update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
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 None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
- Accuracy: 1.0
|
| 21 |
|
| 22 |
## Model description
|
|
@@ -45,15 +45,42 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
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 None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0000
|
| 20 |
- Accuracy: 1.0
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 30
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| No log | 0.67 | 1 | 0.7112 | 0.5238 |
|
| 55 |
+
| No log | 1.67 | 2 | 0.5591 | 0.8571 |
|
| 56 |
+
| 0.811 | 2.67 | 3 | 0.3781 | 0.9524 |
|
| 57 |
+
| 0.811 | 3.67 | 4 | 0.1995 | 1.0 |
|
| 58 |
+
| 0.811 | 4.67 | 5 | 0.1215 | 1.0 |
|
| 59 |
+
| 0.3531 | 5.67 | 6 | 0.0578 | 1.0 |
|
| 60 |
+
| 0.3531 | 6.67 | 7 | 0.0195 | 1.0 |
|
| 61 |
+
| 0.3531 | 7.67 | 8 | 0.0072 | 1.0 |
|
| 62 |
+
| 0.0618 | 8.67 | 9 | 0.0030 | 1.0 |
|
| 63 |
+
| 0.0618 | 9.67 | 10 | 0.0012 | 1.0 |
|
| 64 |
+
| 0.0618 | 10.67 | 11 | 0.0005 | 1.0 |
|
| 65 |
+
| 0.0079 | 11.67 | 12 | 0.0003 | 1.0 |
|
| 66 |
+
| 0.0079 | 12.67 | 13 | 0.0001 | 1.0 |
|
| 67 |
+
| 0.0079 | 13.67 | 14 | 0.0001 | 1.0 |
|
| 68 |
+
| 0.0051 | 14.67 | 15 | 0.0001 | 1.0 |
|
| 69 |
+
| 0.0051 | 15.67 | 16 | 0.0000 | 1.0 |
|
| 70 |
+
| 0.0051 | 16.67 | 17 | 0.0000 | 1.0 |
|
| 71 |
+
| 0.0017 | 17.67 | 18 | 0.0000 | 1.0 |
|
| 72 |
+
| 0.0017 | 18.67 | 19 | 0.0000 | 1.0 |
|
| 73 |
+
| 0.0017 | 19.67 | 20 | 0.0000 | 1.0 |
|
| 74 |
+
| 0.0004 | 20.67 | 21 | 0.0000 | 1.0 |
|
| 75 |
+
| 0.0004 | 21.67 | 22 | 0.0000 | 1.0 |
|
| 76 |
+
| 0.0004 | 22.67 | 23 | 0.0000 | 1.0 |
|
| 77 |
+
| 0.0022 | 23.67 | 24 | 0.0000 | 1.0 |
|
| 78 |
+
| 0.0022 | 24.67 | 25 | 0.0000 | 1.0 |
|
| 79 |
+
| 0.0022 | 25.67 | 26 | 0.0000 | 1.0 |
|
| 80 |
+
| 0.001 | 26.67 | 27 | 0.0000 | 1.0 |
|
| 81 |
+
| 0.001 | 27.67 | 28 | 0.0000 | 1.0 |
|
| 82 |
+
| 0.001 | 28.67 | 29 | 0.0000 | 1.0 |
|
| 83 |
+
| 0.0013 | 29.67 | 30 | 0.0000 | 1.0 |
|
| 84 |
|
| 85 |
|
| 86 |
### Framework versions
|