Training in progress, step 627000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcee279599082c8a68650ad1c53f4bb657d2b897dd2c1d0868612319cde75796
+oid sha256:30cd8050cb6404088c5716079148dd0da70144e4be8ff9a3d8b384acf70755c2
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53521c1c8772490b5cb2d5d8c6ab3b91167890d8c72a13f392f76a89b461989c
+oid sha256:05ee9a7da46e1a224189b23b0c2c4d8a9bfe97d804c74a078fe32f5d0875aad1
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9af1d58327f3b98fb90089b5c903df49f6da59b9a59983147498acfbd86d89
+oid sha256:76cbb628e04923671f85d7d99e49cf45496fe34ffb57a5111e03658d124a7d16
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2192f49211bf58ce883df0e7bd405a373cbbb533174fb4185824eab5f8061fbe
+oid sha256:6143b27eaf96690bbe891751f24c600c4892dab7823d8c13fb59f1cc963b65c0
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498edb01af42115a97b5c07402b6b7000b65b218d39062b591a164029c7f419c
+oid sha256:58e6a28fc1607a90c71dc0e11a421f4fc6f6121d48134da179bd1cba7f5481db
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.35733084480607,
-  "global_step": 624000,
+  "epoch": 16.435971102326704,
+  "global_step": 627000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7494,11 +7494,47 @@
       "learning_rate": 3.995472520106156e-07,
       "loss": 1.0092,
       "step": 624000
+    },
+    {
+      "epoch": 16.37,
+      "learning_rate": 3.9676599636984005e-07,
+      "loss": 1.0272,
+      "step": 624500
+    },
+    {
+      "epoch": 16.38,
+      "learning_rate": 3.939880732106663e-07,
+      "loss": 1.029,
+      "step": 625000
+    },
+    {
+      "epoch": 16.4,
+      "learning_rate": 3.9121907687375336e-07,
+      "loss": 1.0189,
+      "step": 625500
+    },
+    {
+      "epoch": 16.41,
+      "learning_rate": 3.884645302832277e-07,
+      "loss": 1.0061,
+      "step": 626000
+    },
+    {
+      "epoch": 16.42,
+      "learning_rate": 3.857134048518893e-07,
+      "loss": 1.0061,
+      "step": 626500
+    },
+    {
+      "epoch": 16.44,
+      "learning_rate": 3.8297124131692177e-07,
+      "loss": 1.0129,
+      "step": 627000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.43349897241215e+17,
+  "total_flos": 7.466521265780244e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53521c1c8772490b5cb2d5d8c6ab3b91167890d8c72a13f392f76a89b461989c
+oid sha256:05ee9a7da46e1a224189b23b0c2c4d8a9bfe97d804c74a078fe32f5d0875aad1
 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 sha256:1d7b987b3a06c1cc0ab77c064205df298771d5c61a72a19389b26c22a6e5a180
-size 11181
+oid sha256:66ce0e077eb7226d21856c3aa901ae59cffa1521766d1b609f24e1c4b48cd004
+size 12141