umn-cyber/indobert-hoax-detection

README.md

@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0767
-- Accuracy: 0.9885
-- F1: 0.9879
-- Precision: 0.9886
+- Loss: 0.0457
+- Accuracy: 0.9875
+- F1: 0.9868
+- Precision: 0.9865
 - Recall: 0.9872
 
 ## Model description

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9861299052774019,
-    "eval_f1": 0.9854455094071708,
-    "eval_loss": 0.045191410928964615,
-    "eval_precision": 0.9836995038979447,
+    "eval_accuracy": 0.9874830852503383,
+    "eval_f1": 0.9868467827941699,
+    "eval_loss": 0.04571225121617317,
+    "eval_precision": 0.9864960909737029,
     "eval_recall": 0.9871977240398293,
-    "eval_runtime": 82.3688,
-    "eval_samples_per_second": 35.887,
-    "eval_steps_per_second": 1.129,
+    "eval_runtime": 81.5092,
+    "eval_samples_per_second": 36.266,
+    "eval_steps_per_second": 1.141,
     "total_flos": 3.11005644392448e+16,
-    "train_loss": 0.03944617702703827,
-    "train_runtime": 23402.751,
-    "train_samples_per_second": 10.101,
-    "train_steps_per_second": 0.316
+    "train_loss": 0.03391138697509353,
+    "train_runtime": 20063.9202,
+    "train_samples_per_second": 5.891,
+    "train_steps_per_second": 0.184
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9868020304568528,
-    "eval_f1": 0.9861751152073732,
-    "eval_loss": 0.04318568482995033,
-    "eval_precision": 0.9830388692579505,
-    "eval_recall": 0.9893314366998578,
-    "eval_runtime": 82.3694,
-    "eval_samples_per_second": 35.875,
-    "eval_steps_per_second": 1.129
+    "eval_accuracy": 0.9895093062605753,
+    "eval_f1": 0.9889953851615193,
+    "eval_loss": 0.039101775735616684,
+    "eval_precision": 0.9872430900070872,
+    "eval_recall": 0.9907539118065434,
+    "eval_runtime": 81.401,
+    "eval_samples_per_second": 36.302,
+    "eval_steps_per_second": 1.142
 }

test_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9861299052774019,
-    "eval_f1": 0.9854455094071708,
-    "eval_loss": 0.045191410928964615,
-    "eval_precision": 0.9836995038979447,
+    "eval_accuracy": 0.9874830852503383,
+    "eval_f1": 0.9868467827941699,
+    "eval_loss": 0.04571225121617317,
+    "eval_precision": 0.9864960909737029,
     "eval_recall": 0.9871977240398293,
-    "eval_runtime": 82.3688,
-    "eval_samples_per_second": 35.887,
-    "eval_steps_per_second": 1.129
+    "eval_runtime": 81.5092,
+    "eval_samples_per_second": 36.266,
+    "eval_steps_per_second": 1.141
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 3.11005644392448e+16,
-    "train_loss": 0.03944617702703827,
-    "train_runtime": 23402.751,
-    "train_samples_per_second": 10.101,
-    "train_steps_per_second": 0.316
+    "train_loss": 0.03391138697509353,
+    "train_runtime": 20063.9202,
+    "train_samples_per_second": 5.891,
+    "train_steps_per_second": 0.184
 }