thenewsupercell/DF_Image_VIT

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0683
-- F1: 0.6523
+- Loss: 0.0255
+- F1: 0.8152
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_f1": 0.8152492668621701,
+    "eval_loss": 0.02546444721519947,
+    "eval_runtime": 84.6428,
+    "eval_samples_per_second": 120.093,
+    "eval_steps_per_second": 7.514,
+    "total_flos": 2.2832239820043387e+19,
+    "train_loss": 0.018179216772772535,
+    "train_runtime": 6460.7853,
+    "train_samples_per_second": 45.604,
+    "train_steps_per_second": 2.85
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_f1": 0.8152492668621701,
+    "eval_loss": 0.02546444721519947,
+    "eval_runtime": 84.6428,
+    "eval_samples_per_second": 120.093,
+    "eval_steps_per_second": 7.514
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.2832239820043387e+19,
+    "train_loss": 0.018179216772772535,
+    "train_runtime": 6460.7853,
+    "train_samples_per_second": 45.604,
+    "train_steps_per_second": 2.85
+}