candylion

README.md

@@ -19,7 +19,7 @@ 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 beans dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0514
+- Loss: 0.0315
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0729        | 1.5385 | 100  | 0.0967          |
-| 0.0125        | 3.0769 | 200  | 0.0514          |
+| 0.0564        | 1.5385 | 100  | 0.0384          |
+| 0.0204        | 3.0769 | 200  | 0.0315          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42def27e82c24c3eb3b70c7e7f8d9863d73a22bafd8070cf2f6d3ce07a02e772
+oid sha256:f8c5fc9d34fbea26d870877bef302661277e23f8cb979d9ef98d4d35573cf5af
 size 343227052

runs/Sep09_10-32-12_2b10e98029e8/events.out.tfevents.1725877936.2b10e98029e8.835.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c626f695820f5634d415d824b8e9ed6957283465229237baaadef1064f3ff64
+size 11316

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddd603ec345b23977c3d745bcba953fd7c86c2a3a03cf25a80605e5e3d6a5b3
+oid sha256:5dc8bd102b29f791a5d17277874c0062304e9352c36d801329f0aee0d696937e
 size 5176