Hugging Face's logo

t1msan
/
swinv2-tiny-patch4-window8-256-Kontur-competition-1.3K

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
t1msan commited on
Commit
afa8abc
•
1 Parent(s): 077103c

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -11
  2. 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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0416
21
 
22
  ## Model description
23
 
@@ -45,21 +45,25 @@ The following hyperparameters were used during training:
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
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | No log | 0.84 | 4 | 0.6306 |
55
- | No log | 1.89 | 9 | 0.4185 |
56
- | 0.6216 | 2.95 | 14 | 0.2351 |
57
- | 0.6216 | 4.0 | 19 | 0.1235 |
58
- | 0.3128 | 4.84 | 23 | 0.0767 |
59
- | 0.3128 | 5.89 | 28 | 0.0676 |
60
- | 0.1492 | 6.95 | 33 | 0.0416 |
61
- | 0.1492 | 8.0 | 38 | 0.0493 |
62
- | 0.1011 | 8.42 | 40 | 0.0504 |
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0237
21
 
22
  ## Model description
23
 
 
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
48
+ - num_epochs: 15
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | No log | 0.84 | 4 | 0.6834 |
55
+ | No log | 1.89 | 9 | 0.4899 |
56
+ | 0.6773 | 2.95 | 14 | 0.2752 |
57
+ | 0.6773 | 4.0 | 19 | 0.1311 |
58
+ | 0.3528 | 4.84 | 23 | 0.0812 |
59
+ | 0.3528 | 5.89 | 28 | 0.0477 |
60
+ | 0.1595 | 6.95 | 33 | 0.0289 |
61
+ | 0.1595 | 8.0 | 38 | 0.0229 |
62
+ | 0.1054 | 8.84 | 42 | 0.0213 |
63
+ | 0.1054 | 9.89 | 47 | 0.0281 |
64
+ | 0.0822 | 10.95 | 52 | 0.0190 |
65
+ | 0.0822 | 12.0 | 57 | 0.0240 |
66
+ | 0.076 | 12.63 | 60 | 0.0237 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9280326f63517a9db1ad5c4a5e6e3d14569416b7735da479d9e827f7d97de1b
3
  size 110350128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1d88189e76bfc2e3c88362f9fcc9c3cf1036466be103d8edf3777d131ce087
3
  size 110350128