End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 91263793574628.0,
-    "train_loss": 3.7061752422668595,
-    "train_runtime": 211.1615,
-    "train_samples_per_second": 50.317,
-    "train_steps_per_second": 6.294
+    "epoch": 5.0,
+    "total_flos": 455652065088468.0,
+    "train_loss": 0.550444790271326,
+    "train_runtime": 2279.1408,
+    "train_samples_per_second": 23.309,
+    "train_steps_per_second": 2.916
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7c61975afc2b781be7b3cf6404c3dbeaacce60ba2dccab7dc452eff02c5d2f
+oid sha256:38e1fda67386e1ae38c744bfa19776e76fe99d7437d00eefec8f59303eb1343f
 size 738227065

runs/Mar01_19-02-51_32fcff02b087/events.out.tfevents.1677697568.32fcff02b087.154.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743dd23795eb0c0842915bd2d0c4f4ebe215fe0707339a937918a516cd55351a
-size 41285
+oid sha256:9f5b478fd3998eb4ca5e8c4c3839de8f15fe4f84b8d736a7b3813dd314e16ec1
+size 42276

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 91263793574628.0,
-    "train_loss": 3.7061752422668595,
-    "train_runtime": 211.1615,
-    "train_samples_per_second": 50.317,
-    "train_steps_per_second": 6.294
+    "epoch": 5.0,
+    "total_flos": 455652065088468.0,
+    "train_loss": 0.550444790271326,
+    "train_runtime": 2279.1408,
+    "train_samples_per_second": 23.309,
+    "train_steps_per_second": 2.916
 }