update model card README.md
Browse files
README.md
CHANGED
@@ -13,8 +13,8 @@ model-index:
|
|
13 |
name: Image Classification
|
14 |
type: image-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
-
type:
|
18 |
config: default
|
19 |
split: train
|
20 |
args: default
|
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# vit-base-blur
|
31 |
|
32 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
- Accuracy: 1.0
|
36 |
|
37 |
## Model description
|
@@ -51,22 +51,29 @@ More information needed
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
-
- learning_rate: 0.
|
55 |
- train_batch_size: 16
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
-
- num_epochs:
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
|
|
13 |
name: Image Classification
|
14 |
type: image-classification
|
15 |
dataset:
|
16 |
+
name: imagefolder
|
17 |
+
type: imagefolder
|
18 |
config: default
|
19 |
split: train
|
20 |
args: default
|
|
|
29 |
|
30 |
# vit-base-blur
|
31 |
|
32 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.0008
|
35 |
- Accuracy: 1.0
|
36 |
|
37 |
## Model description
|
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0001
|
55 |
- train_batch_size: 16
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 12
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.0082 | 1.02 | 100 | 0.0107 | 1.0 |
|
67 |
+
| 0.0079 | 2.04 | 200 | 0.0052 | 1.0 |
|
68 |
+
| 0.0029 | 3.06 | 300 | 0.0028 | 1.0 |
|
69 |
+
| 0.002 | 4.08 | 400 | 0.0020 | 1.0 |
|
70 |
+
| 0.0016 | 5.1 | 500 | 0.0015 | 1.0 |
|
71 |
+
| 0.0013 | 6.12 | 600 | 0.0013 | 1.0 |
|
72 |
+
| 0.0011 | 7.14 | 700 | 0.0011 | 1.0 |
|
73 |
+
| 0.001 | 8.16 | 800 | 0.0010 | 1.0 |
|
74 |
+
| 0.0009 | 9.18 | 900 | 0.0009 | 1.0 |
|
75 |
+
| 0.0008 | 10.2 | 1000 | 0.0008 | 1.0 |
|
76 |
+
| 0.0008 | 11.22 | 1100 | 0.0008 | 1.0 |
|
77 |
|
78 |
|
79 |
### Framework versions
|