Training in progress, step 603000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428a42c91913879b41a1c2803d998875b9da7f68b57269ba88572bd6d7ce4f64
+oid sha256:7924350aa7b0ef40f7d6a474f587570dc226790bf00568e9c23218d34efafea7
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
+oid sha256:acc7529dd346c8ff89bc38de3cc978fb0d50b278e43d762a8fbf29f855a69d82
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a962056376cc55caa0509a94dce6afead45bd33809ddcfeee2f662b8cd813c4
-size 14511
+oid sha256:ad3efc4595cba42dc788a946613baf66398a880b736516f6252b4e2ec36e45f4
+size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c222d234df96e58f4e769dcdcf413da5cbddf18b696f2ea0f7db071920b58233
+oid sha256:0ad14576306654137543f9b3dec4960f6960720151fa86c828eb19ca18bad036
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4046b8b982634729686d6bf5e39b07e66c1d3c6391448d15bb8c916db29fc5
+oid sha256:4f4f9f9e3abf410947206d3cf2eb5386883eaf03ecc7793d5a1bdcda114c35e9
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.728208784641033,
-  "global_step": 600000,
+  "epoch": 15.806849042161664,
+  "global_step": 603000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7206,11 +7206,47 @@
       "learning_rate": 5.435137855349992e-07,
       "loss": 1.0323,
       "step": 600000
+    },
+    {
+      "epoch": 15.74,
+      "learning_rate": 5.403137338895826e-07,
+      "loss": 1.0327,
+      "step": 600500
+    },
+    {
+      "epoch": 15.75,
+      "learning_rate": 5.371219888310187e-07,
+      "loss": 1.0246,
+      "step": 601000
+    },
+    {
+      "epoch": 15.77,
+      "learning_rate": 5.339449224256996e-07,
+      "loss": 1.0293,
+      "step": 601500
+    },
+    {
+      "epoch": 15.78,
+      "learning_rate": 5.307698144117793e-07,
+      "loss": 1.0265,
+      "step": 602000
+    },
+    {
+      "epoch": 15.79,
+      "learning_rate": 5.276030534388399e-07,
+      "loss": 1.0233,
+      "step": 602500
+    },
+    {
+      "epoch": 15.81,
+      "learning_rate": 5.244509613783047e-07,
+      "loss": 1.0278,
+      "step": 603000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 7.169441382292193e+17,
+  "total_flos": 7.202301206304522e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b080b9b29f961ef52eafaad1999ae2f632518cab5bfbea3cab5786c34f1394b5
+oid sha256:acc7529dd346c8ff89bc38de3cc978fb0d50b278e43d762a8fbf29f855a69d82
 size 1944201353

runs/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:394490a971e3aa4fe7457345f302913ccbdb7dd358e0ce79b6cebace43b0f673
-size 6381
+oid sha256:1265043442cc0302fe0749ab56d51c593485dcf47695ebdeb2d3ec9e330da349
+size 7341