End of training

README.md

@@ -32,7 +32,7 @@ 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: 2.0764
+- Loss: 2.0823
 - Accuracy: 0.1187
 
 ## Model description
@@ -52,9 +52,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.01
-- train_batch_size: 64
-- eval_batch_size: 64
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 10   | 2.1023          | 0.1      |
-| No log        | 2.0   | 20   | 2.0941          | 0.1      |
-| No log        | 3.0   | 30   | 2.0767          | 0.1187   |
+| No log        | 1.0   | 80   | 2.0822          | 0.1062   |
+| No log        | 2.0   | 160  | 2.0839          | 0.1125   |
+| No log        | 3.0   | 240  | 2.0825          | 0.1187   |
 
 
 ### Framework versions