Model save

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7291666666666666
+      value: 0.7333333333333333
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5844
-- Accuracy: 0.7292
+- Loss: 0.5721
+- Accuracy: 0.7333
 
 ## Model description
 
@@ -53,11 +53,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- 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
@@ -67,9 +67,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 8    | 0.6175          | 0.7333   |
-| 0.6122        | 2.0   | 16   | 0.5788          | 0.7333   |
-| 0.5704        | 3.0   | 24   | 0.5844          | 0.7292   |
+| No log        | 1.0   | 4    | 0.5773          | 0.7333   |
+| No log        | 2.0   | 8    | 0.5722          | 0.7333   |
+| 0.6255        | 3.0   | 12   | 0.5721          | 0.7333   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c362cc16738347e1249f5e5fec2f4f790c59fe081ff6dded4ac7d92be20fd4
+oid sha256:db8deb248d3eebbc81fd58dec941edb204e79e84985e479801439fbd753a0752
 size 110394865