End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.325
+      value: 0.39375
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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: 1.9385
-- Accuracy: 0.325
+- Loss: 1.8689
+- Accuracy: 0.3937
 
 ## Model description
 
@@ -53,24 +53,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.059         | 1.0   | 10   | 2.0207          | 0.2938   |
-| 1.966         | 2.0   | 20   | 1.9719          | 0.2812   |
-| 1.9101        | 3.0   | 30   | 1.9268          | 0.3563   |
+| 1.8309        | 10.0  | 100  | 1.8611          | 0.35     |
 
 
 ### Framework versions

runs/Sep06_11-30-16_c027da26715b/events.out.tfevents.1725622385.c027da26715b.482.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17893c0c667515f4d8328226be1757e3b4d2ee2ab5ea065baa934aa5a500f5df
+size 405