Run 4. Outer Step 58. Inner Step 23.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605018,
-    5605022,
-    5605025,
-    5605029,
-    5605033
+    5605038,
+    5605042,
+    5605046,
+    5605050,
+    5605054,
+    5605058
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e40e33ad5efe55d3b4cc8a23e8859e0a0ce64510fcbcd28e7f5affed8a011a4
+oid sha256:98cca988720472a93bbed03bb7974af5232642f852589fe8872d219a0f5624d0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7237f522695c0730970583f0c6924179b05ee13973399a90448d529774ee6d46
+oid sha256:387ffa978256706e7f0975726742ff537a2819e0b84626003d9ff29682691c1c
 size 4040701744