End of training

README.md

@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6142
-- Accuracy: 0.8543
-- Precision: 0.8496
-- Recall: 0.8610
+- Loss: 0.6263
+- Accuracy: 0.8565
+- Precision: 0.8502
+- Recall: 0.8655
 
 ## Model description
 

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 19.05,
+    "eval_accuracy": 0.8565022421524664,
+    "eval_loss": 0.6262843608856201,
+    "eval_precision": 0.8502202643171806,
+    "eval_recall": 0.8654708520179372,
+    "eval_runtime": 90.8066,
+    "eval_samples_per_second": 4.912,
+    "eval_steps_per_second": 1.233
+}

test_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 19.05,
+    "eval_accuracy": 0.8565022421524664,
+    "eval_loss": 0.6262843608856201,
+    "eval_precision": 0.8502202643171806,
+    "eval_recall": 0.8654708520179372,
+    "eval_runtime": 90.8066,
+    "eval_samples_per_second": 4.912,
+    "eval_steps_per_second": 1.233
+}