Training in progress, step 940000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e7257d85066f44137f90721b6eeea6b47af4fdd60cb740d773a3a975cd64d8
+oid sha256:a0c72fdd0154d524cda12334954eb1e4f193d30dc2134990578a195ba70ede7f
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3151d7e7cec0857fd8c0138e846e83ffe158233cc9712166843e469c2af9c3a
+oid sha256:e0068dc2eb70214cc7f3762f96ca920a8342113b2f223dfdea92c9f41e6012f4
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1557f867cc6f3d40a606a0ce0859f55e4a3fbdcdcb8655429fb299c80a41a4d
+oid sha256:04943bf52360b66fe1cc3a9ed304be65d048fdffb6ef9f94a272755dcb0d94a4
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0e1b3397ffbcdba72f77e0e72529212805b3efe290aff36c3ecd969d87bca4
+oid sha256:3dab84d4b75593cd9349f424c4371ea8ac2493751bc544a294c8ef74a18b08e9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.01503407202525,
-  "global_step": 930000,
+  "epoch": 10.126562796248173,
+  "global_step": 940000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18606,11 +18606,211 @@
       "eval_samples_per_second": 877.459,
       "eval_steps_per_second": 13.752,
       "step": 930000
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 1.1840677154152987e-05,
+      "loss": 0.181,
+      "step": 930500
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 1.1814402460652382e-05,
+      "loss": 0.1811,
+      "step": 931000
+    },
+    {
+      "epoch": 10.03,
+      "eval_loss": 0.17144934833049774,
+      "eval_runtime": 2.7383,
+      "eval_samples_per_second": 838.849,
+      "eval_steps_per_second": 13.147,
+      "step": 931000
+    },
+    {
+      "epoch": 10.03,
+      "learning_rate": 1.178831418397181e-05,
+      "loss": 0.181,
+      "step": 931500
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 1.176241239543558e-05,
+      "loss": 0.181,
+      "step": 932000
+    },
+    {
+      "epoch": 10.04,
+      "eval_loss": 0.17210912704467773,
+      "eval_runtime": 2.6312,
+      "eval_samples_per_second": 872.975,
+      "eval_steps_per_second": 13.682,
+      "step": 932000
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 1.173669716585822e-05,
+      "loss": 0.1809,
+      "step": 932500
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 1.171116856554418e-05,
+      "loss": 0.1809,
+      "step": 933000
+    },
+    {
+      "epoch": 10.05,
+      "eval_loss": 0.17279262840747833,
+      "eval_runtime": 2.687,
+      "eval_samples_per_second": 854.858,
+      "eval_steps_per_second": 13.398,
+      "step": 933000
+    },
+    {
+      "epoch": 10.05,
+      "learning_rate": 1.168582666428768e-05,
+      "loss": 0.1809,
+      "step": 933500
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 1.1660671531372517e-05,
+      "loss": 0.1807,
+      "step": 934000
+    },
+    {
+      "epoch": 10.06,
+      "eval_loss": 0.17214839160442352,
+      "eval_runtime": 2.6862,
+      "eval_samples_per_second": 855.103,
+      "eval_steps_per_second": 13.402,
+      "step": 934000
+    },
+    {
+      "epoch": 10.07,
+      "learning_rate": 1.1635703235571846e-05,
+      "loss": 0.181,
+      "step": 934500
+    },
+    {
+      "epoch": 10.07,
+      "learning_rate": 1.1610921845148052e-05,
+      "loss": 0.1805,
+      "step": 935000
+    },
+    {
+      "epoch": 10.07,
+      "eval_loss": 0.17261220514774323,
+      "eval_runtime": 2.7622,
+      "eval_samples_per_second": 831.593,
+      "eval_steps_per_second": 13.033,
+      "step": 935000
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 1.1586327427852503e-05,
+      "loss": 0.1805,
+      "step": 935500
+    },
+    {
+      "epoch": 10.08,
+      "learning_rate": 1.156192005092539e-05,
+      "loss": 0.1807,
+      "step": 936000
+    },
+    {
+      "epoch": 10.08,
+      "eval_loss": 0.17041905224323273,
+      "eval_runtime": 2.643,
+      "eval_samples_per_second": 869.101,
+      "eval_steps_per_second": 13.621,
+      "step": 936000
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 1.153769978109557e-05,
+      "loss": 0.1806,
+      "step": 936500
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 1.1513666684580308e-05,
+      "loss": 0.1809,
+      "step": 937000
+    },
+    {
+      "epoch": 10.09,
+      "eval_loss": 0.1718713790178299,
+      "eval_runtime": 2.6411,
+      "eval_samples_per_second": 869.707,
+      "eval_steps_per_second": 13.631,
+      "step": 937000
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 1.1489820827085185e-05,
+      "loss": 0.1808,
+      "step": 937500
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 1.1466162273803876e-05,
+      "loss": 0.1809,
+      "step": 938000
+    },
+    {
+      "epoch": 10.1,
+      "eval_loss": 0.17236891388893127,
+      "eval_runtime": 2.4881,
+      "eval_samples_per_second": 923.197,
+      "eval_steps_per_second": 14.469,
+      "step": 938000
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 1.144269108941795e-05,
+      "loss": 0.1808,
+      "step": 938500
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 1.1419407338096732e-05,
+      "loss": 0.1807,
+      "step": 939000
+    },
+    {
+      "epoch": 10.12,
+      "eval_loss": 0.17213864624500275,
+      "eval_runtime": 2.697,
+      "eval_samples_per_second": 851.681,
+      "eval_steps_per_second": 13.348,
+      "step": 939000
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 1.1396311083497103e-05,
+      "loss": 0.1808,
+      "step": 939500
+    },
+    {
+      "epoch": 10.13,
+      "learning_rate": 1.1373402388763346e-05,
+      "loss": 0.1806,
+      "step": 940000
+    },
+    {
+      "epoch": 10.13,
+      "eval_loss": 0.17225030064582825,
+      "eval_runtime": 2.5852,
+      "eval_samples_per_second": 888.512,
+      "eval_steps_per_second": 13.925,
+      "step": 940000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.519269511347128e+22,
+  "total_flos": 6.589369772377475e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3151d7e7cec0857fd8c0138e846e83ffe158233cc9712166843e469c2af9c3a
+oid sha256:e0068dc2eb70214cc7f3762f96ca920a8342113b2f223dfdea92c9f41e6012f4
 size 449471589