End of training

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 3.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.6986985802650452,
-    "eval_runtime": 0.0261,
+    "eval_runtime": 0.0217,
     "eval_samples": 5,
-    "eval_samples_per_second": 191.241,
-    "eval_steps_per_second": 38.248,
+    "eval_samples_per_second": 230.317,
+    "eval_steps_per_second": 46.063,
     "train_loss": 2.285688607541627,
-    "train_runtime": 404.3347,
+    "train_runtime": 426.5716,
     "train_samples": 11651,
-    "train_samples_per_second": 86.446,
-    "train_steps_per_second": 10.81
+    "train_samples_per_second": 81.939,
+    "train_steps_per_second": 10.247
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.6986985802650452,
-    "eval_runtime": 0.0261,
+    "eval_runtime": 0.0217,
     "eval_samples": 5,
-    "eval_samples_per_second": 191.241,
-    "eval_steps_per_second": 38.248
+    "eval_samples_per_second": 230.317,
+    "eval_steps_per_second": 46.063
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.285688607541627,
-    "train_runtime": 404.3347,
+    "train_runtime": 426.5716,
     "train_samples": 11651,
-    "train_samples_per_second": 86.446,
-    "train_steps_per_second": 10.81
+    "train_samples_per_second": 81.939,
+    "train_steps_per_second": 10.247
 }

trainer_state.json

@@ -23,9 +23,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.6000000238418579,
       "eval_loss": 2.099963903427124,
-      "eval_runtime": 0.0837,
-      "eval_samples_per_second": 59.702,
-      "eval_steps_per_second": 11.94,
+      "eval_runtime": 0.0157,
+      "eval_samples_per_second": 319.046,
+      "eval_steps_per_second": 63.809,
       "step": 1457
     },
     {
@@ -50,9 +50,9 @@
       "epoch": 2.0,
       "eval_accuracy": 1.0,
       "eval_loss": 0.9956113696098328,
-      "eval_runtime": 0.0198,
-      "eval_samples_per_second": 252.666,
-      "eval_steps_per_second": 50.533,
+      "eval_runtime": 0.0195,
+      "eval_samples_per_second": 256.73,
+      "eval_steps_per_second": 51.346,
       "step": 2914
     },
     {
@@ -78,8 +78,8 @@
       "eval_accuracy": 1.0,
       "eval_loss": 0.6986985802650452,
       "eval_runtime": 0.0153,
-      "eval_samples_per_second": 326.486,
-      "eval_steps_per_second": 65.297,
+      "eval_samples_per_second": 326.232,
+      "eval_steps_per_second": 65.246,
       "step": 4371
     },
     {
@@ -87,9 +87,9 @@
       "step": 4371,
       "total_flos": 1151412634864512.0,
       "train_loss": 2.285688607541627,
-      "train_runtime": 404.3347,
-      "train_samples_per_second": 86.446,
-      "train_steps_per_second": 10.81
+      "train_runtime": 426.5716,
+      "train_samples_per_second": 81.939,
+      "train_steps_per_second": 10.247
     }
   ],
   "max_steps": 4371,