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: 3.3054
-- Accuracy: 0.3943
+- Loss: 3.3094
+- Accuracy: 0.3939
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.39382314851947947,
-    "eval_loss": 3.307018518447876,
-    "eval_runtime": 185.3957,
+    "eval_accuracy": 0.3938669356332687,
+    "eval_loss": 3.3093740940093994,
+    "eval_runtime": 210.502,
     "eval_samples": 18011,
-    "eval_samples_per_second": 97.149,
-    "eval_steps_per_second": 6.073,
-    "perplexity": 27.30359882100141,
-    "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_samples_per_second": 85.562,
+    "eval_steps_per_second": 5.349,
+    "perplexity": 27.367990320873247,
+    "total_flos": 7.7681075945472e+17,
+    "train_loss": 3.481475149870509,
+    "train_runtime": 87526.6739,
+    "train_samples": 297296,
+    "train_samples_per_second": 33.966,
+    "train_steps_per_second": 1.062
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.39382314851947947,
-    "eval_loss": 3.307018518447876,
-    "eval_runtime": 185.3957,
+    "eval_accuracy": 0.3938669356332687,
+    "eval_loss": 3.3093740940093994,
+    "eval_runtime": 210.502,
     "eval_samples": 18011,
-    "eval_samples_per_second": 97.149,
-    "eval_steps_per_second": 6.073,
-    "perplexity": 27.30359882100141
+    "eval_samples_per_second": 85.562,
+    "eval_steps_per_second": 5.349,
+    "perplexity": 27.367990320873247
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "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
+    "total_flos": 7.7681075945472e+17,
+    "train_loss": 3.481475149870509,
+    "train_runtime": 87526.6739,
+    "train_samples": 297296,
+    "train_samples_per_second": 33.966,
+    "train_steps_per_second": 1.062
 }