Model save
Browse files- README.md +14 -14
- model.safetensors +1 -1
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -37,11 +37,11 @@ More information needed
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 5e-05
|
40 |
-
- train_batch_size:
|
41 |
-
- eval_batch_size:
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 4
|
44 |
-
- total_train_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0036
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 64
|
41 |
+
- eval_batch_size: 64
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 256
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.0593 | 0.99 | 55 | 0.0294 |
|
55 |
+
| 0.0098 | 1.99 | 111 | 0.0315 |
|
56 |
+
| 0.0066 | 3.0 | 167 | 0.0322 |
|
57 |
+
| 0.0179 | 4.0 | 223 | 0.0068 |
|
58 |
+
| 0.0078 | 4.99 | 278 | 0.0033 |
|
59 |
+
| 0.0015 | 5.99 | 334 | 0.0008 |
|
60 |
+
| 0.0017 | 7.0 | 390 | 0.0078 |
|
61 |
+
| 0.0008 | 8.0 | 446 | 0.0027 |
|
62 |
+
| 0.0019 | 8.99 | 501 | 0.0011 |
|
63 |
+
| 0.0014 | 9.87 | 550 | 0.0036 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 347498816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ef65de083575fcc494359641c9fa2457572545838b3c2f5327ff22e10b62390
|
3 |
size 347498816
|