Pittawat Taveekitworachai
commited on
Commit
•
e7922dc
1
Parent(s):
50ecc4b
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
- image-classification
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: vit-base-letter
|
| 8 |
results: []
|
|
@@ -13,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# vit-base-letter
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -33,14 +37,52 @@ More information needed
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 0.0002
|
| 36 |
-
- train_batch_size:
|
| 37 |
-
- eval_batch_size:
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- num_epochs: 4
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.26.1
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: vit-base-letter
|
| 9 |
results: []
|
|
|
|
| 14 |
|
| 15 |
# vit-base-letter
|
| 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: 0.0559
|
| 20 |
+
- Accuracy: 0.9865
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0002
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- num_epochs: 4
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.5539 | 0.12 | 100 | 0.5576 | 0.9308 |
|
| 53 |
+
| 0.2688 | 0.25 | 200 | 0.2371 | 0.9665 |
|
| 54 |
+
| 0.1568 | 0.37 | 300 | 0.1829 | 0.9688 |
|
| 55 |
+
| 0.1684 | 0.49 | 400 | 0.1611 | 0.9662 |
|
| 56 |
+
| 0.1584 | 0.62 | 500 | 0.1340 | 0.9673 |
|
| 57 |
+
| 0.1569 | 0.74 | 600 | 0.1933 | 0.9531 |
|
| 58 |
+
| 0.0992 | 0.86 | 700 | 0.1031 | 0.9781 |
|
| 59 |
+
| 0.0573 | 0.98 | 800 | 0.1024 | 0.9781 |
|
| 60 |
+
| 0.0359 | 1.11 | 900 | 0.0950 | 0.9804 |
|
| 61 |
+
| 0.0961 | 1.23 | 1000 | 0.1200 | 0.9723 |
|
| 62 |
+
| 0.0334 | 1.35 | 1100 | 0.0995 | 0.975 |
|
| 63 |
+
| 0.0855 | 1.48 | 1200 | 0.0791 | 0.9815 |
|
| 64 |
+
| 0.0902 | 1.6 | 1300 | 0.0981 | 0.9765 |
|
| 65 |
+
| 0.0583 | 1.72 | 1400 | 0.1192 | 0.9712 |
|
| 66 |
+
| 0.0683 | 1.85 | 1500 | 0.0692 | 0.9846 |
|
| 67 |
+
| 0.1188 | 1.97 | 1600 | 0.0931 | 0.9785 |
|
| 68 |
+
| 0.0366 | 2.09 | 1700 | 0.0919 | 0.9804 |
|
| 69 |
+
| 0.0276 | 2.21 | 1800 | 0.0667 | 0.9846 |
|
| 70 |
+
| 0.0309 | 2.34 | 1900 | 0.0599 | 0.9858 |
|
| 71 |
+
| 0.0183 | 2.46 | 2000 | 0.0892 | 0.9769 |
|
| 72 |
+
| 0.0431 | 2.58 | 2100 | 0.0663 | 0.985 |
|
| 73 |
+
| 0.0424 | 2.71 | 2200 | 0.0643 | 0.9862 |
|
| 74 |
+
| 0.0453 | 2.83 | 2300 | 0.0646 | 0.9862 |
|
| 75 |
+
| 0.0528 | 2.95 | 2400 | 0.0550 | 0.985 |
|
| 76 |
+
| 0.0045 | 3.08 | 2500 | 0.0579 | 0.9846 |
|
| 77 |
+
| 0.007 | 3.2 | 2600 | 0.0517 | 0.9885 |
|
| 78 |
+
| 0.0048 | 3.32 | 2700 | 0.0584 | 0.9865 |
|
| 79 |
+
| 0.019 | 3.44 | 2800 | 0.0560 | 0.9873 |
|
| 80 |
+
| 0.0038 | 3.57 | 2900 | 0.0515 | 0.9881 |
|
| 81 |
+
| 0.0219 | 3.69 | 3000 | 0.0527 | 0.9881 |
|
| 82 |
+
| 0.0117 | 3.81 | 3100 | 0.0523 | 0.9888 |
|
| 83 |
+
| 0.0035 | 3.94 | 3200 | 0.0559 | 0.9865 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
### Framework versions
|
| 87 |
|
| 88 |
- Transformers 4.26.1
|