Model save

all_results.json

@@ -10,7 +10,7 @@
     "total_flos": 6.324139790696448e+19,
     "total_memory_available (GB)": 126.62,
     "train_loss": 0.0,
-    "train_runtime": 0.0064,
-    "train_samples_per_second": 127978890.965,
-    "train_steps_per_second": 15997420.185
+    "train_runtime": 81.7036,
+    "train_samples_per_second": 9987.288,
+    "train_steps_per_second": 1248.416
 }

runs/Nov06_05-38-19_gtown-28NZK54/events.out.tfevents.1730871506.gtown-28NZK54.8152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f5e3e7fd0602c8035c7b9554f944d964932262480e3ea538669264d0d540ce
+size 6838

train_results.json

@@ -5,7 +5,7 @@
     "total_flos": 6.324139790696448e+19,
     "total_memory_available (GB)": 126.62,
     "train_loss": 0.0,
-    "train_runtime": 0.0064,
-    "train_samples_per_second": 127978890.965,
-    "train_steps_per_second": 15997420.185
+    "train_runtime": 81.7036,
+    "train_samples_per_second": 9987.288,
+    "train_steps_per_second": 1248.416
 }

trainer_state.json

@@ -2056,9 +2056,9 @@
       "total_flos": 6.324139790696448e+19,
       "total_memory_available (GB)": 126.62,
       "train_loss": 0.0,
-      "train_runtime": 0.0064,
-      "train_samples_per_second": 127978890.965,
-      "train_steps_per_second": 15997420.185
+      "train_runtime": 81.7036,
+      "train_samples_per_second": 9987.288,
+      "train_steps_per_second": 1248.416
     }
   ],
   "logging_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747910e86a10e4e424a7648d170a024ebd9ff1d59ee9461c5e3d6e4bb2931871
+oid sha256:d37dc3a13a8fb7ad81a087d0d8ffa88653daf9eff99f686985fb7661a1ca3212
 size 5112