Training in progress, step 17000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba3a0160461bb8e2c20c0b9de88893d8c0545616dd9e7c12658f3aa426c584c
+oid sha256:a895873c589d8ef74083a25253aa8bb231c79cc6b7e919f2db278d0d9b10f224
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a409180467f8625d392f4020ac32fac294e1516ba685f1a696251f9c935e2043
+oid sha256:e557c4cdc6a877ff03f5703d66d819768318824d798b9f8ac7cfa70957f2f021
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308b6a83b9347a3745a60cbde6575e04dba27ee5c7b0df34dea5cabff18429b5
+oid sha256:c1d4c7d28e08121a2c31503b8f1679a5fbf50f06fb30f7ac2fe64ab71dc22d6a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22382593125152608,
-  "global_step": 16500,
+  "epoch": 0.23060853522884506,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,11 +204,17 @@
       "learning_rate": 0.0,
       "loss": 0.0367,
       "step": 16500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0,
+      "loss": 0.0392,
+      "step": 17000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.7241758081482752e+16,
+  "total_flos": 1.7764172276170752e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct16_21-59-35_1b3a04926831/events.out.tfevents.1665958666.1b3a04926831.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7318ac9550c4a4581e99860dc134ac8e4e21aa19e51d5213db1d333d0ae18f0c
-size 50797
+oid sha256:fd4db5ed20b24e89472dc39945e3c89ae92df32f98b1e4634a71cb98d0922c16
+size 50957