t1msan
/

swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

t1msan commited on Apr 19

Commit

d9697c9

•

1 Parent(s): 9e67b6b

Model save

Files changed (2) hide show

README.md +14 -14
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.0104
 ## Model description
@@ -37,11 +37,11 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 48
-- eval_batch_size: 48
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 192
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.96  | 6    | 0.4819          |
-| 0.5639        | 1.92  | 12   | 0.2242          |
-| 0.5639        | 2.88  | 18   | 0.0641          |
-| 0.1359        | 4.0   | 25   | 0.0782          |
-| 0.031         | 4.96  | 31   | 0.0250          |
-| 0.031         | 5.92  | 37   | 0.0173          |
-| 0.0221        | 6.88  | 43   | 0.0119          |
-| 0.0144        | 8.0   | 50   | 0.0163          |
-| 0.0144        | 8.96  | 56   | 0.0104          |
-| 0.0144        | 9.6   | 60   | 0.0115          |
 ### Framework versions

 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.
 It achieves the following results on the evaluation set:
+- Loss: 0.0036
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 4
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 0.0593        | 0.99  | 55   | 0.0294          |
+| 0.0098        | 1.99  | 111  | 0.0315          |
+| 0.0066        | 3.0   | 167  | 0.0322          |
+| 0.0179        | 4.0   | 223  | 0.0068          |
+| 0.0078        | 4.99  | 278  | 0.0033          |
+| 0.0015        | 5.99  | 334  | 0.0008          |
+| 0.0017        | 7.0   | 390  | 0.0078          |
+| 0.0008        | 8.0   | 446  | 0.0027          |
+| 0.0019        | 8.99  | 501  | 0.0011          |
+| 0.0014        | 9.87  | 550  | 0.0036          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0133cb6e75ff97bca26fee9bde3ac41c3ed98844ec138fc0d67c5348d4c90d
 size 347498816

 version https://git-lfs.github.com/spec/v1
+oid sha256:6ef65de083575fcc494359641c9fa2457572545838b3c2f5327ff22e10b62390
 size 347498816