End of training
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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 None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -46,23 +46,21 @@ The following hyperparameters were used during training:
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
-
| 1.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.2257 | 5.0 | 125 | 0.3576 | 0.8978 |
|
60 |
-
| 0.1179 | 6.0 | 150 | 0.2879 | 0.9152 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
-
- Transformers 4.
|
66 |
-
- Pytorch 2.2.
|
67 |
-
- Datasets 2.17.
|
68 |
- Tokenizers 0.15.2
|
|
|
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 None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4637
|
21 |
+
- Accuracy: 0.8753
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 4
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 1.2343 | 1.0 | 25 | 0.9184 | 0.7157 |
|
56 |
+
| 0.5527 | 2.0 | 50 | 0.6300 | 0.8130 |
|
57 |
+
| 0.377 | 3.0 | 75 | 0.5489 | 0.8404 |
|
58 |
+
| 0.2202 | 4.0 | 100 | 0.4637 | 0.8753 |
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
+
- Transformers 4.38.1
|
64 |
+
- Pytorch 2.2.1+cu121
|
65 |
+
- Datasets 2.17.1
|
66 |
- Tokenizers 0.15.2
|