End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7700
-- Accuracy: 0.7306
+- Loss: 0.7635
+- Accuracy: 0.7407
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 198.0,
+    "eval_accuracy": 0.7407407407407407,
+    "eval_loss": 0.7634842991828918,
+    "eval_runtime": 178.6688,
+    "eval_samples_per_second": 1.209,
+    "eval_steps_per_second": 0.151
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 198.0,
+    "eval_accuracy": 0.7407407407407407,
+    "eval_loss": 0.7634842991828918,
+    "eval_runtime": 178.6688,
+    "eval_samples_per_second": 1.209,
+    "eval_steps_per_second": 0.151
+}