End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 1.462,
-    "eval_samples_per_second": 90.968,
-    "eval_steps_per_second": 11.628,
-    "train_loss": 0.0,
-    "train_runtime": 0.0708,
-    "train_samples_per_second": 72973.629,
-    "train_steps_per_second": 9174.634
+    "eval_runtime": 0.7758,
+    "eval_samples_per_second": 171.437,
+    "eval_steps_per_second": 21.913,
+    "train_loss": 0.23564630480913015,
+    "train_runtime": 101.4306,
+    "train_samples_per_second": 50.971,
+    "train_steps_per_second": 6.408
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 1.462,
-    "eval_samples_per_second": 90.968,
-    "eval_steps_per_second": 11.628
+    "eval_runtime": 0.7758,
+    "eval_samples_per_second": 171.437,
+    "eval_steps_per_second": 21.913
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.0,
-    "train_runtime": 0.0708,
-    "train_samples_per_second": 72973.629,
-    "train_steps_per_second": 9174.634
+    "train_loss": 0.23564630480913015,
+    "train_runtime": 101.4306,
+    "train_samples_per_second": 50.971,
+    "train_steps_per_second": 6.408
 }

trainer_state.json

@@ -89,9 +89,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.9624060150375939,
       "eval_loss": 0.23068006336688995,
-      "eval_runtime": 0.7684,
-      "eval_samples_per_second": 173.093,
-      "eval_steps_per_second": 22.125,
+      "eval_runtime": 0.7854,
+      "eval_samples_per_second": 169.35,
+      "eval_steps_per_second": 21.646,
       "step": 130
     },
     {
@@ -176,9 +176,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.9924812030075187,
       "eval_loss": 0.11085593700408936,
-      "eval_runtime": 0.7745,
-      "eval_samples_per_second": 171.733,
-      "eval_steps_per_second": 21.951,
+      "eval_runtime": 0.7261,
+      "eval_samples_per_second": 183.181,
+      "eval_steps_per_second": 23.414,
       "step": 260
     },
     {
@@ -263,9 +263,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
       "eval_loss": 0.1108752116560936,
-      "eval_runtime": 0.7607,
-      "eval_samples_per_second": 174.831,
-      "eval_steps_per_second": 22.347,
+      "eval_runtime": 0.7271,
+      "eval_samples_per_second": 182.92,
+      "eval_steps_per_second": 23.381,
       "step": 390
     },
     {
@@ -350,9 +350,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.9849624060150376,
       "eval_loss": 0.08750259131193161,
-      "eval_runtime": 0.7575,
-      "eval_samples_per_second": 175.569,
-      "eval_steps_per_second": 22.441,
+      "eval_runtime": 0.7445,
+      "eval_samples_per_second": 178.634,
+      "eval_steps_per_second": 22.833,
       "step": 520
     },
     {
@@ -437,19 +437,19 @@
       "epoch": 5.0,
       "eval_accuracy": 0.9774436090225563,
       "eval_loss": 0.08863506466150284,
-      "eval_runtime": 0.7631,
-      "eval_samples_per_second": 174.294,
-      "eval_steps_per_second": 22.278,
+      "eval_runtime": 0.7378,
+      "eval_samples_per_second": 180.271,
+      "eval_steps_per_second": 23.042,
       "step": 650
     },
     {
       "epoch": 5.0,
       "step": 650,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 0.0,
-      "train_runtime": 0.0708,
-      "train_samples_per_second": 72973.629,
-      "train_steps_per_second": 9174.634
+      "train_loss": 0.23564630480913015,
+      "train_runtime": 101.4306,
+      "train_samples_per_second": 50.971,
+      "train_steps_per_second": 6.408
     }
   ],
   "max_steps": 650,