Training in progress, step 27500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636a140761337de33586e9a21e42bde04ccf78e3905efb3737fb77439d316140
+oid sha256:420ff4fe9de1143f6d478acce2666b05167b1e73cbb48f68aa640ad83f974110
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34300868011b0ae8d4d940b6c78f02f5375fb03fe809cc0763c1817533d7b4b
+oid sha256:064dee5bf90775739713e79948b81af1622b4b5b79a6d2a89f1f9b54e8753f88
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0198ca1d3ea955c2a16ca6ff5b0c8e46717a34108b416d28c379658452e750f
+oid sha256:9bcd68158522b3abec65e47068b30ffe1fa7af6ba0e5e50ccb5b0e6178b01211
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3662606147752245,
-  "global_step": 27000,
+  "epoch": 0.3730432187525435,
+  "global_step": 27500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -330,11 +330,17 @@
       "learning_rate": 0.0,
       "loss": 0.0362,
       "step": 27000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0,
+      "loss": 0.0358,
+      "step": 27500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.821245616993075e+16,
+  "total_flos": 2.873487036461875e+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:e0549a2c568fb96a174ccf6d37bdb43b76e3ea861290ac3825a9065f8ab3cd61
-size 54157
+oid sha256:983b4c2526ec0ea143b54713f753237200860008c419787b041b74add0dfeace
+size 54317