End of fine-tuning training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0986
+- Loss: 1.0978
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 9.716417910447761,
-    "eval_loss": 2.1617491245269775,
-    "eval_runtime": 16.2011,
-    "eval_samples_per_second": 1033.94,
-    "eval_steps_per_second": 64.625,
-    "perplexity": 8.686317830153754,
+    "eval_loss": 1.0977526903152466,
+    "eval_runtime": 1.7342,
+    "eval_samples_per_second": 1054.072,
+    "eval_steps_per_second": 16.722,
+    "perplexity": 2.9974223129878887,
     "total_flos": 5406457244811264.0,
     "train_loss": 1.8237198396162553,
     "train_runtime": 182.316,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.996316004911994,
-    "eval_loss": 2.1617491245269775,
-    "eval_runtime": 16.2011,
-    "eval_samples_per_second": 1033.94,
-    "eval_steps_per_second": 64.625,
-    "perplexity": 8.686317830153754
+    "epoch": 9.716417910447761,
+    "eval_loss": 1.0977526903152466,
+    "eval_runtime": 1.7342,
+    "eval_samples_per_second": 1054.072,
+    "eval_steps_per_second": 16.722,
+    "perplexity": 2.9974223129878887
 }