diegopetrola
commited on
Commit
•
4119fad
1
Parent(s):
c1a8bf3
update model card README.md
Browse files
README.md
CHANGED
@@ -16,8 +16,8 @@ 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 None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Accuracy: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,23 +36,27 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 0.
|
40 |
- train_batch_size: 64
|
41 |
- eval_batch_size: 64
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
-
- lr_scheduler_type:
|
45 |
-
-
|
46 |
-
-
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
| No log | 1.0 |
|
53 |
-
| No log | 2.0 |
|
54 |
-
| No log | 3.0 |
|
55 |
-
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### 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 None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.5538
|
20 |
+
- Accuracy: 0.7616
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0003
|
40 |
- train_batch_size: 64
|
41 |
- eval_batch_size: 64
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: cosine
|
45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
46 |
+
- num_epochs: 8
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 10 | 0.5944 | 0.7483 |
|
53 |
+
| No log | 2.0 | 20 | 0.5640 | 0.7483 |
|
54 |
+
| No log | 3.0 | 30 | 0.5582 | 0.7483 |
|
55 |
+
| No log | 4.0 | 40 | 0.5585 | 0.7483 |
|
56 |
+
| No log | 5.0 | 50 | 0.5598 | 0.7483 |
|
57 |
+
| No log | 6.0 | 60 | 0.5484 | 0.7483 |
|
58 |
+
| No log | 7.0 | 70 | 0.5524 | 0.7417 |
|
59 |
+
| No log | 8.0 | 80 | 0.5538 | 0.7616 |
|
60 |
|
61 |
|
62 |
### Framework versions
|