Run 4. Outer Step 29. Inner Step 20.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539136,
-    5539139,
-    5539141,
-    5539143,
-    5539146
+    5539148,
+    5539150,
+    5539153,
+    5539156,
+    5539157,
+    5539159,
+    5539160,
+    5539162,
+    5539165,
+    5539167
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98221c5f993130251fa1868601ca05877e695d4d6515266d1472fa25bfe13192
+oid sha256:ce2988e1523487925f1eb85b7006051209056e8556c8dcc1ab4fa69bb597d5dd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967764014275c855430a3fd1aa73c75ae1545dd5e22ccdc8fc44f25726c9799f
+oid sha256:1971d99f964a7409a1566184008d2823a6e793d937abd7f33145e4d3b2938da6
 size 4040701744