json files after training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9961612284069098,
     "eval_loss": 0.13847295939922333,
-    "eval_runtime": 35.6829,
-    "eval_samples_per_second": 14.601,
-    "eval_steps_per_second": 0.476,
-    "train_loss": 0.17887740957325904,
-    "train_runtime": 628.2613,
-    "train_samples_per_second": 29.494,
-    "train_steps_per_second": 0.231
+    "eval_runtime": 14.1605,
+    "eval_samples_per_second": 36.792,
+    "eval_steps_per_second": 1.201,
+    "train_loss": 0.17903739583903344,
+    "train_runtime": 421.3317,
+    "train_samples_per_second": 43.98,
+    "train_steps_per_second": 0.344
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9961612284069098,
     "eval_loss": 0.13847295939922333,
-    "eval_runtime": 35.6829,
-    "eval_samples_per_second": 14.601,
-    "eval_steps_per_second": 0.476
+    "eval_runtime": 14.1605,
+    "eval_samples_per_second": 36.792,
+    "eval_steps_per_second": 1.201
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.17887740957325904,
-    "train_runtime": 628.2613,
-    "train_samples_per_second": 29.494,
-    "train_steps_per_second": 0.231
+    "train_loss": 0.17903739583903344,
+    "train_runtime": 421.3317,
+    "train_samples_per_second": 43.98,
+    "train_steps_per_second": 0.344
 }

trainer_state.json

@@ -23,9 +23,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.9961612284069098,
       "eval_loss": 0.13847295939922333,
-      "eval_runtime": 36.4538,
-      "eval_samples_per_second": 14.292,
-      "eval_steps_per_second": 0.466,
+      "eval_runtime": 13.4936,
+      "eval_samples_per_second": 38.611,
+      "eval_steps_per_second": 1.26,
       "step": 29
     },
     {
@@ -37,34 +37,34 @@
     {
       "epoch": 1.38,
       "learning_rate": 2.423076923076923e-05,
-      "loss": 0.151,
+      "loss": 0.1511,
       "step": 40
     },
     {
       "epoch": 1.72,
       "learning_rate": 2.1923076923076924e-05,
-      "loss": 0.1297,
+      "loss": 0.1289,
       "step": 50
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9961612284069098,
-      "eval_loss": 0.051253072917461395,
-      "eval_runtime": 36.428,
-      "eval_samples_per_second": 14.302,
-      "eval_steps_per_second": 0.467,
+      "eval_loss": 0.05099393427371979,
+      "eval_runtime": 13.2879,
+      "eval_samples_per_second": 39.209,
+      "eval_steps_per_second": 1.279,
       "step": 58
     },
     {
       "epoch": 2.07,
       "learning_rate": 1.9615384615384617e-05,
-      "loss": 0.1075,
+      "loss": 0.1076,
       "step": 60
     },
     {
       "epoch": 2.41,
       "learning_rate": 1.7307692307692306e-05,
-      "loss": 0.084,
+      "loss": 0.088,
       "step": 70
     },
     {
@@ -76,10 +76,10 @@
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9884836852207294,
-      "eval_loss": 0.038927894085645676,
-      "eval_runtime": 36.427,
-      "eval_samples_per_second": 14.303,
-      "eval_steps_per_second": 0.467,
+      "eval_loss": 0.043337538838386536,
+      "eval_runtime": 13.6871,
+      "eval_samples_per_second": 38.065,
+      "eval_steps_per_second": 1.242,
       "step": 87
     },
     {
@@ -91,59 +91,59 @@
     {
       "epoch": 3.45,
       "learning_rate": 1.0384615384615384e-05,
-      "loss": 0.0684,
+      "loss": 0.069,
       "step": 100
     },
     {
       "epoch": 3.79,
       "learning_rate": 8.076923076923077e-06,
-      "loss": 0.058,
+      "loss": 0.0605,
       "step": 110
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.9923224568138196,
-      "eval_loss": 0.030210411176085472,
-      "eval_runtime": 36.3815,
-      "eval_samples_per_second": 14.32,
-      "eval_steps_per_second": 0.467,
+      "eval_loss": 0.033004965633153915,
+      "eval_runtime": 13.3003,
+      "eval_samples_per_second": 39.172,
+      "eval_steps_per_second": 1.278,
       "step": 116
     },
     {
       "epoch": 4.14,
       "learning_rate": 5.76923076923077e-06,
-      "loss": 0.0863,
+      "loss": 0.0835,
       "step": 120
     },
     {
       "epoch": 4.48,
       "learning_rate": 3.4615384615384617e-06,
-      "loss": 0.0669,
+      "loss": 0.0671,
       "step": 130
     },
     {
       "epoch": 4.83,
       "learning_rate": 1.153846153846154e-06,
-      "loss": 0.0481,
+      "loss": 0.0479,
       "step": 140
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9942418426103646,
-      "eval_loss": 0.024523714557290077,
-      "eval_runtime": 36.414,
-      "eval_samples_per_second": 14.308,
-      "eval_steps_per_second": 0.467,
+      "eval_accuracy": 0.9904030710172744,
+      "eval_loss": 0.027281073853373528,
+      "eval_runtime": 13.6485,
+      "eval_samples_per_second": 38.173,
+      "eval_steps_per_second": 1.246,
       "step": 145
     },
     {
       "epoch": 5.0,
       "step": 145,
       "total_flos": 1.682270628192e+17,
-      "train_loss": 0.17887740957325904,
-      "train_runtime": 628.2613,
-      "train_samples_per_second": 29.494,
-      "train_steps_per_second": 0.231
+      "train_loss": 0.17903739583903344,
+      "train_runtime": 421.3317,
+      "train_samples_per_second": 43.98,
+      "train_steps_per_second": 0.344
     }
   ],
   "max_steps": 145,