Run 4. Outer Step 49. Inner Step 56.

config.json

@@ -268,32 +268,28 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571302,
-    5571304,
-    5571306,
-    5571307,
-    5571308,
-    5571309,
-    5571310,
-    5571312,
-    5571313,
-    5571315,
-    5571317,
-    5571318,
-    5571319,
-    5571320,
-    5571321,
-    5571322,
-    5571323,
-    5571325,
-    5571327
+    5571329,
+    5571330,
+    5571332,
+    5571334,
+    5571335,
+    5571336,
+    5571338,
+    5571339,
+    5571341,
+    5571343,
+    5571345,
+    5571347,
+    5571348,
+    5571350,
+    5571352
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "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 sha256:947e0569feee419ae4c3d75ef6265862e9849eb5d2bbb60194f10529c4b5b85e
+oid sha256:40b3508a7283546b5ed990315d3518f6ba1dbd2f905c36a5963aae924c8632ce
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094dccd460dfe242057f999a168813406f73a4f7d02fea815e1c37f5fe524056
+oid sha256:6475118e7814745bdf22ca28f6ebdfe4d824c3c0f977544bee0f39173b298a83
 size 4040701744