End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3011
-- Accuracy: 0.3945
+- Loss: 3.2973
+- Accuracy: 0.3949
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3941733367769055,
-    "eval_loss": 3.3049395084381104,
-    "eval_runtime": 152.0001,
+    "eval_accuracy": 0.39493445025604595,
+    "eval_loss": 3.2973227500915527,
+    "eval_runtime": 185.7489,
     "eval_samples": 18011,
-    "eval_samples_per_second": 118.493,
-    "eval_steps_per_second": 7.408,
-    "perplexity": 27.246893331814494,
-    "total_flos": 7.7680292069376e+17,
-    "train_loss": 3.4601568499392577,
-    "train_runtime": 61802.9922,
-    "train_samples": 297293,
-    "train_samples_per_second": 48.103,
-    "train_steps_per_second": 1.503
+    "eval_samples_per_second": 96.964,
+    "eval_steps_per_second": 6.062,
+    "perplexity": 27.040148691118805,
+    "total_flos": 7.7682904989696e+17,
+    "train_loss": 3.456335383197512,
+    "train_runtime": 80092.1362,
+    "train_samples": 297303,
+    "train_samples_per_second": 37.12,
+    "train_steps_per_second": 1.16
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3941733367769055,
-    "eval_loss": 3.3049395084381104,
-    "eval_runtime": 152.0001,
+    "eval_accuracy": 0.39493445025604595,
+    "eval_loss": 3.2973227500915527,
+    "eval_runtime": 185.7489,
     "eval_samples": 18011,
-    "eval_samples_per_second": 118.493,
-    "eval_steps_per_second": 7.408,
-    "perplexity": 27.246893331814494
+    "eval_samples_per_second": 96.964,
+    "eval_steps_per_second": 6.062,
+    "perplexity": 27.040148691118805
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7680292069376e+17,
-    "train_loss": 3.4601568499392577,
-    "train_runtime": 61802.9922,
-    "train_samples": 297293,
-    "train_samples_per_second": 48.103,
-    "train_steps_per_second": 1.503
+    "total_flos": 7.7682904989696e+17,
+    "train_loss": 3.456335383197512,
+    "train_runtime": 80092.1362,
+    "train_samples": 297303,
+    "train_samples_per_second": 37.12,
+    "train_steps_per_second": 1.16
 }