Training in progress, step 8000, checkpoint

checkpoint-8000/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 2.5,
       "eval_loss": 7.232339382171631,
-      "eval_runtime": 1.6226,
-      "eval_samples_per_second": 1272.646,
-      "eval_steps_per_second": 80.118,
+      "eval_runtime": 3.1848,
+      "eval_samples_per_second": 648.395,
+      "eval_steps_per_second": 40.819,
       "step": 2000
     },
     {
@@ -26,17 +26,17 @@
     {
       "epoch": 5.0,
       "eval_loss": 5.976784706115723,
-      "eval_runtime": 1.6382,
-      "eval_samples_per_second": 1260.5,
-      "eval_steps_per_second": 79.353,
+      "eval_runtime": 3.0375,
+      "eval_samples_per_second": 679.836,
+      "eval_steps_per_second": 42.798,
       "step": 4000
     },
     {
       "epoch": 7.5,
       "eval_loss": 5.826813220977783,
-      "eval_runtime": 3.0373,
-      "eval_samples_per_second": 679.889,
-      "eval_steps_per_second": 42.802,
+      "eval_runtime": 2.9574,
+      "eval_samples_per_second": 698.238,
+      "eval_steps_per_second": 43.957,
       "step": 6000
     },
     {
@@ -49,9 +49,9 @@
     {
       "epoch": 10.0,
       "eval_loss": 5.744414806365967,
-      "eval_runtime": 3.0316,
-      "eval_samples_per_second": 681.153,
-      "eval_steps_per_second": 42.881,
+      "eval_runtime": 2.5747,
+      "eval_samples_per_second": 802.048,
+      "eval_steps_per_second": 50.492,
       "step": 8000
     }
   ],