Run 4. Outer Step 47. Inner Step 39.

config.json

@@ -268,31 +268,34 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5568254,
-    5568256,
-    5568258,
-    5568260,
-    5568262,
-    5568264,
-    5568265,
-    5568267,
-    5568268,
-    5568270,
-    5568270,
-    5568273,
-    5568275,
-    5568276,
-    5568277,
-    5568279,
-    5568281,
-    5568283
+    5568285,
+    5568287,
+    5568288,
+    5568289,
+    5568291,
+    5568293,
+    5568294,
+    5568295,
+    5568296,
+    5568297,
+    5568299,
+    5568300,
+    5568302,
+    5568303,
+    5568305,
+    5568306,
+    5568306,
+    5568309,
+    5568310,
+    5568311,
+    5568313
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5566279,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f419a9180a059a51e4dbfcaaa714b125da444696fbf6c1020ca059f44dbf4a4
+oid sha256:ff8ff9ca0c19cac34746ecbbb26fb82fae87da33f0d3e1913ec9a70728654b27
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486a48e09e4f1e75a0881fd8922ce93a86e8c29ec77e02f060e7b8e2232f1137
+oid sha256:38c5f6e16ac7b6297a1101fad8910422aad59d6963948b004816e01095a44172
 size 4040701744