bombshelll
/

swin-brain-modality-classification

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2790
-- Accuracy: 0.9227
 ## Model description
@@ -47,24 +47,31 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 12
 ### Training results
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 1.2317        | 0.9412  | 12   | 0.8056          | 0.7680   |
-| 0.7321        | 1.9608  | 25   | 0.3427          | 0.8785   |
-| 0.4526        | 2.9804  | 38   | 0.2999          | 0.9116   |
-| 0.3984        | 4.0     | 51   | 0.3048          | 0.8950   |
-| 0.3362        | 4.9412  | 63   | 0.2832          | 0.9061   |
-| 0.3356        | 5.9608  | 76   | 0.2910          | 0.8950   |
-| 0.2958        | 6.9804  | 89   | 0.2802          | 0.9116   |
-| 0.2728        | 8.0     | 102  | 0.2807          | 0.9116   |
-| 0.2605        | 8.9412  | 114  | 0.2815          | 0.9171   |
-| 0.2407        | 9.9608  | 127  | 0.2806          | 0.9171   |
-| 0.2549        | 10.9804 | 140  | 0.2795          | 0.9171   |
-| 0.2549        | 11.2941 | 144  | 0.2790          | 0.9227   |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3453
+- Accuracy: 0.8895
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
 ### Training results
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 1.3069        | 0.9412  | 12   | 1.0000          | 0.6077   |
+| 0.8924        | 1.9608  | 25   | 0.4334          | 0.8785   |
+| 0.5365        | 2.9804  | 38   | 0.3143          | 0.9006   |
+| 0.3814        | 4.0     | 51   | 0.2871          | 0.9116   |
+| 0.3336        | 4.9412  | 63   | 0.2963          | 0.9116   |
+| 0.353         | 5.9608  | 76   | 0.3195          | 0.8729   |
+| 0.3069        | 6.9804  | 89   | 0.2952          | 0.9116   |
+| 0.293         | 8.0     | 102  | 0.3174          | 0.8895   |
+| 0.2667        | 8.9412  | 114  | 0.3226          | 0.8950   |
+| 0.2424        | 9.9608  | 127  | 0.3213          | 0.8895   |
+| 0.2605        | 10.9804 | 140  | 0.3172          | 0.8895   |
+| 0.232         | 12.0    | 153  | 0.3385          | 0.8895   |
+| 0.242         | 12.9412 | 165  | 0.3274          | 0.8950   |
+| 0.215         | 13.9608 | 178  | 0.3385          | 0.8950   |
+| 0.2131        | 14.9804 | 191  | 0.3422          | 0.8950   |
+| 0.201         | 16.0    | 204  | 0.3419          | 0.8785   |
+| 0.1976        | 16.9412 | 216  | 0.3448          | 0.9006   |
+| 0.1886        | 17.9608 | 229  | 0.3460          | 0.8895   |
+| 0.1972        | 18.8235 | 240  | 0.3453          | 0.8895   |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d46575785d0b3af8b49ece2d6d3a0499a7ea7c05c9fea687eaff7efad82a4f
 size 110348984

 version https://git-lfs.github.com/spec/v1
+oid sha256:f213253a0458d53917871fecb5fcba67d79fc84b24a19d9e59bb574d34393f3a
 size 110348984