End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.10625
+      value: 0.40625
 ---
 
 <!-- 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: 2.2890
-- Accuracy: 0.1062
+- Loss: 1.5970
+- Accuracy: 0.4062
 
 ## Model description
 
@@ -52,22 +52,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.005
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 150
+- lr_scheduler_type: linear
 - num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.3152          | 0.1      |
-| No log        | 2.0   | 80   | 2.0998          | 0.0938   |
-| No log        | 3.0   | 120  | 2.1057          | 0.0938   |
+| No log        | 1.0   | 40   | 1.9142          | 0.325    |
+| No log        | 2.0   | 80   | 1.6677          | 0.3812   |
+| No log        | 3.0   | 120  | 1.6038          | 0.4188   |
 
 
 ### Framework versions