End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8199152542372882
+      value: 0.8008474576271186
 ---
 
 <!-- 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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4752
-- Accuracy: 0.8199
+- Loss: 0.4598
+- Accuracy: 0.8008
 
 ## Model description
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 69
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 8
+- 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: 0.05
@@ -68,9 +68,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3876        | 4.51  | 150  | 0.4823          | 0.7542   |
-| 0.229         | 9.02  | 300  | 0.4535          | 0.8157   |
-| 0.1884        | 13.53 | 450  | 0.4752          | 0.8199   |
+| 0.2931        | 9.02  | 150  | 0.4598          | 0.8008   |
 
 
 ### Framework versions