Training in progress, step 880000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a2010561ae6b219703766f77123488046a173556bad32795a979a0714f6e7c
+oid sha256:86cf27fbaeb2a38de0ef33258b77f6fefbd96bfd63b67353f72569cf9236a376
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70f0274e15c89ba1e5e2f894493b1d0b23475cd923b06c04110b0afc32880fa
+oid sha256:8ff45cd407febf926d10bda98ff4d352e6977480876fc00eacce9c1938f55c43
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55186c11fcb4a70528459949af80ac1b2eb9ca8f4193cbb9f48d92b908839fa5
+oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d368f4f79d735aeb82977d11fd8d84913a3919ff8ecbae0982e3d606c331447e
+oid sha256:ebaa6261431616bb924fa3611c1e782327703255936f9b7e34a1eda29c117895
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.345861726687708,
-  "global_step": 870000,
+  "epoch": 9.457390450910632,
+  "global_step": 880000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17406,11 +17406,211 @@
       "eval_samples_per_second": 841.196,
       "eval_steps_per_second": 13.184,
       "step": 870000
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 1.6321390014277996e-05,
+      "loss": 0.1831,
+      "step": 870500
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 1.6273411576885517e-05,
+      "loss": 0.1836,
+      "step": 871000
+    },
+    {
+      "epoch": 9.36,
+      "eval_loss": 0.17539818584918976,
+      "eval_runtime": 2.6712,
+      "eval_samples_per_second": 859.901,
+      "eval_steps_per_second": 13.477,
+      "step": 871000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 1.6225607365552378e-05,
+      "loss": 0.1831,
+      "step": 871500
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 1.617797751097349e-05,
+      "loss": 0.1832,
+      "step": 872000
+    },
+    {
+      "epoch": 9.37,
+      "eval_loss": 0.1717691868543625,
+      "eval_runtime": 2.6798,
+      "eval_samples_per_second": 857.157,
+      "eval_steps_per_second": 13.434,
+      "step": 872000
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 1.6130522143367032e-05,
+      "loss": 0.1832,
+      "step": 872500
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 1.608324139247421e-05,
+      "loss": 0.1835,
+      "step": 873000
+    },
+    {
+      "epoch": 9.38,
+      "eval_loss": 0.1719122976064682,
+      "eval_runtime": 2.6225,
+      "eval_samples_per_second": 875.898,
+      "eval_steps_per_second": 13.728,
+      "step": 873000
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 1.6036135387558756e-05,
+      "loss": 0.1831,
+      "step": 873500
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 1.5989204257406693e-05,
+      "loss": 0.1833,
+      "step": 874000
+    },
+    {
+      "epoch": 9.39,
+      "eval_loss": 0.17478306591510773,
+      "eval_runtime": 2.6101,
+      "eval_samples_per_second": 880.046,
+      "eval_steps_per_second": 13.793,
+      "step": 874000
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 1.594244813032595e-05,
+      "loss": 0.1829,
+      "step": 874500
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 1.5895867134145974e-05,
+      "loss": 0.1829,
+      "step": 875000
+    },
+    {
+      "epoch": 9.4,
+      "eval_loss": 0.17394264042377472,
+      "eval_runtime": 2.5878,
+      "eval_samples_per_second": 887.623,
+      "eval_steps_per_second": 13.911,
+      "step": 875000
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 1.5849461396217467e-05,
+      "loss": 0.1834,
+      "step": 875500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 1.5803231043411912e-05,
+      "loss": 0.1827,
+      "step": 876000
+    },
+    {
+      "epoch": 9.41,
+      "eval_loss": 0.17351944744586945,
+      "eval_runtime": 2.6686,
+      "eval_samples_per_second": 860.761,
+      "eval_steps_per_second": 13.49,
+      "step": 876000
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 1.575717620212132e-05,
+      "loss": 0.183,
+      "step": 876500
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 1.5711296998257902e-05,
+      "loss": 0.1832,
+      "step": 877000
+    },
+    {
+      "epoch": 9.42,
+      "eval_loss": 0.17347006499767303,
+      "eval_runtime": 2.7428,
+      "eval_samples_per_second": 837.47,
+      "eval_steps_per_second": 13.125,
+      "step": 877000
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 1.5665593557253623e-05,
+      "loss": 0.1833,
+      "step": 877500
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 1.562006600405996e-05,
+      "loss": 0.1829,
+      "step": 878000
+    },
+    {
+      "epoch": 9.44,
+      "eval_loss": 0.1734461635351181,
+      "eval_runtime": 2.6113,
+      "eval_samples_per_second": 879.646,
+      "eval_steps_per_second": 13.786,
+      "step": 878000
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 1.5574714463147512e-05,
+      "loss": 0.1831,
+      "step": 878500
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 1.5529539058505624e-05,
+      "loss": 0.183,
+      "step": 879000
+    },
+    {
+      "epoch": 9.45,
+      "eval_loss": 0.17375677824020386,
+      "eval_runtime": 2.5315,
+      "eval_samples_per_second": 907.374,
+      "eval_steps_per_second": 14.221,
+      "step": 879000
+    },
+    {
+      "epoch": 9.45,
+      "learning_rate": 1.5484539913642175e-05,
+      "loss": 0.1826,
+      "step": 879500
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 1.543971715158307e-05,
+      "loss": 0.1828,
+      "step": 880000
+    },
+    {
+      "epoch": 9.46,
+      "eval_loss": 0.17431409657001495,
+      "eval_runtime": 2.6398,
+      "eval_samples_per_second": 870.144,
+      "eval_steps_per_second": 13.637,
+      "step": 880000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.098673421612561e+22,
+  "total_flos": 6.168773682642908e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70f0274e15c89ba1e5e2f894493b1d0b23475cd923b06c04110b0afc32880fa
+oid sha256:8ff45cd407febf926d10bda98ff4d352e6977480876fc00eacce9c1938f55c43
 size 449471589