Commit
•
f036c7b
1
Parent(s):
a0ce1cf
update model card README.md
Browse files
README.md
CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Accuracy: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,15 +45,22 @@ 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
|
53 |
-
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0279
|
20 |
+
- Accuracy: 0.9928
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
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: 10
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
54 |
+
| 0.1943 | 1.0 | 1406 | 0.0682 | 0.9757 |
|
55 |
+
| 0.1288 | 2.0 | 2812 | 0.0423 | 0.9852 |
|
56 |
+
| 0.0952 | 3.0 | 4218 | 0.0393 | 0.9866 |
|
57 |
+
| 0.0743 | 4.0 | 5625 | 0.0410 | 0.9866 |
|
58 |
+
| 0.0587 | 5.0 | 7031 | 0.0332 | 0.9889 |
|
59 |
+
| 0.0493 | 6.0 | 8437 | 0.0253 | 0.9919 |
|
60 |
+
| 0.06 | 7.0 | 9843 | 0.0279 | 0.9922 |
|
61 |
+
| 0.0738 | 8.0 | 11250 | 0.0326 | 0.9907 |
|
62 |
+
| 0.065 | 9.0 | 12656 | 0.0278 | 0.9931 |
|
63 |
+
| 0.045 | 10.0 | 14060 | 0.0279 | 0.9928 |
|
64 |
|
65 |
|
66 |
### Framework versions
|