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. -->
 
 # cifar100-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 cifar100 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3032
-- Accuracy: 0.9269
+- Loss: 0.2945
+- Accuracy: 0.926
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.926,
+    "eval_loss": 0.29454880952835083,
+    "eval_runtime": 54.3337,
+    "eval_samples_per_second": 138.036,
+    "eval_steps_per_second": 17.264,
+    "train_loss": 0.8302146609071148,
+    "train_runtime": 9599.828,
+    "train_samples_per_second": 44.272,
+    "train_steps_per_second": 5.534
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.926,
+    "eval_loss": 0.29454880952835083,
+    "eval_runtime": 54.3337,
+    "eval_samples_per_second": 138.036,
+    "eval_steps_per_second": 17.264
+}

runs/Aug16_13-41-30_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723793008.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.2786854.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dc44e0a0e1b5c7c3400081afba3095ceb6db82b7ebb9562a59568916747bc3
+size 417

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.8302146609071148,
+    "train_runtime": 9599.828,
+    "train_samples_per_second": 44.272,
+    "train_steps_per_second": 5.534
+}