Commit
•
1fbd54a
1
Parent(s):
1ca3990
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
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 | Validation Loss | Accuracy |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.939
|
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3194
|
35 |
+
- Accuracy: 0.939
|
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 |
+
| 0.8638 | 0.99 | 62 | 0.9578 | 0.913 |
|
70 |
+
| 0.6163 | 2.0 | 125 | 0.7060 | 0.911 |
|
71 |
+
| 0.5103 | 2.99 | 187 | 0.4994 | 0.936 |
|
72 |
+
| 0.3659 | 4.0 | 250 | 0.4539 | 0.927 |
|
73 |
+
| 0.3207 | 4.99 | 312 | 0.3999 | 0.933 |
|
74 |
+
| 0.2523 | 6.0 | 375 | 0.3799 | 0.921 |
|
75 |
+
| 0.2257 | 6.99 | 437 | 0.3703 | 0.922 |
|
76 |
+
| 0.1937 | 8.0 | 500 | 0.3160 | 0.936 |
|
77 |
+
| 0.1854 | 8.99 | 562 | 0.3229 | 0.93 |
|
78 |
+
| 0.2048 | 9.92 | 620 | 0.3194 | 0.939 |
|
79 |
|
80 |
|
81 |
### Framework versions
|