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: 3.3040
-- Accuracy: 0.3943
+- Loss: 3.3070
+- Accuracy: 0.3938
 
 ## Model description
 

all_results.json

@@ -2,15 +2,15 @@
     "epoch": 10.0,
     "eval_accuracy": 0.39382314851947947,
     "eval_loss": 3.307018518447876,
-    "eval_runtime": 179.6693,
+    "eval_runtime": 185.3957,
     "eval_samples": 18011,
-    "eval_samples_per_second": 100.245,
-    "eval_steps_per_second": 6.267,
+    "eval_samples_per_second": 97.149,
+    "eval_steps_per_second": 6.073,
     "perplexity": 27.30359882100141,
-    "total_flos": 7.7683166281728e+17,
-    "train_loss": 3.4505478588888865,
-    "train_runtime": 80739.4287,
-    "train_samples": 297304,
-    "train_samples_per_second": 36.823,
-    "train_steps_per_second": 1.151
+    "total_flos": 7.76821211136e+17,
+    "train_loss": 3.458438355611428,
+    "train_runtime": 80109.3033,
+    "train_samples": 297300,
+    "train_samples_per_second": 37.112,
+    "train_steps_per_second": 1.16
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 10.0,
     "eval_accuracy": 0.39382314851947947,
     "eval_loss": 3.307018518447876,
-    "eval_runtime": 179.6693,
+    "eval_runtime": 185.3957,
     "eval_samples": 18011,
-    "eval_samples_per_second": 100.245,
-    "eval_steps_per_second": 6.267,
+    "eval_samples_per_second": 97.149,
+    "eval_steps_per_second": 6.073,
     "perplexity": 27.30359882100141
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7683166281728e+17,
-    "train_loss": 3.4505478588888865,
-    "train_runtime": 80739.4287,
-    "train_samples": 297304,
-    "train_samples_per_second": 36.823,
-    "train_steps_per_second": 1.151
+    "total_flos": 7.76821211136e+17,
+    "train_loss": 3.458438355611428,
+    "train_runtime": 80109.3033,
+    "train_samples": 297300,
+    "train_samples_per_second": 37.112,
+    "train_steps_per_second": 1.16
 }