Training in progress, step 500

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 24.787,
     "eval_steps_per_second": 3.168,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.14008638873123205,
-    "train_runtime": 205.5518,
-    "train_samples_per_second": 20.121,
-    "train_steps_per_second": 2.53
+    "train_loss": 0.06151588481779282,
+    "train_runtime": 197.6861,
+    "train_samples_per_second": 20.922,
+    "train_steps_per_second": 2.63
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f628dae392e49320053166930e8ce576c5c4fd8d0ee4b4a1679d70a5926865
+oid sha256:bbc616a8ebde9c8a43408cbf8bb92819e55a24fe82ccffdec4125196b83456d3
 size 343271789

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.14008638873123205,
-    "train_runtime": 205.5518,
-    "train_samples_per_second": 20.121,
-    "train_steps_per_second": 2.53
+    "train_loss": 0.06151588481779282,
+    "train_runtime": 197.6861,
+    "train_samples_per_second": 20.922,
+    "train_steps_per_second": 2.63
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9fa5c5fea34d06e724326459c671507fab501e5b2c57ec670ed85f82dd9b18
+oid sha256:a1b1a182d555c69ac920494e33771f68e20bb20b8964a2669bad9815466cb21c
 size 4155