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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,24 +41,22 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.1553 | 8.4 | 1000 | 0.2809 |
|
61 |
-
| 0.1519 | 9.24 | 1100 | 0.2830 |
|
62 |
|
63 |
|
64 |
### 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 the imagefolder dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.2867
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 8
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 0.3751 | 0.84 | 100 | 0.3845 |
|
52 |
+
| 0.3237 | 1.68 | 200 | 0.3215 |
|
53 |
+
| 0.2812 | 2.52 | 300 | 0.3092 |
|
54 |
+
| 0.2441 | 3.36 | 400 | 0.2960 |
|
55 |
+
| 0.2268 | 4.2 | 500 | 0.2884 |
|
56 |
+
| 0.2236 | 5.04 | 600 | 0.2873 |
|
57 |
+
| 0.2027 | 5.88 | 700 | 0.2859 |
|
58 |
+
| 0.2024 | 6.72 | 800 | 0.2877 |
|
59 |
+
| 0.1952 | 7.56 | 900 | 0.2867 |
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|