Run 2. Outer Step 2. Inner Step 84.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330164,
-    5330169,
-    5330173,
-    5330177,
-    5330181
+    5330212,
+    5330216,
+    5330220,
+    5330224,
+    5330228
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 77,
+  "inner_step": 84,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9311adac72449047be84f8d5eed71b4ada9303f68a3f28f6316f7adfb07874bc
+oid sha256:ffa1e201588a7b5dbc6b0beaeef9cc148c11adaf490f17edd3c1833fc47509fa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fcf2d7ce04ec6c6ea7edd8260a58ca4ed579ee051e42f268aad7648235e723
+oid sha256:30c9d546dbcd3fb8648269591970bd5d40bbdb4a51964eb3ec44d202d1777304
 size 4040701744