Training in progress, step 9000, checkpoint

checkpoint-9000/trainer_state.json

@@ -26,9 +26,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 3.5286149978637695,
-      "eval_runtime": 19.6679,
-      "eval_samples_per_second": 1618.73,
-      "eval_steps_per_second": 6.356,
+      "eval_runtime": 19.6261,
+      "eval_samples_per_second": 1622.178,
+      "eval_steps_per_second": 6.369,
       "step": 496
     },
     {
@@ -41,9 +41,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 3.3015408515930176,
-      "eval_runtime": 19.7709,
-      "eval_samples_per_second": 1610.299,
-      "eval_steps_per_second": 6.322,
+      "eval_runtime": 19.6779,
+      "eval_samples_per_second": 1617.907,
+      "eval_steps_per_second": 6.352,
       "step": 992
     },
     {
@@ -56,9 +56,9 @@
     {
       "epoch": 3.0,
       "eval_loss": 3.2177340984344482,
-      "eval_runtime": 19.6424,
-      "eval_samples_per_second": 1620.83,
-      "eval_steps_per_second": 6.364,
+      "eval_runtime": 19.6725,
+      "eval_samples_per_second": 1618.351,
+      "eval_steps_per_second": 6.354,
       "step": 1488
     },
     {
@@ -71,9 +71,9 @@
     {
       "epoch": 4.0,
       "eval_loss": 3.172600269317627,
-      "eval_runtime": 19.9514,
-      "eval_samples_per_second": 1595.729,
-      "eval_steps_per_second": 6.265,
+      "eval_runtime": 19.983,
+      "eval_samples_per_second": 1593.2,
+      "eval_steps_per_second": 6.255,
       "step": 1984
     },
     {
@@ -86,9 +86,9 @@
     {
       "epoch": 5.0,
       "eval_loss": 3.143342971801758,
-      "eval_runtime": 19.7887,
-      "eval_samples_per_second": 1608.847,
-      "eval_steps_per_second": 6.317,
+      "eval_runtime": 19.7509,
+      "eval_samples_per_second": 1611.929,
+      "eval_steps_per_second": 6.329,
       "step": 2480
     },
     {
@@ -101,9 +101,9 @@
     {
       "epoch": 6.0,
       "eval_loss": 3.122177839279175,
-      "eval_runtime": 20.027,
-      "eval_samples_per_second": 1589.702,
-      "eval_steps_per_second": 6.242,
+      "eval_runtime": 19.7374,
+      "eval_samples_per_second": 1613.03,
+      "eval_steps_per_second": 6.333,
       "step": 2976
     },
     {
@@ -116,9 +116,9 @@
     {
       "epoch": 7.0,
       "eval_loss": 3.110217332839966,
-      "eval_runtime": 21.4316,
-      "eval_samples_per_second": 1485.514,
-      "eval_steps_per_second": 5.832,
+      "eval_runtime": 19.7314,
+      "eval_samples_per_second": 1613.519,
+      "eval_steps_per_second": 6.335,
       "step": 3472
     },
     {
@@ -131,9 +131,9 @@
     {
       "epoch": 8.0,
       "eval_loss": 3.0961976051330566,
-      "eval_runtime": 25.6412,
-      "eval_samples_per_second": 1241.633,
-      "eval_steps_per_second": 4.875,
+      "eval_runtime": 19.9255,
+      "eval_samples_per_second": 1597.8,
+      "eval_steps_per_second": 6.273,
       "step": 3968
     },
     {
@@ -146,9 +146,9 @@
     {
       "epoch": 9.0,
       "eval_loss": 3.093751907348633,
-      "eval_runtime": 25.4277,
-      "eval_samples_per_second": 1252.062,
-      "eval_steps_per_second": 4.916,
+      "eval_runtime": 19.7735,
+      "eval_samples_per_second": 1610.084,
+      "eval_steps_per_second": 6.322,
       "step": 4464
     },
     {
@@ -161,9 +161,9 @@
     {
       "epoch": 10.0,
       "eval_loss": 3.0947883129119873,
