End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 4.99,
     "eval_accuracy": 0.9984836997725549,
     "eval_loss": 0.00841992162168026,
-    "eval_runtime": 3.7904,
-    "eval_samples_per_second": 695.976,
-    "eval_steps_per_second": 21.898,
+    "eval_runtime": 3.7799,
+    "eval_samples_per_second": 697.905,
+    "eval_steps_per_second": 21.958,
     "train_loss": 0.07950978533641712,
-    "train_runtime": 401.0405,
-    "train_samples_per_second": 295.955,
-    "train_steps_per_second": 2.307
+    "train_runtime": 480.1024,
+    "train_samples_per_second": 247.218,
+    "train_steps_per_second": 1.927
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 4.99,
     "eval_accuracy": 0.9984836997725549,
     "eval_loss": 0.00841992162168026,
-    "eval_runtime": 3.7904,
-    "eval_samples_per_second": 695.976,
-    "eval_steps_per_second": 21.898
+    "eval_runtime": 3.7799,
+    "eval_samples_per_second": 697.905,
+    "eval_steps_per_second": 21.958
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.99,
     "train_loss": 0.07950978533641712,
-    "train_runtime": 401.0405,
-    "train_samples_per_second": 295.955,
-    "train_steps_per_second": 2.307
+    "train_runtime": 480.1024,
+    "train_samples_per_second": 247.218,
+    "train_steps_per_second": 1.927
 }

trainer_state.json

@@ -119,9 +119,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.9844579226686884,
       "eval_loss": 0.056594911962747574,
-      "eval_runtime": 3.9927,
-      "eval_samples_per_second": 660.713,
-      "eval_steps_per_second": 20.788,
+      "eval_runtime": 3.9857,
+      "eval_samples_per_second": 661.869,
+      "eval_steps_per_second": 20.825,
       "step": 185
     },
     {
@@ -242,9 +242,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.9909021986353298,
       "eval_loss": 0.04098781570792198,
-      "eval_runtime": 3.7973,
-      "eval_samples_per_second": 694.71,
-      "eval_steps_per_second": 21.858,
+      "eval_runtime": 3.7805,
+      "eval_samples_per_second": 697.785,
+      "eval_steps_per_second": 21.955,
       "step": 371
     },
     {
@@ -359,9 +359,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.9901440485216073,
       "eval_loss": 0.04609154537320137,
-      "eval_runtime": 3.799,
-      "eval_samples_per_second": 694.397,
-      "eval_steps_per_second": 21.848,
+      "eval_runtime": 3.7832,
+      "eval_samples_per_second": 697.296,
+      "eval_steps_per_second": 21.939,
       "step": 556
     },
     {
@@ -482,9 +482,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.9984836997725549,
       "eval_loss": 0.00841992162168026,
-      "eval_runtime": 3.8253,
-      "eval_samples_per_second": 689.625,
-      "eval_steps_per_second": 21.698,
+      "eval_runtime": 3.7804,
+      "eval_samples_per_second": 697.802,
+      "eval_steps_per_second": 21.955,
       "step": 742
     },
     {
@@ -599,9 +599,9 @@
       "epoch": 4.99,
       "eval_accuracy": 0.9984836997725549,
       "eval_loss": 0.008393567055463791,
-      "eval_runtime": 3.8262,
-      "eval_samples_per_second": 689.451,
-      "eval_steps_per_second": 21.692,
+      "eval_runtime": 3.7999,
+      "eval_samples_per_second": 694.227,
+      "eval_steps_per_second": 21.843,
       "step": 925
     },
     {
@@ -609,9 +609,9 @@
       "step": 925,
       "total_flos": 2.0985718924353213e+18,
       "train_loss": 0.07950978533641712,
-      "train_runtime": 401.0405,
-      "train_samples_per_second": 295.955,
-      "train_steps_per_second": 2.307
+      "train_runtime": 480.1024,
+      "train_samples_per_second": 247.218,
+      "train_steps_per_second": 1.927
     }
   ],
   "max_steps": 925,