End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0956
+- Loss: 0.0681
 - Accuracy: 0.9624
 
 ## Model description
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 65   | 0.1944          | 0.9474   |
-| No log        | 2.0   | 130  | 0.0990          | 0.9549   |
-| No log        | 3.0   | 195  | 0.1107          | 0.9624   |
-| No log        | 4.0   | 260  | 0.0951          | 0.9624   |
-| No log        | 5.0   | 325  | 0.0956          | 0.9624   |
+| No log        | 1.0   | 65   | 0.1897          | 0.9248   |
+| No log        | 2.0   | 130  | 0.0980          | 0.9624   |
+| No log        | 3.0   | 195  | 0.0736          | 0.9699   |
+| No log        | 4.0   | 260  | 0.0687          | 0.9624   |
+| No log        | 5.0   | 325  | 0.0681          | 0.9624   |
 
 
 ### Framework versions

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Dec27_15-46-18_debian/events.out.tfevents.1735314379.debian.208767.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de055d4a69ab52d975ec7d898fe88af06a5aeda60813b21d2c4c2f781905bd8
-size 6755
+oid sha256:84d891f72fbc3dfdc4b24d6741fc44666df324b8519f6f52cb1085fb5b663591
+size 7109