Run 4. Outer Step 21. Inner Step 31.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526463,
-    5526469,
-    5526475,
-    5526480,
-    5526486
+    5526492,
+    5526498,
+    5526503,
+    5526509,
+    5526515
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5c5509cc71daecae0c294b9b6b6d20f1cc7916181d8ed88d6c6b229793ca51
+oid sha256:1265a9e371b71f2826195084e000d79c846ab82fbf4b4d2e7ee40a464793c752
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da37e2bcf13762e233f766f8a2f5cad0a8c146770708ed3b0261c9255f661dd
+oid sha256:f0b05fa52087960b0db587c8c7030f38fa089a69765580ec0177f9c7ba88e380
 size 4040701744