-      "eval_runtime": 27.0755,
-      "eval_samples_per_second": 1175.86,
-      "eval_steps_per_second": 4.617,
+      "eval_runtime": 19.7413,
+      "eval_samples_per_second": 1612.712,
+      "eval_steps_per_second": 6.332,
       "step": 4960
     },
     {
@@ -176,9 +176,9 @@
     {
       "epoch": 11.0,
       "eval_loss": 3.1004531383514404,
-      "eval_runtime": 25.2164,
-      "eval_samples_per_second": 1262.553,
-      "eval_steps_per_second": 4.957,
+      "eval_runtime": 19.7085,
+      "eval_samples_per_second": 1615.393,
+      "eval_steps_per_second": 6.342,
       "step": 5456
     },
     {
@@ -191,9 +191,9 @@
     {
       "epoch": 12.0,
       "eval_loss": 3.103127956390381,
-      "eval_runtime": 25.3186,
-      "eval_samples_per_second": 1257.455,
-      "eval_steps_per_second": 4.937,
+      "eval_runtime": 19.9635,
+      "eval_samples_per_second": 1594.759,
+      "eval_steps_per_second": 6.261,
       "step": 5952
     },
     {
@@ -206,9 +206,9 @@
     {
       "epoch": 13.0,
       "eval_loss": 3.1127891540527344,
-      "eval_runtime": 25.1178,
-      "eval_samples_per_second": 1267.507,
-      "eval_steps_per_second": 4.977,
+      "eval_runtime": 19.7496,
+      "eval_samples_per_second": 1612.03,
+      "eval_steps_per_second": 6.329,
       "step": 6448
     },
     {
@@ -221,9 +221,9 @@
     {
       "epoch": 14.0,
       "eval_loss": 3.121568202972412,
-      "eval_runtime": 25.7204,
-      "eval_samples_per_second": 1237.813,
-      "eval_steps_per_second": 4.86,
+      "eval_runtime": 19.7097,
+      "eval_samples_per_second": 1615.292,
+      "eval_steps_per_second": 6.342,
       "step": 6944
     },
     {
@@ -236,9 +236,9 @@
     {
       "epoch": 15.0,
       "eval_loss": 3.133429765701294,
-      "eval_runtime": 20.0808,
-      "eval_samples_per_second": 1585.443,
-      "eval_steps_per_second": 6.225,
+      "eval_runtime": 19.7554,
+      "eval_samples_per_second": 1611.559,
+      "eval_steps_per_second": 6.327,
       "step": 7440
     },
     {
@@ -251,9 +251,9 @@
     {
       "epoch": 16.0,
       "eval_loss": 3.145784616470337,
-      "eval_runtime": 19.9481,
-      "eval_samples_per_second": 1595.99,
-      "eval_steps_per_second": 6.266,
+      "eval_runtime": 19.9093,
+      "eval_samples_per_second": 1599.105,
+      "eval_steps_per_second": 6.278,
       "step": 7936
     },
     {
@@ -266,9 +266,9 @@
     {
       "epoch": 17.0,
       "eval_loss": 3.153964042663574,
-      "eval_runtime": 19.733,
-      "eval_samples_per_second": 1613.388,
-      "eval_steps_per_second": 6.335,
+      "eval_runtime": 19.7382,
+      "eval_samples_per_second": 1612.963,
+      "eval_steps_per_second": 6.333,
       "step": 8432
     },
     {
@@ -281,9 +281,9 @@
     {
       "epoch": 18.0,
       "eval_loss": 3.1646533012390137,
-      "eval_runtime": 19.726,
-      "eval_samples_per_second": 1613.965,
-      "eval_steps_per_second": 6.337,
+      "eval_runtime": 19.7147,
+      "eval_samples_per_second": 1614.886,
+      "eval_steps_per_second": 6.34,
       "step": 8928
     }
   ],

checkpoint-9000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3935421c77a2c0993b65276d4eac518a2796b439d9c09991132ba490295309
+oid sha256:4c0beaf4c8a5b7d39410a27bab89f903a80b445e9952ea5d058c24d8d31577fc
 size 5905