Training in progress, step 624000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806be1299dc9f397b015bf45e4e9491d4765b5be56231fa086b220f80466e124
+oid sha256:bcee279599082c8a68650ad1c53f4bb657d2b897dd2c1d0868612319cde75796
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
+oid sha256:53521c1c8772490b5cb2d5d8c6ab3b91167890d8c72a13f392f76a89b461989c
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce33c87ee60e5c5f09d3f93624e4aea152d072fa3e8cb2a51f34ae26cdbcf071
+oid sha256:ee9af1d58327f3b98fb90089b5c903df49f6da59b9a59983147498acfbd86d89
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef3ed6db2003a0d35336f0e4da89c5bcb53719a88d56afdb76ca509399bfcd3
+oid sha256:2192f49211bf58ce883df0e7bd405a373cbbb533174fb4185824eab5f8061fbe
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d821665fd46cc125e074beaa5297a592c3b1a69d3f8eda9777d00bef746240d
+oid sha256:498edb01af42115a97b5c07402b6b7000b65b218d39062b591a164029c7f419c
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.278690587285443,
-  "global_step": 621000,
+  "epoch": 16.35733084480607,
+  "global_step": 624000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7458,11 +7458,47 @@
       "learning_rate": 4.1644903774592405e-07,
       "loss": 1.024,
       "step": 621000
+    },
+    {
+      "epoch": 16.29,
+      "learning_rate": 4.1361466525607436e-07,
+      "loss": 1.0129,
+      "step": 621500
+    },
+    {
+      "epoch": 16.3,
+      "learning_rate": 4.107834474557934e-07,
+      "loss": 1.017,
+      "step": 622000
+    },
+    {
+      "epoch": 16.32,
+      "learning_rate": 4.079610852866661e-07,
+      "loss": 1.0148,
+      "step": 622500
+    },
+    {
+      "epoch": 16.33,
+      "learning_rate": 4.0514759071193235e-07,
+      "loss": 1.0082,
+      "step": 623000
+    },
+    {
+      "epoch": 16.34,
+      "learning_rate": 4.0234297565724334e-07,
+      "loss": 1.0035,
+      "step": 623500
+    },
+    {
+      "epoch": 16.36,
+      "learning_rate": 3.995472520106156e-07,
+      "loss": 1.0092,
+      "step": 624000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.400442013835674e+17,
+  "total_flos": 7.43349897241215e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4467c2e695dbb515cc354d8e7385cc956efa20f7924c326db2a4ecdc2455acee
+oid sha256:53521c1c8772490b5cb2d5d8c6ab3b91167890d8c72a13f392f76a89b461989c
 size 1944201353

runs/Jun02_06-43-44_462ae3634d0f/events.out.tfevents.1685689892.462ae3634d0f.537.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf0201424bc705d483ce8d79fd3c5ea059fa9c2831940cf15877da9e6a36860
-size 10221
+oid sha256:1d7b987b3a06c1cc0ab77c064205df298771d5c61a72a19389b26c22a6e5a180
+size 11181