Training in progress, step 880000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e93b07dd856f0dcb5f8d337f717d57dfe290919f17cc810a0ab94d8971b7b8e
+oid sha256:6da5e919e619fc37caeb953290b94918647456cda690ed7144cc7178be39d996
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f95eaff5ba49e944cce01defd24612a1c006bd8b68e7d8b6c201dec46570c0
+oid sha256:ad82584973d0520c6413d732f42ff58e62845f5cbb51b8e6c61b5efa59935b29
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9a5b19b5e6086c1b46537730410e6434224c5e3b8a150ae1f6ffa0b0403da5
+oid sha256:8247214429488e1ea2f48554aadf9d9e15296edc93a8c054713ad6895a659c39
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d406f3a150dc327386b1fe7c40ac833ace65767a7a63b870db21104ccf5eb518
+oid sha256:117f7d200093f36e829666009e11215a545656db39c99ea467c0382946c51c22
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e79e63475cece03ae5d2720177141fff64fcde5033ba647f27c46dc1cce1e92
+oid sha256:85f55aebb09939f1fc3dd2058ded88566ba4348e9d7ff44ef41bb43747cfc1b0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64496346cbbe377de7eb74096cb4a928e4b77370483c82ca56a5a6927676dd2a
-size 14503
+oid sha256:9b627f03b99c458439f40d3224dc9c96157642aba0d132f2a4952c2022aee879
+size 14439

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": 13.285079481423795,
-  "global_step": 870000,
+  "epoch": 13.437781544428665,
+  "global_step": 880000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6444,11 +6444,85 @@
       "eval_samples_per_second": 1133.455,
       "eval_steps_per_second": 18.135,
       "step": 870000
+    },
+    {
+      "epoch": 13.3,
+      "learning_rate": 1.6273411576885517e-05,
+      "loss": 0.2323,
+      "step": 871000
+    },
+    {
+      "epoch": 13.32,
+      "learning_rate": 1.617797751097349e-05,
+      "loss": 0.2322,
+      "step": 872000
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 1.608324139247421e-05,
+      "loss": 0.2335,
+      "step": 873000
+    },
+    {
+      "epoch": 13.35,
+      "learning_rate": 1.5989204257406693e-05,
+      "loss": 0.2329,
+      "step": 874000
+    },
+    {
+      "epoch": 13.36,
+      "learning_rate": 1.5895867134145974e-05,
+      "loss": 0.2325,
+      "step": 875000
+    },
+    {
+      "epoch": 13.36,
+      "eval_runtime": 0.8114,
+      "eval_samples_per_second": 1232.442,
+      "eval_steps_per_second": 19.719,
+      "step": 875000
+    },
+    {
+      "epoch": 13.38,
+      "learning_rate": 1.5803231043411912e-05,
+      "loss": 0.2322,
+      "step": 876000
+    },
+    {
+      "epoch": 13.39,
+      "learning_rate": 1.5711296998257902e-05,
+      "loss": 0.232,
+      "step": 877000
+    },
+    {
+      "epoch": 13.41,
+      "learning_rate": 1.562006600405996e-05,
+      "loss": 0.2322,
+      "step": 878000
+    },
+    {
+      "epoch": 13.42,
+      "learning_rate": 1.5529539058505624e-05,
+      "loss": 0.2317,
+      "step": 879000
+    },
+    {
+      "epoch": 13.44,
+      "learning_rate": 1.543971715158307e-05,
+      "loss": 0.2318,
+      "step": 880000
+    },
+    {
+      "epoch": 13.44,
+      "eval_runtime": 0.8591,
+      "eval_samples_per_second": 1164.009,
+      "eval_steps_per_second": 18.624,
+      "step": 880000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.098714167754268e+22,
+  "total_flos": 6.168814428784615e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f95eaff5ba49e944cce01defd24612a1c006bd8b68e7d8b6c201dec46570c0
+oid sha256:ad82584973d0520c6413d732f42ff58e62845f5cbb51b8e6c61b5efa59935b29
 size 449471589