Run 4. Outer Step 58. Inner Step 6.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586882,
-    5586884,
-    5586885,
-    5586886,
-    5586887,
-    5586889,
-    5586891,
-    5586893,
-    5586896,
-    5586898,
-    5586900
+    5586903,
+    5586906,
+    5586910,
+    5586912,
+    5586915
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5586129,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2b82e772137aa9fa256c2b02f7aad333c021d203219aa3452adf733ecf6fc2
+oid sha256:a352da19563dc1255ecc19aa261f1c6a972cdc01f8b54070cc2ce344a252cad8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f899f1bf844d88d5169c283872968c70f104a12bdb09e15f61a89674515b9c7
+oid sha256:04fa9691292302f00a4db7fc8323c1de5692639952cd2917f9438385fb9dba9c
 size 4040701744