Training in progress, step 500, checkpoint

last-checkpoint/trainer_state.json

@@ -25,9 +25,9 @@
     {
       "epoch": 0.1662510390689942,
       "eval_loss": 0.4418589174747467,
-      "eval_runtime": 37.2641,
-      "eval_samples_per_second": 13.257,
-      "eval_steps_per_second": 1.664,
+      "eval_runtime": 38.3971,
+      "eval_samples_per_second": 12.866,
+      "eval_steps_per_second": 1.615,
       "step": 100
     },
     {
@@ -47,9 +47,9 @@
     {
       "epoch": 0.3325020781379884,
       "eval_loss": 0.3926239609718323,
-      "eval_runtime": 37.396,
-      "eval_samples_per_second": 13.21,
-      "eval_steps_per_second": 1.658,
+      "eval_runtime": 38.3601,
+      "eval_samples_per_second": 12.878,
+      "eval_steps_per_second": 1.616,
       "step": 200
     },
     {
@@ -69,9 +69,9 @@
     {
       "epoch": 0.49875311720698257,
       "eval_loss": 0.36712247133255005,
-      "eval_runtime": 37.6429,
-      "eval_samples_per_second": 13.123,
-      "eval_steps_per_second": 1.647,
+      "eval_runtime": 38.3686,
+      "eval_samples_per_second": 12.875,
+      "eval_steps_per_second": 1.616,
       "step": 300
     },
     {
@@ -91,9 +91,9 @@
     {
       "epoch": 0.6650041562759768,
       "eval_loss": 0.3487951159477234,
-      "eval_runtime": 37.3276,
-      "eval_samples_per_second": 13.234,
-      "eval_steps_per_second": 1.661,
+      "eval_runtime": 38.1805,
+      "eval_samples_per_second": 12.939,
+      "eval_steps_per_second": 1.624,
       "step": 400
     },
     {
@@ -113,9 +113,9 @@
     {
       "epoch": 0.8312551953449709,
       "eval_loss": 0.3375319242477417,
-      "eval_runtime": 37.2773,
-      "eval_samples_per_second": 13.252,
-      "eval_steps_per_second": 1.663,
+      "eval_runtime": 38.2231,
+      "eval_samples_per_second": 12.924,
+      "eval_steps_per_second": 1.622,
       "step": 500
     }
   ],