End of training

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 0.04,
     "eval_loss": 0.07713703066110611,
-    "eval_runtime": 1039.9476,
-    "eval_samples_per_second": 37.261,
-    "eval_steps_per_second": 4.658,
+    "eval_runtime": 761.1334,
+    "eval_samples_per_second": 50.911,
+    "eval_steps_per_second": 6.364,
     "train_loss": 0.0033295607640092873,
-    "train_runtime": 264.6407,
-    "train_samples_per_second": 442.695,
-    "train_steps_per_second": 55.339
+    "train_runtime": 303.4327,
+    "train_samples_per_second": 386.099,
+    "train_steps_per_second": 48.264
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.04,
     "eval_loss": 0.07713703066110611,
-    "eval_runtime": 1039.9476,
-    "eval_samples_per_second": 37.261,
-    "eval_steps_per_second": 4.658
+    "eval_runtime": 761.1334,
+    "eval_samples_per_second": 50.911,
+    "eval_steps_per_second": 6.364
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.04,
     "train_loss": 0.0033295607640092873,
-    "train_runtime": 264.6407,
-    "train_samples_per_second": 442.695,
-    "train_steps_per_second": 55.339
+    "train_runtime": 303.4327,
+    "train_samples_per_second": 386.099,
+    "train_steps_per_second": 48.264
 }

trainer_state.json

@@ -208,9 +208,9 @@
       "step": 14645,
       "total_flos": 7.904602466056929e+18,
       "train_loss": 0.0033295607640092873,
-      "train_runtime": 264.6407,
-      "train_samples_per_second": 442.695,
-      "train_steps_per_second": 55.339
+      "train_runtime": 303.4327,
+      "train_samples_per_second": 386.099,
+      "train_steps_per_second": 48.264
     }
   ],
   "max_steps": 14645,