Run 4. Outer Step 32. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543919,
-    5543923,
-    5543927,
-    5543932,
-    5543936
+    5543941,
+    5543945,
+    5543949,
+    5543954,
+    5543958
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e078ce27dc531711a1644da7d9912a2ac3b4923a45c98ceb2d342b6074fcfb0
+oid sha256:01abfd847ca6548bb7b647256cd2b4d15e7351a243a6b5f9ae57058a1982a6e1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df36c028b9534c3b8c35ef6d60512aceee0ba5b9ca84aace712c2f95715a97cd
+oid sha256:bd046f165d06f1830330f95a1f6567b0841e0ed7b550a91c7c609f38478db939
 size 4040701744