Training in progress, step 890000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86cf27fbaeb2a38de0ef33258b77f6fefbd96bfd63b67353f72569cf9236a376
+oid sha256:683c63bc197cf3bb64f6c2ce95a62fc4f0bf6028b19e6d2e5831707a2f06c758
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff45cd407febf926d10bda98ff4d352e6977480876fc00eacce9c1938f55c43
+oid sha256:40f6901c05f87feaf8e889e20cabff1c85d845893260d2343fe525c0b122a6e9
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044c8fd4cb46d527c7cfde8c2f060ed7dc755348a5dbf6882b40d299eabc87d2
+oid sha256:05ef6355cd8ed257d93bbf3bb6826ffc7fce329c4f54e85b15a0f850c99370ac
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebaa6261431616bb924fa3611c1e782327703255936f9b7e34a1eda29c117895
+oid sha256:2afa6aa14483adb7c817c2439178a198c4680dbfe427eab82def33bea1566914
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.457390450910632,
-  "global_step": 880000,
+  "epoch": 9.568919175133555,
+  "global_step": 890000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17606,11 +17606,211 @@
       "eval_samples_per_second": 870.144,
       "eval_steps_per_second": 13.637,
       "step": 880000
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 1.539507089487205e-05,
+      "loss": 0.183,
+      "step": 880500
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 1.535060126557028e-05,
+      "loss": 0.1829,
+      "step": 881000
+    },
+    {
+      "epoch": 9.47,
+      "eval_loss": 0.17408204078674316,
+      "eval_runtime": 2.6439,
+      "eval_samples_per_second": 868.809,
+      "eval_steps_per_second": 13.617,
+      "step": 881000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 1.5306308385255997e-05,
+      "loss": 0.1827,
+      "step": 881500
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 1.5262192375024284e-05,
+      "loss": 0.1827,
+      "step": 882000
+    },
+    {
+      "epoch": 9.48,
+      "eval_loss": 0.17428572475910187,
+      "eval_runtime": 2.6251,
+      "eval_samples_per_second": 875.0,
+      "eval_steps_per_second": 13.714,
+      "step": 882000
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 1.521825335548661e-05,
+      "loss": 0.1832,
+      "step": 882500
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 1.5174491446770566e-05,
+      "loss": 0.1827,
+      "step": 883000
+    },
+    {
+      "epoch": 9.49,
+      "eval_loss": 0.17153075337409973,
+      "eval_runtime": 2.6515,
+      "eval_samples_per_second": 866.317,
+      "eval_steps_per_second": 13.577,
+      "step": 883000
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 1.5130906768519563e-05,
+      "loss": 0.1827,
+      "step": 883500
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 1.508749943989242e-05,
+      "loss": 0.183,
+      "step": 884000
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.17301537096500397,
+      "eval_runtime": 2.656,
+      "eval_samples_per_second": 864.819,
+      "eval_steps_per_second": 13.554,
+      "step": 884000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 1.5044269579563144e-05,
+      "loss": 0.1825,
+      "step": 884500
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 1.500121730572051e-05,
+      "loss": 0.183,
+      "step": 885000
+    },
+    {
+      "epoch": 9.51,
+      "eval_loss": 0.17374014854431152,
+      "eval_runtime": 2.719,
+      "eval_samples_per_second": 844.787,
+      "eval_steps_per_second": 13.24,
+      "step": 885000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 1.4958342736067783e-05,
+      "loss": 0.1829,
+      "step": 885500
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 1.4915645987822406e-05,
+      "loss": 0.1829,
+      "step": 886000
+    },
+    {
+      "epoch": 9.52,
+      "eval_loss": 0.17604438960552216,
+      "eval_runtime": 2.7026,
+      "eval_samples_per_second": 849.921,
+      "eval_steps_per_second": 13.32,
+      "step": 886000
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 1.4873127177715653e-05,
+      "loss": 0.1827,
+      "step": 886500
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 1.4830786421992347e-05,
+      "loss": 0.1829,
+      "step": 887000
+    },
+    {
+      "epoch": 9.54,
+      "eval_loss": 0.17339639365673065,
+      "eval_runtime": 2.7392,
+      "eval_samples_per_second": 838.573,
+      "eval_steps_per_second": 13.143,
+      "step": 887000
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 1.4788623836410479e-05,
+      "loss": 0.1823,
+      "step": 887500
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 1.4746639536240942e-05,
+      "loss": 0.1824,
+      "step": 888000
+    },
+    {
+      "epoch": 9.55,
+      "eval_loss": 0.17382191121578217,
+      "eval_runtime": 2.7435,
+      "eval_samples_per_second": 837.254,
+      "eval_steps_per_second": 13.122,
+      "step": 888000
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 1.4704833636267232e-05,
+      "loss": 0.1825,
+      "step": 888500
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 1.4663206250785055e-05,
+      "loss": 0.1824,
+      "step": 889000
+    },
+    {
+      "epoch": 9.56,
+      "eval_loss": 0.17390523850917816,
+      "eval_runtime": 2.7145,
+      "eval_samples_per_second": 846.211,
+      "eval_steps_per_second": 13.262,
+      "step": 889000
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 1.4621757493602125e-05,
+      "loss": 0.1826,
+      "step": 889500
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 1.4580487478037748e-05,
+      "loss": 0.1826,
+      "step": 890000
+    },
+    {
+      "epoch": 9.57,
+      "eval_loss": 0.17268939316272736,
+      "eval_runtime": 2.6865,
+      "eval_samples_per_second": 855.002,
+      "eval_steps_per_second": 13.4,
+      "step": 890000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 6.168773682642908e+22,
+  "total_flos": 6.238873943673255e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff45cd407febf926d10bda98ff4d352e6977480876fc00eacce9c1938f55c43
+oid sha256:40f6901c05f87feaf8e889e20cabff1c85d845893260d2343fe525c0b122a6e9
 size 449471589