End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 0.7701,
-    "eval_samples_per_second": 172.714,
-    "eval_steps_per_second": 22.076,
+    "eval_runtime": 0.8068,
+    "eval_samples_per_second": 164.846,
+    "eval_steps_per_second": 21.071,
     "train_loss": 0.23564630480913015,
-    "train_runtime": 86.389,
-    "train_samples_per_second": 59.846,
-    "train_steps_per_second": 7.524
+    "train_runtime": 92.709,
+    "train_samples_per_second": 55.766,
+    "train_steps_per_second": 7.011
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 0.7701,
-    "eval_samples_per_second": 172.714,
-    "eval_steps_per_second": 22.076
+    "eval_runtime": 0.8068,
+    "eval_samples_per_second": 164.846,
+    "eval_steps_per_second": 21.071
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
     "train_loss": 0.23564630480913015,
-    "train_runtime": 86.389,
-    "train_samples_per_second": 59.846,
-    "train_steps_per_second": 7.524
+    "train_runtime": 92.709,
+    "train_samples_per_second": 55.766,
+    "train_steps_per_second": 7.011
 }

trainer_state.json

@@ -89,9 +89,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.9624060150375939,
       "eval_loss": 0.23068006336688995,
-      "eval_runtime": 0.7405,
-      "eval_samples_per_second": 179.618,
-      "eval_steps_per_second": 22.959,
+      "eval_runtime": 0.7684,
+      "eval_samples_per_second": 173.093,
+      "eval_steps_per_second": 22.125,
       "step": 130
     },
     {
@@ -176,9 +176,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.9924812030075187,
       "eval_loss": 0.11085593700408936,
-      "eval_runtime": 0.7599,
-      "eval_samples_per_second": 175.032,
-      "eval_steps_per_second": 22.373,
+      "eval_runtime": 0.7745,
+      "eval_samples_per_second": 171.733,
+      "eval_steps_per_second": 21.951,
       "step": 260
     },
     {
@@ -263,9 +263,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
       "eval_loss": 0.1108752116560936,
-      "eval_runtime": 0.7499,
-      "eval_samples_per_second": 177.363,
-      "eval_steps_per_second": 22.67,
+      "eval_runtime": 0.7607,
+      "eval_samples_per_second": 174.831,
+      "eval_steps_per_second": 22.347,
       "step": 390
     },
     {
@@ -350,9 +350,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.9849624060150376,
       "eval_loss": 0.08750259131193161,
-      "eval_runtime": 0.7317,
-      "eval_samples_per_second": 181.777,
-      "eval_steps_per_second": 23.235,
+      "eval_runtime": 0.7575,
+      "eval_samples_per_second": 175.569,
+      "eval_steps_per_second": 22.441,
       "step": 520
     },
     {
@@ -437,9 +437,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.9774436090225563,
       "eval_loss": 0.08863506466150284,
-      "eval_runtime": 0.7357,
-      "eval_samples_per_second": 180.787,
-      "eval_steps_per_second": 23.108,
+      "eval_runtime": 0.7631,
+      "eval_samples_per_second": 174.294,
+      "eval_steps_per_second": 22.278,
       "step": 650
     },
     {
@@ -447,9 +447,9 @@
       "step": 650,
       "total_flos": 4.006371770595533e+17,
       "train_loss": 0.23564630480913015,
-      "train_runtime": 86.389,
-      "train_samples_per_second": 59.846,
-      "train_steps_per_second": 7.524
+      "train_runtime": 92.709,
+      "train_samples_per_second": 55.766,
+      "train_steps_per_second": 7.011
     }
   ],
   "max_steps": 650,