Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8950
-- Accuracy: 0.6124
+- Loss: 0.9924
+- Accuracy: 0.5595
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 49.01109090909091,
+    "eval_accuracy": 0.5595238095238095,
+    "eval_loss": 0.9923801422119141,
+    "eval_runtime": 148.7567,
+    "eval_samples_per_second": 5.082,
+    "eval_steps_per_second": 0.639
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 49.01109090909091,
+    "eval_accuracy": 0.5595238095238095,
+    "eval_loss": 0.9923801422119141,
+    "eval_runtime": 148.7567,
+    "eval_samples_per_second": 5.082,
+    "eval_steps_per_second": 0.639
+}