End of training

README.md

@@ -17,13 +17,13 @@ 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:
-- eval_loss: 2.7619
-- eval_accuracy: 0.475
-- eval_runtime: 2.0446
-- eval_samples_per_second: 78.255
-- eval_steps_per_second: 4.891
-- epoch: 38.73
-- step: 1549
+- eval_loss: 1.8405
+- eval_accuracy: 0.5563
+- eval_runtime: 2.1774
+- eval_samples_per_second: 73.483
+- eval_steps_per_second: 4.593
+- epoch: 43.75
+- step: 1750
 
 ## Model description
 
@@ -42,7 +42,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8e-08
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280f03a9392bf62d41488b008bd9271ce4696af1b0f0ede9dce995b40417b2ca
+oid sha256:21716885a4d84b9450a6d20e3bb3a18644259ca2ae4fddf391090a1c26660612
 size 343287149

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104cb1447cbc9cea20808e69ee3e4afd0c76af856bd642b8f97ac89b7b73c4ad
+oid sha256:9da5e3add342008c962ddaa72234ce11e028328995882571c91d32bf4e6b0960
 size 4091