End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1233
-- Accuracy: 0.8396
+- Loss: 0.7685
+- Accuracy: 0.7754
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.02494719168066,
+    "eval_accuracy": 0.775413176364048,
+    "eval_loss": 0.7684532999992371,
+    "eval_runtime": 167.5463,
+    "eval_samples_per_second": 26.363,
+    "eval_steps_per_second": 3.301
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 39.02494719168066,
+    "eval_accuracy": 0.775413176364048,
+    "eval_loss": 0.7684532999992371,
+    "eval_runtime": 167.5463,
+    "eval_samples_per_second": 26.363,
+    "eval_steps_per_second": 3.301
+}