End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # food101-vit-base-patch16-224-in21k
 
-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.
+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 food101 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3894
-- Accuracy: 0.9072
+- Loss: 0.3873
+- Accuracy: 0.9035
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9035247524752476,
+    "eval_loss": 0.38733184337615967,
+    "eval_runtime": 228.3973,
+    "eval_samples_per_second": 110.553,
+    "eval_steps_per_second": 13.822,
+    "train_loss": 0.6563277260213383,
+    "train_runtime": 13063.3743,
+    "train_samples_per_second": 57.987,
+    "train_steps_per_second": 7.249
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9035247524752476,
+    "eval_loss": 0.38733184337615967,
+    "eval_runtime": 228.3973,
+    "eval_samples_per_second": 110.553,
+    "eval_steps_per_second": 13.822
+}

runs/Aug12_14-38-34_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723454450.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.339363.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80c657faf420c2cc568e5bb26549d75ffc9660e85c2a4b2b3e258da905e3db9
+size 417

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6563277260213383,
+    "train_runtime": 13063.3743,
+    "train_samples_per_second": 57.987,
+    "train_steps_per_second": 7.249
+}