End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7902542372881356
+      value: 0.8199152542372882
 ---
 
 <!-- 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: 0.5746
-- Accuracy: 0.7903
+- Loss: 0.4752
+- Accuracy: 0.8199
 
 ## Model description
 
@@ -56,25 +56,21 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 69
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 15
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4968        | 1.13  | 150  | 0.5187          | 0.7627   |
-| 0.4266        | 2.26  | 300  | 0.4863          | 0.7627   |
-| 0.3521        | 3.38  | 450  | 0.5066          | 0.7627   |
-| 0.3407        | 4.51  | 600  | 0.4736          | 0.7860   |
-| 0.2895        | 5.64  | 750  | 0.5043          | 0.7712   |
-| 0.2595        | 6.77  | 900  | 0.6222          | 0.7669   |
-| 0.2132        | 7.89  | 1050 | 0.4935          | 0.8008   |
-| 0.2156        | 9.02  | 1200 | 0.5229          | 0.7924   |
-| 0.192         | 10.15 | 1350 | 0.5168          | 0.7881   |
-| 0.1329        | 11.28 | 1500 | 0.5746          | 0.7903   |
+| 0.3876        | 4.51  | 150  | 0.4823          | 0.7542   |
+| 0.229         | 9.02  | 300  | 0.4535          | 0.8157   |
+| 0.1884        | 13.53 | 450  | 0.4752          | 0.8199   |
 
 
 ### Framework versions