Training in progress, step 370000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44471d6e6546be5ac1a0d86dea95ba4d44ec44baa5148bbd72a7ea895ad69cfc
+oid sha256:c8e6e5d6289bafd465e0f93748ab1bb630e682cf3fe16da7f34107958c699159
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3b9e249ae21e66394d1e5adda08ca3c78e35cfc386e28fe333440be7a14450
+oid sha256:b0f65f9d24c194387d73c6d6206aa2a527cc855b09f2bbd98f42e2d70ffdd0e6
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd407f01a45e91c6a9d73f9ffcc5948c50f62ac1349333301934ceecd28bde2
-size 14439
+oid sha256:a14c2ca87be8d848b5b7a5987a7e41580ee4714e56c6a11b74724ade62186fac
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ca9bf76c7cf63afb390947106325fd549859bdbd17156e672be09fdd4b8f4d
+oid sha256:14c65884de0d108ce0c8462f58d63c86fe3c03bc71ad62ad4517385a4a06be4d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458dbb378f2ef2f1049b9621261d1e352171f603268c570c20cc0831e3c801af
-size 14439
+oid sha256:d71883cda87e2e2a13d7e90ee7788adac16f770d7d78f7236989f184f7851175
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed71a40157ab7c8a370261156f0220243926bfa7450a89c6374ca93f070e4120
-size 14503
+oid sha256:ebafa49c46a1fb807fcc2cd7ad8adabd30b87b658f944a88ac912fe32d5b60d0
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42c32ab3c49e09d799093ca137ee6e22777a2749e499367cd831d70ce83fb58
+oid sha256:540b632982ca1e514de58c2d575a52863f5386c323edbc210ecc94c61bdc1b4b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.497274268175363,
-  "global_step": 360000,
+  "epoch": 5.649976331180234,
+  "global_step": 370000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2670,11 +2670,85 @@
       "eval_samples_per_second": 908.433,
       "eval_steps_per_second": 14.535,
       "step": 360000
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 0.0001161297995343628,
+      "loss": 0.2815,
+      "step": 361000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 0.00011593133379434138,
+      "loss": 0.2815,
+      "step": 362000
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 0.00011573247511501028,
+      "loss": 0.2811,
+      "step": 363000
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 0.00011553322567105619,
+      "loss": 0.2807,
+      "step": 364000
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 0.00011533358764143905,
+      "loss": 0.2808,
+      "step": 365000
+    },
+    {
+      "epoch": 5.57,
+      "eval_runtime": 1.1301,
+      "eval_samples_per_second": 884.842,
+      "eval_steps_per_second": 14.157,
+      "step": 365000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 0.00011513356320936841,
+      "loss": 0.2808,
+      "step": 366000
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 0.00011493315456227943,
+      "loss": 0.2817,
+      "step": 367000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 0.00011473236389180894,
+      "loss": 0.2803,
+      "step": 368000
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 0.00011453119339377154,
+      "loss": 0.2803,
+      "step": 369000
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 0.00011432964526813558,
+      "loss": 0.2817,
+      "step": 370000
+    },
+    {
+      "epoch": 5.65,
+      "eval_runtime": 1.2187,
+      "eval_samples_per_second": 820.56,
+      "eval_steps_per_second": 13.129,
+      "step": 370000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.5236061117517534e+22,
+  "total_flos": 2.5937063727821006e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3b9e249ae21e66394d1e5adda08ca3c78e35cfc386e28fe333440be7a14450
+oid sha256:b0f65f9d24c194387d73c6d6206aa2a527cc855b09f2bbd98f42e2d70ffdd0e6
 size 449471589