Run 4. Outer Step 52. Inner Step 27.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575828,
-    5575831,
-    5575833,
-    5575835,
-    5575838,
-    5575840,
-    5575841
+    5575844,
+    5575847,
+    5575850,
+    5575851,
+    5575855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91af97f34982687944b9baa0cad0fbab9993bcf4f05cf375eae08781bc39bc3
+oid sha256:93cab72c346bf6f716af376a8350d14f92fb33165fc13ac99d11ddf64c79bbf6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ce06419d6ef0fe19386e92fb56ee34747c698a452a40953a7e25e6b9711b76
+oid sha256:f4fbe4a0215f26c6a9dd2092f24586b809c96bf0ce98c05a5eb2268edb99ed77
 size 4040701744