Training in progress, step 3000, checkpoint

checkpoint-3000/trainer_state.json

@@ -26,9 +26,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 6.196061611175537,
-      "eval_runtime": 19.8675,
-      "eval_samples_per_second": 1293.016,
-      "eval_steps_per_second": 5.084,
+      "eval_runtime": 15.8722,
+      "eval_samples_per_second": 1618.49,
+      "eval_steps_per_second": 6.363,
       "step": 400
     },
     {
@@ -41,9 +41,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 5.85089111328125,
-      "eval_runtime": 19.8952,
-      "eval_samples_per_second": 1291.217,
-      "eval_steps_per_second": 5.077,
+      "eval_runtime": 15.8702,
+      "eval_samples_per_second": 1618.694,
+      "eval_steps_per_second": 6.364,
       "step": 800
     },
     {
@@ -56,9 +56,9 @@
     {
       "epoch": 3.0,
       "eval_loss": 5.716405868530273,
-      "eval_runtime": 19.9828,
-      "eval_samples_per_second": 1285.556,
-      "eval_steps_per_second": 5.054,
+      "eval_runtime": 15.8847,
+      "eval_samples_per_second": 1617.216,
+      "eval_steps_per_second": 6.358,
       "step": 1200
     },
     {
@@ -71,9 +71,9 @@
     {
       "epoch": 4.0,
       "eval_loss": 5.620945930480957,
-      "eval_runtime": 19.8762,
-      "eval_samples_per_second": 1292.448,
-      "eval_steps_per_second": 5.081,
+      "eval_runtime": 15.8581,
+      "eval_samples_per_second": 1619.932,
+      "eval_steps_per_second": 6.369,
       "step": 1600
     },
     {
@@ -86,9 +86,9 @@
     {
       "epoch": 5.0,
       "eval_loss": 5.550532817840576,
-      "eval_runtime": 19.812,
-      "eval_samples_per_second": 1296.639,
-      "eval_steps_per_second": 5.098,
+      "eval_runtime": 15.806,
+      "eval_samples_per_second": 1625.264,
+      "eval_steps_per_second": 6.39,
       "step": 2000
     },
     {
@@ -101,9 +101,9 @@
     {
       "epoch": 6.0,
       "eval_loss": 5.495365619659424,
-      "eval_runtime": 19.885,
-      "eval_samples_per_second": 1291.877,
-      "eval_steps_per_second": 5.079,
+      "eval_runtime": 15.9205,
+      "eval_samples_per_second": 1613.576,
+      "eval_steps_per_second": 6.344,
       "step": 2400
     },
     {
@@ -116,9 +116,9 @@
     {
       "epoch": 7.0,
       "eval_loss": 5.454991817474365,
-      "eval_runtime": 19.7619,
-      "eval_samples_per_second": 1299.925,
-      "eval_steps_per_second": 5.111,
+      "eval_runtime": 15.8923,
+      "eval_samples_per_second": 1616.441,
+      "eval_steps_per_second": 6.355,
       "step": 2800
     }
   ],

checkpoint-3000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b078d8226f9a217ccc7c12a996dd0129f468cfb1b8c6998179c8f8fdf41b1d7a
+oid sha256:0bd8a847d4ccae62f28fa03470f7b388a6e051d0adb6cfd0ecec17d5b7bf3549
 size 5905