Training in progress, step 500, checkpoint

last-checkpoint/trainer_state.json

@@ -25,9 +25,9 @@
     {
       "epoch": 0.017563888644945992,
       "eval_loss": 0.16095133125782013,
-      "eval_runtime": 172.0049,
-      "eval_samples_per_second": 25.929,
-      "eval_steps_per_second": 3.244,
+      "eval_runtime": 175.5949,
+      "eval_samples_per_second": 25.399,
+      "eval_steps_per_second": 3.178,
       "step": 100
     },
     {
@@ -47,9 +47,9 @@
     {
       "epoch": 0.035127777289891984,
       "eval_loss": 0.14671418070793152,
-      "eval_runtime": 171.7647,
-      "eval_samples_per_second": 25.966,
-      "eval_steps_per_second": 3.249,
+      "eval_runtime": 175.3478,
+      "eval_samples_per_second": 25.435,
+      "eval_steps_per_second": 3.182,
       "step": 200
     },
     {
@@ -69,9 +69,9 @@
     {
       "epoch": 0.052691665934837977,
       "eval_loss": 0.14008501172065735,
-      "eval_runtime": 172.0977,
-      "eval_samples_per_second": 25.916,
-      "eval_steps_per_second": 3.242,
+      "eval_runtime": 175.2345,
+      "eval_samples_per_second": 25.452,
+      "eval_steps_per_second": 3.184,
       "step": 300
     },
     {
@@ -91,9 +91,9 @@
     {
       "epoch": 0.07025555457978397,
       "eval_loss": 0.13591521978378296,
-      "eval_runtime": 171.8998,
-      "eval_samples_per_second": 25.945,
-      "eval_steps_per_second": 3.246,
+      "eval_runtime": 175.0506,
+      "eval_samples_per_second": 25.478,
+      "eval_steps_per_second": 3.188,
       "step": 400
     },
     {
@@ -113,9 +113,9 @@
     {
       "epoch": 0.08781944322472995,
       "eval_loss": 0.13329531252384186,
-      "eval_runtime": 172.0472,
-      "eval_samples_per_second": 25.923,
-      "eval_steps_per_second": 3.243,
+      "eval_runtime": 175.1721,
+      "eval_samples_per_second": 25.461,
+      "eval_steps_per_second": 3.185,
       "step": 500
     }
   ],