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: 0.5072
+- Loss: 0.5289
 - Accuracy: 0.8188
 
 ## Model description
@@ -58,23 +58,25 @@ The following hyperparameters were used during training:
 - seed: 69
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4952 | 1.16 | 150 | 0.5743 | 0.7009 |
-| 0.4475 | 2.33 | 300 | 0.4772 | 0.7729 |
-| 0.4287 | 3.49 | 450 | 0.4688 | 0.7642 |
-| 0.2978 | 4.65 | 600 | 0.5202 | 0.7707 |
-| 0.3176 | 5.81 | 750 | 0.4475 | 0.7926 |
-| 0.2602 | 6.98 | 900 | 0.4760 | 0.7882 |
-| 0.2526 | 8.14 | 1050 | 0.4766 | 0.8188 |
-| 0.1601 | 9.3 | 1200 | 0.4925 | 0.8122 |
-| 0.1925 | 10.47 | 1350 | 0.5308 | 0.8079 |
-| 0.1343 | 11.63 | 1500 | 0.5072 | 0.8188 |
+| 0.5055 | 1.16 | 150 | 0.5578 | 0.6943 |
+| 0.4352 | 2.33 | 300 | 0.4578 | 0.7817 |
+| 0.4009 | 3.49 | 450 | 0.4632 | 0.7795 |
+| 0.295 | 4.65 | 600 | 0.5191 | 0.7729 |
+| 0.297 | 5.81 | 750 | 0.4560 | 0.7926 |
+| 0.2507 | 6.98 | 900 | 0.4803 | 0.7969 |
+| 0.2317 | 8.14 | 1050 | 0.4836 | 0.7969 |
+| 0.1745 | 9.3 | 1200 | 0.5272 | 0.7860 |
+| 0.1714 | 10.47 | 1350 | 0.5344 | 0.8035 |
+| 0.1437 | 11.63 | 1500 | 0.5477 | 0.7969 |
+| 0.1356 | 12.79 | 1650 | 0.5300 | 0.7904 |
+| 0.1148 | 13.95 | 1800 | 0.5289 | 0.8188 |
 
 
 ### Framework versions