Model save

all_results.json

@@ -5,12 +5,12 @@
     "eval_runtime": 239.9792,
     "eval_samples_per_second": 200.017,
     "eval_steps_per_second": 3.125,
-    "max_memory_allocated (GB)": 1.61,
-    "memory_allocated (GB)": 1.53,
+    "max_memory_allocated (GB)": 0.97,
+    "memory_allocated (GB)": 0.97,
     "total_flos": 6.324139790696448e+19,
     "total_memory_available (GB)": 126.62,
     "train_loss": 0.0,
-    "train_runtime": 0.0059,
-    "train_samples_per_second": 138946877.277,
-    "train_steps_per_second": 17368423.514
+    "train_runtime": 0.0058,
+    "train_samples_per_second": 139912496.161,
+    "train_steps_per_second": 17489126.318
 }

runs/Nov06_05-35-38_gtown-28NZK54/events.out.tfevents.1730871346.gtown-28NZK54.5786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9b9ba8b2a08feb6634675cb920808b5943b5a932d01b4a7db86b175c007f64
+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": 0.0059,
-    "train_samples_per_second": 138946877.277,
-    "train_steps_per_second": 17368423.514
+    "train_runtime": 0.0058,
+    "train_samples_per_second": 139912496.161,
+    "train_steps_per_second": 17489126.318
 }

trainer_state.json

@@ -2056,9 +2056,9 @@
       "total_flos": 6.324139790696448e+19,
       "total_memory_available (GB)": 126.62,
       "train_loss": 0.0,
-      "train_runtime": 0.0059,
-      "train_samples_per_second": 138946877.277,
-      "train_steps_per_second": 17368423.514
+      "train_runtime": 0.0058,
+      "train_samples_per_second": 139912496.161,
+      "train_steps_per_second": 17489126.318
     }
   ],
   "logging_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d288ef92a768fde4f1071485c821b02a927d0f0d3a19bfd0e86dcaa05b98eb6
+oid sha256:c031d86c7e1ebfb3077464e5fb470d2aba3ca68e9ddda2e9e55c0525444f5136
 size 5112