End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_LM loss": 3.9581172466278076,
+    "eval_Perplexity": "52.36",
+    "eval_loss": 3.9581923484802246,
+    "eval_runtime": 85.3075,
+    "eval_samples_per_second": 20.338,
+    "eval_steps_per_second": 10.175,
+    "total_flos": 1.81336670208e+16,
+    "train_loss": 3.9090830725414265,
+    "train_runtime": 7314.8812,
+    "train_samples_per_second": 9.488,
+    "train_steps_per_second": 4.744
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.81336670208e+16,
+    "train_loss": 3.9090830725414265,
+    "train_runtime": 7314.8812,
+    "train_samples_per_second": 9.488,
+    "train_steps_per_second": 4.744
+}

with_eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_LM loss": 3.9581172466278076,
+    "eval_Perplexity": "52.36",
+    "eval_loss": 3.9581923484802246,
+    "eval_runtime": 85.3075,
+    "eval_samples_per_second": 20.338,
+    "eval_steps_per_second": 10.175
+}