Training in progress, step 8500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b024a931dabdb6020b59d49bfba3ba1f585c919b3441c6ce9ff793e0308951
+oid sha256:e405e2276620571ad48d8d30039ac254250be64b58238f43bbfbdb6a4ae9ef33
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11d13abdb8c1adab04561ae1a520906f8e0809907edb46c7f7f51b4380aefe2
+oid sha256:2678c61d137bab5fa74d721616136531139c237c7859adcebeff832eec98b096
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8a79e6b8682a3b96294e50732547883904f035c5b2067ddab3c09016d40479
+oid sha256:9ded256e273468e2a5158119d6afcd8b89dac3cd9e85c79c68cef68912944e0b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10852166363710355,
-  "global_step": 8000,
+  "epoch": 0.11530426761442253,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,11 +102,17 @@
       "learning_rate": 0.0,
       "loss": 0.0358,
       "step": 8000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0,
+      "loss": 0.04,
+      "step": 8500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 8360716771786752.0,
+  "total_flos": 8883130966474752.0,
   "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:f97fe64238913855ea5f87daf64f0c4442dc829b6a20a48dc4f4d9876b2075fb
-size 48125
+oid sha256:85fb361ed3890e950c07588bda7b5b2d0d3185548f63e5e8da88a5cfb055769f
+size 48282