 | 0.4755 | 0.8333 |
|
88 |
+
| 0.6539 | 19.0 | 19 | 0.4544 | 0.8333 |
|
89 |
+
| 0.2777 | 20.0 | 20 | 0.4328 | 0.8333 |
|
90 |
+
| 0.2777 | 21.0 | 21 | 0.4171 | 0.8333 |
|
91 |
+
| 0.2777 | 22.0 | 22 | 0.4066 | 0.8333 |
|
92 |
+
| 0.2777 | 23.0 | 23 | 0.3995 | 0.8333 |
|
93 |
+
| 0.2777 | 24.0 | 24 | 0.3954 | 0.8333 |
|
94 |
+
| 0.2777 | 25.0 | 25 | 0.3933 | 0.8333 |
|
95 |
|
96 |
|
97 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110358212
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bf5ae1b8c0b04690e4c827ceef8918761dfb091503fdb0c44d2c414110ca905
|
3 |
size 110358212
|
runs/May05_19-43-16_503a5f38d136/events.out.tfevents.1714938204.503a5f38d136.8635.2
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 sha256:54af827b28a9479c1717858bd2e3f687a76d7433de52ef9e7b877a4a07e64c9c
|
3 |
+
size 14110
|