Training in progress, step 500, checkpoint

last-checkpoint/trainer_state.json

@@ -25,9 +25,9 @@
     {
       "epoch": 0.07024938531787847,
       "eval_loss": 0.22961987555027008,
-      "eval_runtime": 71.5175,
-      "eval_samples_per_second": 62.362,
-      "eval_steps_per_second": 1.958,
+      "eval_runtime": 67.6563,
+      "eval_samples_per_second": 65.921,
+      "eval_steps_per_second": 2.069,
       "step": 100
     },
     {
@@ -47,9 +47,9 @@
     {
       "epoch": 0.14049877063575694,
       "eval_loss": 0.22477279603481293,
-      "eval_runtime": 71.1758,
-      "eval_samples_per_second": 62.662,
-      "eval_steps_per_second": 1.967,
+      "eval_runtime": 67.2438,
+      "eval_samples_per_second": 66.326,
+      "eval_steps_per_second": 2.082,
       "step": 200
     },
     {
@@ -69,9 +69,9 @@
     {
       "epoch": 0.2107481559536354,
       "eval_loss": 0.22264569997787476,
-      "eval_runtime": 71.2392,
-      "eval_samples_per_second": 62.606,
-      "eval_steps_per_second": 1.965,
+      "eval_runtime": 67.1557,
+      "eval_samples_per_second": 66.413,
+      "eval_steps_per_second": 2.085,
       "step": 300
     },
     {
@@ -91,9 +91,9 @@
     {
       "epoch": 0.2809975412715139,
       "eval_loss": 0.22040367126464844,
-      "eval_runtime": 71.1652,
-      "eval_samples_per_second": 62.671,
-      "eval_steps_per_second": 1.967,
+      "eval_runtime": 67.2556,
+      "eval_samples_per_second": 66.314,
+      "eval_steps_per_second": 2.082,
       "step": 400
     },
     {
@@ -113,9 +113,9 @@
     {
       "epoch": 0.3512469265893923,
       "eval_loss": 0.21807625889778137,
-      "eval_runtime": 71.5449,
-      "eval_samples_per_second": 62.338,
-      "eval_steps_per_second": 1.957,
+      "eval_runtime": 67.3281,
+      "eval_samples_per_second": 66.243,
+      "eval_steps_per_second": 2.079,
       "step": 500
     }
   ],