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: 0.3180
+- Loss: 0.1320
 - Accuracy: 1.0
 
 ## Model description
@@ -56,8 +56,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 6
 - eval_batch_size: 6
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -67,13 +65,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 0.4744          | 1.0      |
-| No log        | 2.0   | 3    | 0.4077          | 0.75     |
-| No log        | 3.0   | 5    | 0.3667          | 1.0      |
-| No log        | 4.0   | 6    | 0.3882          | 1.0      |
-| No log        | 5.0   | 7    | 0.3146          | 1.0      |
-| No log        | 6.0   | 9    | 0.2811          | 1.0      |
-| No log        | 6.67  | 10   | 0.3180          | 1.0      |
+| No log        | 1.0   | 3    | 0.2907          | 1.0      |
+| No log        | 2.0   | 6    | 0.3263          | 0.75     |
+| No log        | 3.0   | 9    | 0.1912          | 1.0      |
+| No log        | 4.0   | 12   | 0.1993          | 1.0      |
+| No log        | 5.0   | 15   | 0.1437          | 1.0      |
+| No log        | 6.0   | 18   | 0.1236          | 1.0      |
+| 0.175         | 7.0   | 21   | 0.1102          | 1.0      |
+| 0.175         | 8.0   | 24   | 0.0924          | 1.0      |
+| 0.175         | 9.0   | 27   | 0.1220          | 1.0      |
+| 0.175         | 10.0  | 30   | 0.1320          | 1.0      |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3be6d57721e9695e9305e1cd62f2e216a78cdd9c40e6180bbc6f0f2dcc2890
+oid sha256:429d628b7ca44fa5347e3657fc3211921884e22a478d0a8f2f31bc89a1cf9cfc
 size 343268717