update model card README.md
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 |
|
|
@@ -56,19 +56,67 @@ The following hyperparameters were used during training:
|
|
| 56 |
- train_batch_size: 64
|
| 57 |
- eval_batch_size: 64
|
| 58 |
- seed: 42
|
| 59 |
-
- gradient_accumulation_steps:
|
| 60 |
-
- total_train_batch_size:
|
| 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 | 0
|
| 71 |
-
| No log | 2.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 1.0
|
| 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: 0.0000
|
| 36 |
+
- Accuracy: 1.0
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 56 |
- train_batch_size: 64
|
| 57 |
- eval_batch_size: 64
|
| 58 |
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 2
|
| 60 |
+
- total_train_batch_size: 128
|
| 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: 50
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 3 | 0.6245 | 0.7778 |
|
| 71 |
+
| No log | 2.0 | 6 | 0.5321 | 0.7778 |
|
| 72 |
+
| No log | 3.0 | 9 | 0.5123 | 0.7778 |
|
| 73 |
+
| 0.6482 | 4.0 | 12 | 0.4956 | 0.7778 |
|
| 74 |
+
| 0.6482 | 5.0 | 15 | 0.4585 | 0.7778 |
|
| 75 |
+
| 0.6482 | 6.0 | 18 | 0.3743 | 0.8611 |
|
| 76 |
+
| 0.5574 | 7.0 | 21 | 0.2842 | 0.9167 |
|
| 77 |
+
| 0.5574 | 8.0 | 24 | 0.2125 | 0.9167 |
|
| 78 |
+
| 0.5574 | 9.0 | 27 | 0.2683 | 0.9167 |
|
| 79 |
+
| 0.4882 | 10.0 | 30 | 0.1316 | 0.9444 |
|
| 80 |
+
| 0.4882 | 11.0 | 33 | 0.1366 | 0.9444 |
|
| 81 |
+
| 0.4882 | 12.0 | 36 | 0.0745 | 0.9722 |
|
| 82 |
+
| 0.4882 | 13.0 | 39 | 0.1065 | 0.9444 |
|
| 83 |
+
| 0.0907 | 14.0 | 42 | 0.0477 | 0.9722 |
|
| 84 |
+
| 0.0907 | 15.0 | 45 | 0.0460 | 0.9444 |
|
| 85 |
+
| 0.0907 | 16.0 | 48 | 0.0438 | 0.9722 |
|
| 86 |
+
| 0.0481 | 17.0 | 51 | 0.0203 | 1.0 |
|
| 87 |
+
| 0.0481 | 18.0 | 54 | 0.0093 | 1.0 |
|
| 88 |
+
| 0.0481 | 19.0 | 57 | 0.0082 | 1.0 |
|
| 89 |
+
| 0.013 | 20.0 | 60 | 0.0017 | 1.0 |
|
| 90 |
+
| 0.013 | 21.0 | 63 | 0.0008 | 1.0 |
|
| 91 |
+
| 0.013 | 22.0 | 66 | 0.0002 | 1.0 |
|
| 92 |
+
| 0.013 | 23.0 | 69 | 0.0001 | 1.0 |
|
| 93 |
+
| 0.0101 | 24.0 | 72 | 0.0938 | 0.9722 |
|
| 94 |
+
| 0.0101 | 25.0 | 75 | 0.1019 | 0.9722 |
|
| 95 |
+
| 0.0101 | 26.0 | 78 | 0.0005 | 1.0 |
|
| 96 |
+
| 0.0085 | 27.0 | 81 | 0.0000 | 1.0 |
|
| 97 |
+
| 0.0085 | 28.0 | 84 | 0.0000 | 1.0 |
|
| 98 |
+
| 0.0085 | 29.0 | 87 | 0.0001 | 1.0 |
|
| 99 |
+
| 0.0196 | 30.0 | 90 | 0.0001 | 1.0 |
|
| 100 |
+
| 0.0196 | 31.0 | 93 | 0.0001 | 1.0 |
|
| 101 |
+
| 0.0196 | 32.0 | 96 | 0.0000 | 1.0 |
|
| 102 |
+
| 0.0196 | 33.0 | 99 | 0.0000 | 1.0 |
|
| 103 |
+
| 0.0027 | 34.0 | 102 | 0.0000 | 1.0 |
|
| 104 |
+
| 0.0027 | 35.0 | 105 | 0.0000 | 1.0 |
|
| 105 |
+
| 0.0027 | 36.0 | 108 | 0.0000 | 1.0 |
|
| 106 |
+
| 0.0016 | 37.0 | 111 | 0.0000 | 1.0 |
|
| 107 |
+
| 0.0016 | 38.0 | 114 | 0.0000 | 1.0 |
|
| 108 |
+
| 0.0016 | 39.0 | 117 | 0.0000 | 1.0 |
|
| 109 |
+
| 0.0021 | 40.0 | 120 | 0.0000 | 1.0 |
|
| 110 |
+
| 0.0021 | 41.0 | 123 | 0.0000 | 1.0 |
|
| 111 |
+
| 0.0021 | 42.0 | 126 | 0.0000 | 1.0 |
|
| 112 |
+
| 0.0021 | 43.0 | 129 | 0.0000 | 1.0 |
|
| 113 |
+
| 0.0024 | 44.0 | 132 | 0.0000 | 1.0 |
|
| 114 |
+
| 0.0024 | 45.0 | 135 | 0.0000 | 1.0 |
|
| 115 |
+
| 0.0024 | 46.0 | 138 | 0.0000 | 1.0 |
|
| 116 |
+
| 0.0009 | 47.0 | 141 | 0.0000 | 1.0 |
|
| 117 |
+
| 0.0009 | 48.0 | 144 | 0.0000 | 1.0 |
|
| 118 |
+
| 0.0009 | 49.0 | 147 | 0.0000 | 1.0 |
|
| 119 |
+
| 0.0006 | 50.0 | 150 | 0.0000 | 1.0 |
|
| 120 |
|
| 121 |
|
| 122 |
### Framework versions
|