End of training

.ipynb_checkpoints/preprocessor_config-checkpoint.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
+  }
+}

README.md

@@ -15,9 +15,9 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3769
-- Validation Loss: 0.3429
-- Train Accuracy: 0.917
+- Train Loss: 0.3935
+- Validation Loss: 0.3000
+- Train Accuracy: 0.932
 - Epoch: 4
 
 ## Model description
@@ -44,11 +44,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.8373     | 1.7012          | 0.802          | 0     |
-| 1.2331     | 0.8580          | 0.866          | 1     |
-| 0.7057     | 0.5621          | 0.89           | 2     |
-| 0.4982     | 0.4215          | 0.908          | 3     |
-| 0.3769     | 0.3429          | 0.917          | 4     |
+| 2.8460     | 1.6868          | 0.827          | 0     |
+| 1.2591     | 0.8662          | 0.87           | 1     |
+| 0.7270     | 0.5129          | 0.909          | 2     |
+| 0.5073     | 0.3779          | 0.928          | 3     |
+| 0.3935     | 0.3000          | 0.932          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ba07ff669fe10c61b13040c470de33b18173870e9991024cdeb2d83c487c2d
+oid sha256:28e5d64f441dd47abe3e906286b233a94266f96e33b10ab48c97aa449a63c8b5
 size 343773880