milkymarky

README.md

@@ -19,8 +19,8 @@ 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 the beans dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0572
-- Accuracy: 0.9850
+- Loss: 0.1622
+- Accuracy: 0.9609
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 4.0,
+    "eval_accuracy": 0.9609375,
+    "eval_loss": 0.16221070289611816,
+    "eval_runtime": 2.1151,
+    "eval_samples_per_second": 60.518,
+    "eval_steps_per_second": 7.565,
     "total_flos": 3.205097416476426e+17,
     "train_loss": 0.12077335517566938,
     "train_runtime": 98.1926,

runs/Jul08_07-18-50_5bc5fb378f1b/events.out.tfevents.1720424130.5bc5fb378f1b.24589.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5e5bb4065bf50d1b546d71a3b70145db38881fb7a16057cd7b4049600f9214
+size 411

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9609375,
+    "eval_loss": 0.16221070289611816,
+    "eval_runtime": 2.1151,
+    "eval_samples_per_second": 60.518,
+    "eval_steps_per_second": 7.565
+}