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: 0.0258
+- Loss: 0.0514
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0601        | 1.5385 | 100  | 0.0598          |
-| 0.0387        | 3.0769 | 200  | 0.0258          |
+| 0.0729        | 1.5385 | 100  | 0.0967          |
+| 0.0125        | 3.0769 | 200  | 0.0514          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d96dfa5d7c39799911bcc79046f06d3b90afe0c6809730ea31462b1044be99c
+oid sha256:42def27e82c24c3eb3b70c7e7f8d9863d73a22bafd8070cf2f6d3ce07a02e772
 size 343227052

runs/Sep08_06-03-29_7f3436e4e877/events.out.tfevents.1725775413.7f3436e4e877.5995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353ee0997d38a475d507028c31799fe9ec81d3bf6185331ab064e9f7ed89d052
+size 11316

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9823efb777d9a5fd1f0447f6e21b95d58c254d5ba0e28a65e999c9f87a33849d
+oid sha256:2ddd603ec345b23977c3d745bcba953fd7c86c2a3a03cf25a80605e5e3d6a5b3
 size 5176