Commit
·
b020b4e
1
Parent(s):
bfd34dd
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
- image-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# vit-base-clothing-leafs-example-full-simple
|
| 17 |
|
| 18 |
-
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
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -37,7 +36,7 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate: 5e-05
|
| 41 |
- train_batch_size: 32
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
|
@@ -50,34 +49,34 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
|
|
|
| 14 |
|
| 15 |
# vit-base-clothing-leafs-example-full-simple
|
| 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 None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0593
|
| 20 |
+
- Accuracy: 0.7100
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 7.5e-05
|
| 40 |
- train_batch_size: 32
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 1.6085 | 0.14 | 1000 | 1.2965 | 0.6414 |
|
| 53 |
+
| 1.2071 | 0.28 | 2000 | 1.1638 | 0.6690 |
|
| 54 |
+
| 1.1467 | 0.41 | 3000 | 1.1357 | 0.6722 |
|
| 55 |
+
| 1.1073 | 0.55 | 4000 | 1.0940 | 0.6833 |
|
| 56 |
+
| 1.0721 | 0.69 | 5000 | 1.0802 | 0.6859 |
|
| 57 |
+
| 1.0607 | 0.83 | 6000 | 1.0509 | 0.6947 |
|
| 58 |
+
| 1.032 | 0.97 | 7000 | 1.0557 | 0.6915 |
|
| 59 |
+
| 0.9224 | 1.11 | 8000 | 1.0506 | 0.6966 |
|
| 60 |
+
| 0.9029 | 1.24 | 9000 | 1.0421 | 0.6952 |
|
| 61 |
+
| 0.8858 | 1.38 | 10000 | 1.0204 | 0.7019 |
|
| 62 |
+
| 0.8943 | 1.52 | 11000 | 1.0182 | 0.7038 |
|
| 63 |
+
| 0.8756 | 1.66 | 12000 | 1.0011 | 0.7108 |
|
| 64 |
+
| 0.8657 | 1.8 | 13000 | 1.0035 | 0.7074 |
|
| 65 |
+
| 0.8737 | 1.94 | 14000 | 0.9963 | 0.7102 |
|
| 66 |
+
| 0.7893 | 2.07 | 15000 | 1.0208 | 0.7089 |
|
| 67 |
+
| 0.7067 | 2.21 | 16000 | 1.0219 | 0.7076 |
|
| 68 |
+
| 0.7072 | 2.35 | 17000 | 1.0181 | 0.7096 |
|
| 69 |
+
| 0.6914 | 2.49 | 18000 | 1.0165 | 0.7123 |
|
| 70 |
+
| 0.7044 | 2.63 | 19000 | 1.0173 | 0.7124 |
|
| 71 |
+
| 0.7014 | 2.77 | 20000 | 1.0056 | 0.7145 |
|
| 72 |
+
| 0.6997 | 2.9 | 21000 | 1.0049 | 0.7116 |
|
| 73 |
+
| 0.6378 | 3.04 | 22000 | 1.0353 | 0.7105 |
|
| 74 |
+
| 0.5446 | 3.18 | 23000 | 1.0574 | 0.7086 |
|
| 75 |
+
| 0.5307 | 3.32 | 24000 | 1.0585 | 0.7079 |
|
| 76 |
+
| 0.5269 | 3.46 | 25000 | 1.0661 | 0.7094 |
|
| 77 |
+
| 0.525 | 3.6 | 26000 | 1.0599 | 0.7104 |
|
| 78 |
+
| 0.516 | 3.73 | 27000 | 1.0658 | 0.7111 |
|
| 79 |
+
| 0.5224 | 3.87 | 28000 | 1.0593 | 0.7100 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|