End of training

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 7.0,
     "eval_accuracy": 0.6086399414241259,
     "eval_loss": 0.652438759803772,
-    "eval_runtime": 5.5381,
+    "eval_runtime": 5.4307,
     "eval_samples": 5463,
-    "eval_samples_per_second": 986.44,
-    "eval_steps_per_second": 3.972,
+    "eval_samples_per_second": 1005.942,
+    "eval_steps_per_second": 4.051,
     "train_loss": 0.6110314930772948,
-    "train_runtime": 2246.0309,
+    "train_runtime": 2217.6487,
     "train_samples": 104743,
-    "train_samples_per_second": 2331.735,
-    "train_steps_per_second": 9.127
+    "train_samples_per_second": 2361.578,
+    "train_steps_per_second": 9.244
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "eval_accuracy": 0.6086399414241259,
     "eval_loss": 0.652438759803772,
-    "eval_runtime": 5.5381,
+    "eval_runtime": 5.4307,
     "eval_samples": 5463,
-    "eval_samples_per_second": 986.44,
-    "eval_steps_per_second": 3.972
+    "eval_samples_per_second": 1005.942,
+    "eval_steps_per_second": 4.051
 }

logs/events.out.tfevents.1674306641.serv-3331.3429984.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b6fa0fdfc92a8462f741ce11429bc4851609913cbc4b27e7df3158749ab300
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 7.0,
     "train_loss": 0.6110314930772948,
-    "train_runtime": 2246.0309,
+    "train_runtime": 2217.6487,
     "train_samples": 104743,
-    "train_samples_per_second": 2331.735,
-    "train_steps_per_second": 9.127
+    "train_samples_per_second": 2361.578,
+    "train_steps_per_second": 9.244
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5996705107084019,
       "eval_loss": 0.6577625870704651,
-      "eval_runtime": 5.8921,
-      "eval_samples_per_second": 927.166,
-      "eval_steps_per_second": 3.734,
+      "eval_runtime": 5.6422,
+      "eval_samples_per_second": 968.24,
+      "eval_steps_per_second": 3.899,
       "step": 410
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.6086399414241259,
       "eval_loss": 0.652438759803772,
-      "eval_runtime": 5.6333,
-      "eval_samples_per_second": 969.772,
-      "eval_steps_per_second": 3.905,
+      "eval_runtime": 5.5355,
+      "eval_samples_per_second": 986.904,
+      "eval_steps_per_second": 3.974,
       "step": 820
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.6071755445725792,
       "eval_loss": 0.6553815603256226,
-      "eval_runtime": 6.0135,
-      "eval_samples_per_second": 908.451,
-      "eval_steps_per_second": 3.658,
+      "eval_runtime": 5.4718,
+      "eval_samples_per_second": 998.389,
+      "eval_steps_per_second": 4.021,
       "step": 1230
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.6051619989017024,
       "eval_loss": 0.6619159579277039,
-      "eval_runtime": 5.6649,
-      "eval_samples_per_second": 964.36,
-      "eval_steps_per_second": 3.884,
+      "eval_runtime": 5.4488,
+      "eval_samples_per_second": 1002.613,
+      "eval_steps_per_second": 4.038,
       "step": 1640
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.598572213069742,
       "eval_loss": 0.668364405632019,
-      "eval_runtime": 5.6978,
-      "eval_samples_per_second": 958.799,
-      "eval_steps_per_second": 3.861,
+      "eval_runtime": 5.5979,
+      "eval_samples_per_second": 975.905,
+      "eval_steps_per_second": 3.93,
       "step": 2050
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.5978400146439685,
       "eval_loss": 0.680844783782959,
-      "eval_runtime": 5.7494,
-      "eval_samples_per_second": 950.18,
-      "eval_steps_per_second": 3.826,
+      "eval_runtime": 5.501,
+      "eval_samples_per_second": 993.091,
+      "eval_steps_per_second": 3.999,
       "step": 2460
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.5844773933736043,
       "eval_loss": 0.7068149447441101,
-      "eval_runtime": 5.675,
-      "eval_samples_per_second": 962.642,
-      "eval_steps_per_second": 3.877,
+      "eval_runtime": 5.4741,
+      "eval_samples_per_second": 997.977,
+      "eval_steps_per_second": 4.019,
       "step": 2870
     },
     {
@@ -117,9 +117,9 @@
       "step": 2870,
       "total_flos": 2.328477811133645e+16,
       "train_loss": 0.6110314930772948,
-      "train_runtime": 2246.0309,
-      "train_samples_per_second": 2331.735,
-      "train_steps_per_second": 9.127
+      "train_runtime": 2217.6487,
+      "train_samples_per_second": 2361.578,
+      "train_steps_per_second": 9.244
     }
   ],
   "max_steps": 20500,