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
@@ -17,7 +19,7 @@ should 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:
-- Loss: 0.0542
+- Loss: 0.0538
 - Accuracy: 0.4973
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.49727767695099817,
+    "eval_loss": 0.05379448086023331,
+    "eval_runtime": 166.1563,
+    "eval_samples_per_second": 228.815,
+    "eval_steps_per_second": 7.156,
+    "total_flos": 8.347401051492786e+19,
+    "train_loss": 0.06811449300626686,
+    "train_runtime": 11899.7505,
+    "train_samples_per_second": 90.523,
+    "train_steps_per_second": 2.829
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.49727767695099817,
+    "eval_loss": 0.05379448086023331,
+    "eval_runtime": 166.1563,
+    "eval_samples_per_second": 228.815,
+    "eval_steps_per_second": 7.156
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 8.347401051492786e+19,
+    "train_loss": 0.06811449300626686,
+    "train_runtime": 11899.7505,
+    "train_samples_per_second": 90.523,
+    "train_steps_per_second": 2.829
+}