Training in progress, step 4000, checkpoint

last-checkpoint/trainer_state.json

@@ -81,9 +81,9 @@
     {
       "epoch": 0.08,
       "eval_loss": 0.09235642850399017,
-      "eval_runtime": 109.274,
-      "eval_samples_per_second": 18.303,
-      "eval_steps_per_second": 2.288,
+      "eval_runtime": 116.7651,
+      "eval_samples_per_second": 17.128,
+      "eval_steps_per_second": 2.141,
       "step": 500
     },
     {
@@ -159,9 +159,9 @@
     {
       "epoch": 0.16,
       "eval_loss": 0.08949962258338928,
-      "eval_runtime": 109.2536,
-      "eval_samples_per_second": 18.306,
-      "eval_steps_per_second": 2.288,
+      "eval_runtime": 116.7407,
+      "eval_samples_per_second": 17.132,
+      "eval_steps_per_second": 2.141,
       "step": 1000
     },
     {
@@ -237,9 +237,9 @@
     {
       "epoch": 0.24,
       "eval_loss": 0.08808805048465729,
-      "eval_runtime": 109.2355,
-      "eval_samples_per_second": 18.309,
-      "eval_steps_per_second": 2.289,
+      "eval_runtime": 116.8722,
+      "eval_samples_per_second": 17.113,
+      "eval_steps_per_second": 2.139,
       "step": 1500
     },
     {
@@ -315,9 +315,9 @@
     {
       "epoch": 0.32,
       "eval_loss": 0.08704760670661926,
-      "eval_runtime": 109.4348,
-      "eval_samples_per_second": 18.276,
-      "eval_steps_per_second": 2.284,
+      "eval_runtime": 116.8362,
+      "eval_samples_per_second": 17.118,
+      "eval_steps_per_second": 2.14,
       "step": 2000
     },
     {
@@ -393,9 +393,9 @@
     {
       "epoch": 0.4,
       "eval_loss": 0.08615937829017639,
-      "eval_runtime": 109.2621,
-      "eval_samples_per_second": 18.305,
-      "eval_steps_per_second": 2.288,
+      "eval_runtime": 116.9591,
+      "eval_samples_per_second": 17.1,
+      "eval_steps_per_second": 2.137,
       "step": 2500
     },
     {
@@ -471,9 +471,9 @@
     {
       "epoch": 0.48,
       "eval_loss": 0.08551913499832153,
-      "eval_runtime": 109.2626,
-      "eval_samples_per_second": 18.305,
-      "eval_steps_per_second": 2.288,
+      "eval_runtime": 116.545,
+      "eval_samples_per_second": 17.161,
+      "eval_steps_per_second": 2.145,
       "step": 3000
     },
     {
@@ -549,9 +549,9 @@
     {
       "epoch": 0.56,
       "eval_loss": 0.08540560305118561,
-      "eval_runtime": 109.3641,
-      "eval_samples_per_second": 18.288,
-      "eval_steps_per_second": 2.286,
+      "eval_runtime": 116.9131,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 2.138,
       "step": 3500
     },
     {
@@ -627,9 +627,9 @@
     {
       "epoch": 0.64,
       "eval_loss": 0.08466340601444244,
-      "eval_runtime": 109.2066,
-      "eval_samples_per_second": 18.314,
-      "eval_steps_per_second": 2.289,
+      "eval_runtime": 116.6411,
+      "eval_samples_per_second": 17.147,
+      "eval_steps_per_second": 2.143,
       "step": 4000
     }
   ],