Run 3. Outer Step 12. Inner Step 119.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470061,
-    5470063,
-    5470064,
-    5470066,
-    5470067
+    5470107,
+    5470109,
+    5470111,
+    5470112,
+    5470114
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 117,
+  "inner_step": 119,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc32d2579c7d7b70c2196a4c575245b9a6268f383d73b1dfae8499152be13441
+oid sha256:da625aa28bbb140a83d6b085065677022e6140df2eedf2981c15b50e3bd9d5e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5706788aa94e59c593fca1548fbf77f5eaf6b7a630fec6bec11089f8ac748a60
+oid sha256:a6710434cd57854ddbc7623142117b081d9addb26de26f944e173d9461486df4
 size 4040701744