End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.125
+      value: 0.15625
 ---
 
 <!-- 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: 2.0825
-- Accuracy: 0.125
+- Loss: 2.0560
+- Accuracy: 0.1562
 
 ## Model description
 
@@ -52,23 +52,36 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.0823          | 0.125    |
-| No log        | 2.0   | 80   | 2.0817          | 0.125    |
-| No log        | 3.0   | 120  | 2.0812          | 0.125    |
-| No log        | 4.0   | 160  | 2.0784          | 0.125    |
-| No log        | 5.0   | 200  | 2.0789          | 0.125    |
+| No log        | 1.0   | 10   | 2.0641          | 0.1562   |
+| No log        | 2.0   | 20   | 1.9868          | 0.1562   |
+| No log        | 3.0   | 30   | 1.8525          | 0.1562   |
+| No log        | 4.0   | 40   | 1.7080          | 0.1562   |
+| No log        | 5.0   | 50   | 1.5731          | 0.1375   |
+| No log        | 6.0   | 60   | 1.5035          | 0.1      |
+| No log        | 7.0   | 70   | 1.4341          | 0.0625   |
+| No log        | 8.0   | 80   | 1.3996          | 0.0688   |
+| No log        | 9.0   | 90   | 1.3553          | 0.1062   |
+| No log        | 10.0  | 100  | 1.3415          | 0.1125   |
+| No log        | 11.0  | 110  | 1.3121          | 0.1      |
+| No log        | 12.0  | 120  | 1.2617          | 0.1      |
+| No log        | 13.0  | 130  | 1.2658          | 0.1062   |
+| No log        | 14.0  | 140  | 1.3010          | 0.1125   |
+| No log        | 15.0  | 150  | 1.2777          | 0.1125   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93cb404c6ed21c9c1d0c74afa3844b3345c22b0d623dc9e634665adefe2b7b9f
+oid sha256:601a75c5f3ae7a648fc0317af829a15e3dae8a7abe7b743af76ad5442b6443e9
 size 343287149

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d3ae03e7c0a66c24d9991ed3ccef48b955af026566ef6e1b8e3fdfc212ba74
+oid sha256:3dc8c7bd919a1c6c03b8bcbdfc5af3c9544758a32e402ae739fcfe955cbb2d17
 size 4027