Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0098
-- Accuracy: 0.5707
+- Loss: 1.0268
+- Accuracy: 0.5779
 
 ## Model description
 
@@ -37,12 +37,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0958        | 1.0   | 104  | 1.0098          | 0.5707   |
+| 1.2002        | 0.98  | 13   | 1.0268          | 0.5779   |
 
 
 ### Framework versions

runs/Mar06_05-53-50_1f48482cd460/events.out.tfevents.1709704431.1f48482cd460.34.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0d3bc80cb22cf17a1a99c53bf0f0961d81008dff93a9bfc9dd75526156de8d
-size 5203
+oid sha256:90416fdb720491b38f3c56f3ebc6b98f4e3b3d78830a6e63d4a20b9a333749d6
+size 5551