Euron Zhang
commited on
Commit
·
b002923
1
Parent(s):
6631475
update model card README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
-
value: 0.
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the food101 dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss: 0.
|
| 35 |
-
- Accuracy: 0.
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
@@ -60,15 +60,22 @@ The following hyperparameters were used during training:
|
|
| 60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
- lr_scheduler_type: linear
|
| 62 |
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
-
- num_epochs:
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
-
| Training Loss | Epoch | Step
|
| 68 |
-
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
+
value: 0.9220198019801981
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the food101 dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.4401
|
| 35 |
+
- Accuracy: 0.9220
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
- lr_scheduler_type: linear
|
| 62 |
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
+
- num_epochs: 10
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 69 |
+
| 0.0579 | 1.0 | 1183 | 0.4190 | 0.9102 |
|
| 70 |
+
| 0.0129 | 2.0 | 2366 | 0.4179 | 0.9155 |
|
| 71 |
+
| 0.0076 | 3.0 | 3549 | 0.4219 | 0.9198 |
|
| 72 |
+
| 0.0197 | 4.0 | 4732 | 0.4487 | 0.9160 |
|
| 73 |
+
| 0.0104 | 5.0 | 5915 | 0.4414 | 0.9210 |
|
| 74 |
+
| 0.0007 | 6.0 | 7098 | 0.4401 | 0.9220 |
|
| 75 |
+
| 0.0021 | 7.0 | 8281 | 0.4401 | 0.9220 |
|
| 76 |
+
| 0.0015 | 8.0 | 9464 | 0.4401 | 0.9220 |
|
| 77 |
+
| 0.0056 | 9.0 | 10647 | 0.4401 | 0.9220 |
|
| 78 |
+
| 0.0019 | 10.0 | 11830 | 0.4401 | 0.9220 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|