Training in progress, step 18500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9fb59e8fbfc69c16492317f5ee60f5405215bf3710cc750f7a2f0c4d12d9bf
+oid sha256:7d9a3900750d852ef912d4ac403e488e326c033ebb670c82e9bcf1a2a60b073d
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc742b892cf217bc9e7e3a486930ea7a4f5a5347344220eea2891637eb788f6f
+oid sha256:13a30bbde9b4602c5ab8825e275aa2bdaf413702030191e06267677988829194
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3828ff92ca92db6e1595e10a596145a8ed18c8f856c6b9e18b657e809f136b96
+oid sha256:5376bea5aa8f9ef4ec637a1ceab235b8c9ce7715c6e0e96c31bed840be3b0276
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.244173743183483,
-  "global_step": 18000,
+  "epoch": 0.25095634716080195,
+  "global_step": 18500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -222,11 +222,17 @@
       "learning_rate": 0.0,
       "loss": 0.0403,
       "step": 18000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0,
+      "loss": 0.0361,
+      "step": 18500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.880900066554675e+16,
+  "total_flos": 1.933141486023475e+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:e5878a6b386983e4259b3007ace3d8a9312206f02ee3f8ce309de882a6ee2ecf
-size 51277
+oid sha256:063edb9a5890416332d4caf3919f08d6691c1c75227fa729ad77e7020debbf29
+size 51437