End of training

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 987700271455806.0,
-    "train_loss": 0.04072496389336196,
-    "train_runtime": 346.2253,
-    "train_samples_per_second": 69.954,
-    "train_steps_per_second": 4.379
+    "train_loss": 0.030514834148902693,
+    "train_runtime": 341.5893,
+    "train_samples_per_second": 70.904,
+    "train_steps_per_second": 4.438
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff22937e2a38e20db8c1e99f80f046226158513358d6e2907b5b94457d0cb321
+oid sha256:e0ba21536af349ff1d431bbcb02ea2ecfe99f95576a7bf69a21a7ccbe6df9b3d
 size 737784566

runs/Apr18_08-45-33_main1/events.out.tfevents.1745992759.main1.4756.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2316500e50f71e21f8664caad6d00820dce37729560f9a94fe3da2bf635552
+size 6975

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 987700271455806.0,
-    "train_loss": 0.04072496389336196,
-    "train_runtime": 346.2253,
-    "train_samples_per_second": 69.954,
-    "train_steps_per_second": 4.379
+    "train_loss": 0.030514834148902693,
+    "train_runtime": 341.5893,
+    "train_samples_per_second": 70.904,
+    "train_steps_per_second": 4.438
 }