End of training

README.md

@@ -4,18 +4,20 @@ base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_keras_callback
 model-index:
-- name: petro-daemon
+- name: volvoDon/petro-daemon
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# petro-daemon
+# volvoDon/petro-daemon
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.7004
+- Train Loss: 1.6516
+- Validation Loss: 1.7445
+- Train Accuracy: 0.2
 - Epoch: 4
 
 ## Model description
@@ -40,13 +42,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Epoch |
-|:----------:|:-----:|
-| 1.9276     | 0     |
-| 1.8672     | 1     |
-| 1.8053     | 2     |
-| 1.7584     | 3     |
-| 1.7004     | 4     |
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 1.8912     | 1.8835          | 0.4            | 0     |
+| 1.8500     | 1.8507          | 0.2            | 1     |
+| 1.8146     | 1.8129          | 0.2            | 2     |
+| 1.7311     | 1.7768          | 0.2            | 3     |
+| 1.6516     | 1.7445          | 0.2            | 4     |
 
 
 ### Framework versions

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "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
+  }
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89c530c3bdc7721b7343822683c0095da2b91588e1641e0005f1a97fea8e993
-size 343485112
+oid sha256:3f38816bea17e19414b428723755746f2b59e64bb737524207ab61674bc6c696
+size 343501496