End of training

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_loss": NaN,
+    "eval_loss": 0.0,
     "eval_mean_acc": 0.0,
     "eval_median_acc": 0.0,
-    "eval_runtime": 16.2793,
+    "eval_runtime": 17.3951,
     "eval_samples": 18477,
-    "eval_samples_per_second": 1135.001,
-    "eval_steps_per_second": 0.614,
+    "eval_samples_per_second": 1062.195,
+    "eval_steps_per_second": 0.575,
     "train_loss": 0.0,
-    "train_runtime": 124.2018,
+    "train_runtime": 126.9411,
     "train_samples": 100000,
-    "train_samples_per_second": 805.142,
-    "train_steps_per_second": 0.789
+    "train_samples_per_second": 787.767,
+    "train_steps_per_second": 0.772
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": NaN,
+    "eval_loss": 0.0,
     "eval_mean_acc": 0.0,
     "eval_median_acc": 0.0,
-    "eval_runtime": 16.2793,
+    "eval_runtime": 17.3951,
     "eval_samples": 18477,
-    "eval_samples_per_second": 1135.001,
-    "eval_steps_per_second": 0.614
+    "eval_samples_per_second": 1062.195,
+    "eval_steps_per_second": 0.575
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 124.2018,
+    "train_runtime": 126.9411,
     "train_samples": 100000,
-    "train_samples_per_second": 805.142,
-    "train_steps_per_second": 0.789
+    "train_samples_per_second": 787.767,
+    "train_steps_per_second": 0.772
 }

trainer_state.json

@@ -9,12 +9,12 @@
   "log_history": [
     {
       "epoch": 0.51,
-      "eval_loss": NaN,
+      "eval_loss": 0.0,
       "eval_mean_acc": 0.0,
       "eval_median_acc": 0.0,
-      "eval_runtime": 16.276,
-      "eval_samples_per_second": 1135.228,
-      "eval_steps_per_second": 0.614,
+      "eval_runtime": 17.1474,
+      "eval_samples_per_second": 1077.541,
+      "eval_steps_per_second": 0.583,
       "step": 50
     },
     {
@@ -22,9 +22,9 @@
       "step": 98,
       "total_flos": 1.038017592e+16,
       "train_loss": 0.0,
-      "train_runtime": 124.2018,
-      "train_samples_per_second": 805.142,
-      "train_steps_per_second": 0.789
+      "train_runtime": 126.9411,
+      "train_samples_per_second": 787.767,
+      "train_steps_per_second": 0.772
     }
   ],
   "max_steps": 98,