End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5625
+      value: 0.5875
 ---
 
 <!-- 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: 1.2464
-- Accuracy: 0.5625
+- Loss: 1.8494
+- Accuracy: 0.5875
 
 ## Model description
 
@@ -62,15 +62,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 50
+- num_epochs: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.1547        | 20.0  | 200  | 1.3886          | 0.4437   |
-| 0.8794        | 40.0  | 400  | 1.2265          | 0.55     |
+| 0.2496        | 100.0 | 1000 | 1.5520          | 0.5125   |
+| 0.1094        | 200.0 | 2000 | 1.6204          | 0.55     |
+| 0.096         | 300.0 | 3000 | 1.9443          | 0.5375   |
+| 0.0543        | 400.0 | 4000 | 2.0227          | 0.5437   |
+| 0.0455        | 500.0 | 5000 | 2.0049          | 0.5563   |
 
 
 ### Framework versions

runs/Sep06_11-46-23_c027da26715b/events.out.tfevents.1725628588.c027da26715b.482.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606c90993e24d709f5868fb79aae9c762140a7798b065018871022bae496d3d2
+size 411